Knowledge library / Data + MCP

Data for you.
Context for your agent.

Connect your agent to AI Engineer, discover upcoming conferences, research past talks, or download the public data that powers the pages.

6 public collectionsJSON + CSVNo sign-in required

Official AI Engineer MCP

Connect your agent.

Copy the setup for your agent to give it access to public AI Engineer conference information and the talk library. No account, API key, or local server required.

Reading with an agent? Open the Markdown guide, or request /data with Accept: text/markdown or text/plain. Browser requests keep this interactive view.

Remote MCP URL
https://ai.engineer/mcp

Streamable HTTP · No authentication. Paste this URL into a custom connector, or choose your agent below.

Add the server with the Codex CLI, then start a new agent session.

Run in your terminal
codex mcp add ai-engineer --url https://ai.engineer/mcp

Already have MCP servers configured? Keep them and add the ai-engineer entry.

Codex setup docs ↗

After connecting, enable AI Engineer’s tools in your agent and try: “What AI Engineer conferences are coming up?” Your agent chooses and calls the tools for you.

What your agent can do

Explore the conferences. Research the talks.

Conferences are organized by series and edition. Published talks are separate records, connected to speaker profiles, organizations, and topics across the archive.

list_conferences

Find your next conference

List upcoming, ongoing, or past editions. Filter by conference series and year, and get dates, locations, and official ticket and CFP links.

Try asking: Which AI Engineer events are coming up this year?

Valid inputs & outputs

JSON Schema generated from the server’s validators. Input describes tool arguments; output describes successful structuredContent, including unavailable-data variants.

Expand objects to inspect fields and constraints. For alternative responses, use the variant selector. The raw JSON includes every schema keyword.

Raw JSON Schema / Copy
list_conferences input schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"timing": {
"default": "upcoming",
"type": "string",
"enum": [
"all",
"upcoming",
"ongoing",
"past",
"unconfirmed"
]
},
"series": {
"description": "Exact series key returned by list_conferences, for example europe or worldsfair.",
"type": "string",
"maxLength": 50
},
"year": {
"type": "integer",
"minimum": 2023,
"maximum": 2100
}
},
"additionalProperties": false
}

Only fields listed in required are mandatory. additionalProperties: false rejects unknown fields. anyOf lists alternative response shapes; null is different from an omitted field.

  • All fields are optional. Omitted timing means upcoming. Use timing=all to discover valid series keys and edition IDs.
  • Dates and timing may be unconfirmed; publicationStatus is not the event lifecycle. CFP availability is unknown, and ticket purchase is unsupported.
Example request / response

Successful live snapshot from August 28, 2026, without the MCP envelope. Data and versions change.

list_conferences input
{
"timing": "all",
"series": "europe",
"year": 2026
}

list_conferences output
{
"conferences": [
{
"id": "conference:europe/2026",
"series": "europe",
"year": 2026,
"title": "AI Engineer Europe 2026",
"url": "https://ai.engineer/europe/2026",
"location": "London",
"dates": "2026",
"startDate": "2026-04-08",
"endDate": "2026-04-10",
"timing": "past",
"publicationStatus": "active",
"scheduleUrl": "https://ai.engineer/europe/2026/schedule",
"tickets": {
"status": "not_supported",
"message": "Ticket buying is not available through MCP. Consult the official conference page.",
"url": "https://ai.engineer/europe/2026"
},
"cfp": {
"status": "external_portal",
"acceptsSubmissions": null,
"url": "https://ai.engineer/europe/2026/cfp",
"message": "Applications use the conference’s external portal. Check the official page for current availability and deadlines; MCP cannot submit applications."
}
}
],
"asOf": "2026-08-28T06:23:03.999Z"
}

get_schedule

Plan your conference day

Read published sessions for a conference edition, filter by day, and page through the schedule. If structured schedule data is unavailable, the tool says so and links to the official page.

Try asking: Show me the published World’s Fair 2026 schedule.

Valid inputs & outputs

JSON Schema generated from the server’s validators. Input describes tool arguments; output describes successful structuredContent, including unavailable-data variants.

Expand objects to inspect fields and constraints. For alternative responses, use the variant selector. The raw JSON includes every schema keyword.

Raw JSON Schema / Copy
get_schedule input schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"conferenceId": {
"type": "string",
"pattern": "^conference:[a-z0-9-]+\\/\\d{4}$"
},
"day": {
"description": "Exact day label returned by the schedule; not necessarily an ISO date.",
"type": "string",
"maxLength": 100
},
"offset": {
"default": 0,
"description": "Pass the previous nextOffset to continue.",
"type": "integer",
"minimum": 0,
"maximum": 100000
},
"limit": {
"default": 10,
"type": "integer",
"minimum": 1,
"maximum": 10
},
"contentVersion": {
"type": "string",
"pattern": "^[a-f0-9]{64}$"
}
},
"required": [
"conferenceId"
],
"additionalProperties": false
}

Only fields listed in required are mandatory. additionalProperties: false rejects unknown fields. anyOf lists alternative response shapes; null is different from an omitted field.

  • conferenceId is required. day must exactly match a returned day label. Missing structured data returns status=structured_schedule_unavailable and sessions=null.
  • For pagination, pass nextOffset as offset and the returned contentVersion. nextOffset=null means complete; restart if the content version changes.
Example request / response

Successful live snapshot from August 28, 2026, without the MCP envelope. Data and versions change.

get_schedule input
{
"conferenceId": "conference:europe/2026",
"limit": 1
}

get_schedule output
{
"conferenceId": "conference:europe/2026",
"status": "available",
"sourceUrl": "https://ai.engineer/europe/2026/sessions.json",
"contentVersion": "e466cb7065151621c04cacaa8691688fe13455785a81534e8ef14aef116e687f",
"sessions": [
{
"title": "AI Coding For Real Engineers",
"description": "A hands-on workshop covering the full lifecycle of AI-assisted development, from turning ambiguous requirements into agent-ready plans to running autonomous coding agents that ship production features.\n\nYou'll learn to stress-test vague briefs into structured PRDs, slice work into thin \"tracer bullet\" vertical slices, and run an AI agent with TDD. You'll watch it select tasks, write tests, implement code, and commit. You'll then refine your prompts based on where it struggles, graduate to fully autonomous (AFK) runs, and learn to design codebases that maximize agent effectiveness.\n\nYou'll walk away knowing how to:\n\n- Turn ambiguous requirements into agent-ready issues\n\n- Slice work into vertical tracer bullets an agent can grab independently\n\n- Run AI agents human-in-the-loop and autonomously with TDD\n\n- Design codebase architectures that AI agents love to work in\n\nFor: Engineers ready to move beyond chat-based AI assistance and build a real workflow for shipping features with autonomous coding agents.",
"day": "April 8",
"time": "3:45pm-5:45pm",
"room": "St. James",
"track": null,
"type": "workshop",
"speakers": [
"Matt Pocock"
]
}
],
"total": 196,
"nextOffset": 1,
"retrievedAt": "2026-08-28T06:23:05.344Z"
}

search

Discover talks and people

Search talks, speakers, organizations, topics, and conference editions. Narrow talk results by event, speaker, or topic. Results include source links and report unavailable coverage.

Try asking: Find AI Engineer talks about agent memory and RAG evaluation.

Valid inputs & outputs

JSON Schema generated from the server’s validators. Input describes tool arguments; output describes successful structuredContent, including unavailable-data variants.

Expand objects to inspect fields and constraints. For alternative responses, use the variant selector. The raw JSON includes every schema keyword.

Raw JSON Schema / Copy
search input schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 2,
"maxLength": 120,
"pattern": "^[^\\x00-\\x1f\\x7f]+$",
"description": "Trimmed search text; no control characters."
},
"kind": {
"default": "all",
"type": "string",
"enum": [
"all",
"conference",
"talk",
"speaker",
"topic",
"organization"
]
},
"event": {
"type": "string",
"minLength": 2,
"maxLength": 120,
"pattern": "^[^\\x00-\\x1f\\x7f]+$",
"description": "Trimmed search text; no control characters."
},
"speaker": {
"type": "string",
"minLength": 2,
"maxLength": 120,
"pattern": "^[^\\x00-\\x1f\\x7f]+$",
"description": "Trimmed search text; no control characters."
},
"topic": {
"type": "string",
"minLength": 2,
"maxLength": 120,
"pattern": "^[^\\x00-\\x1f\\x7f]+$",
"description": "Trimmed search text; no control characters."
},
"limit": {
"default": 6,
"type": "integer",
"minimum": 1,
"maximum": 10
}
},
"required": [
"query"
],
"additionalProperties": false
}

Only fields listed in required are mandatory. additionalProperties: false rejects unknown fields. anyOf lists alternative response shapes; null is different from an omitted field.

  • query is required. event, speaker and topic narrow talk records; event can also filter conference results. Use kind=talk when combining talk filters.
  • Search covers public metadata and enrichment, not corpus-wide transcript text. Inspect coverage.unavailable before treating results as complete.
Example request / response

Successful live snapshot from August 28, 2026, without the MCP envelope. Data and versions change.

search input
{
"query": "harness engineering",
"kind": "talk",
"limit": 1
}

search output
{
"results": [
{
"id": "talk:harness-engineering",
"title": "Harness Engineering: How to Build Software When Humans Steer, Agents Execute — Ryan Lopopolo, OpenAI",
"url": "https://ai.engineer/talks/harness-engineering",
"kind": "talk",
"excerpt": "Ryan Lopopolo, a member of technical staff at OpenAI, argues that software engineers must shift to 'harness engineering' where agents produce all code and humans focus on delegation, system design, and guardrails. He describes how his team banned editors, using Codex with skills to manipulate apps, and reduced review friction by automating lint rules and review agents. Lopopolo explains that code is free but human time and model context are scarce, so teams should structure repositories for consistency and use 'garbage collection days' to eliminate recurring slop. He shares practical technique",
"excerptType": "metadata",
"recordVersion": "0cf7f5e52f380f67be25553a60c49b86a1c66ae91c230193ba3a813b14e7c55a",
"event": null,
"speakers": [
"Ryan Lopopolo"
]
}
],
"coverage": {
"loaded": 1041,
"unavailable": [],
"enrichment": "available",
"searchScope": "Public metadata and enrichment. Use fetch with a query to search passages within a selected talk; this is not corpus-wide transcript search."
},
"retrievedAt": "2026-08-28T06:23:07.020Z"
}

fetch

Read the source and jump to the video

Retrieve a record by its returned ID, or read timestamped transcript passages from a selected talk. Search within that transcript or request a time range. Video links let you check the original moment.

Try asking: Find the passages about evaluation in that talk and give me timestamped video links.

Valid inputs & outputs

JSON Schema generated from the server’s validators. Input describes tool arguments; output describes successful structuredContent, including unavailable-data variants.

Expand objects to inspect fields and constraints. For alternative responses, use the variant selector. The raw JSON includes every schema keyword.

Raw JSON Schema / Copy
fetch input schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"id": {
"type": "string",
"maxLength": 350,
"pattern": "^(?:conference:[a-z0-9-]+\\/\\d{4}|(?:talk|speaker|topic|organization):[a-z0-9]+(?:-[a-z0-9]+)*)$",
"description": "Use an ID returned by search or list_conferences, not a URL."
},
"section": {
"default": "metadata",
"type": "string",
"enum": [
"metadata",
"transcript"
]
},
"query": {
"type": "string",
"minLength": 2,
"maxLength": 120,
"pattern": "^[^\\x00-\\x1f\\x7f]+$",
"description": "Trimmed search text; no control characters."
},
"startMs": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"endMs": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"offset": {
"default": 0,
"description": "Pass the previous nextOffset to continue.",
"type": "integer",
"minimum": 0,
"maximum": 100000
},
"limit": {
"default": 3,
"type": "integer",
"minimum": 1,
"maximum": 10
},
"contentVersion": {
"type": "string",
"pattern": "^[a-f0-9]{64}$"
}
},
"required": [
"id"
],
"additionalProperties": false
}

Only fields listed in required are mandatory. additionalProperties: false rejects unknown fields. anyOf lists alternative response shapes; null is different from an omitted field.

  • id is required. Transcript query, time range, offset and limit apply only to section=transcript on a talk. Conference IDs return conference metadata.
  • When both timestamps are supplied, endMs must exceed startMs. This cross-field rule is validated by the server but cannot be expressed in standard JSON Schema.
  • A queried passage includes score. Null endMs means the final passage has no known end. A null video URL means no valid video ID is available.
  • For pagination, pass nextOffset as offset and the returned contentVersion. If content changes, restart without contentVersion. Missing transcripts are an explicit success variant, not an empty available transcript.
Example request / response

Successful live snapshot from August 28, 2026, without the MCP envelope. Data and versions change.

fetch input
{
"id": "talk:harness-engineering",
"section": "transcript",
"limit": 1
}

fetch output
{
"id": "talk:harness-engineering",
"title": "Harness Engineering: How to Build Software When Humans Steer, Agents Execute — Ryan Lopopolo, OpenAI",
"url": "https://ai.engineer/talks/harness-engineering",
"contentVersion": "1a1ac76c7ef621f0d53a97c9edbdc46bceaee3d57d2033384ab4bc0c4a685e65",
"transcriptStatus": "available",
"contentType": "automated_transcript",
"passages": [
{
"startMs": 15030,
"endMs": 199290,
"text": "Our next speaker is here to speak about Harness Engineering: how to build software when humans steer and agents execute. Please join me in welcoming to the stage—member of technical staff at OpenAI, Ryan Lopopolo. Good morning, London! I'm super excited to be here today. I'm Ryan Lopopolo, and for the last 9 months I have had the privilege of building software exclusively with agents. I am a token billionaire, and I believe that in order for us to get into our AGI future, we want everybody to be token billionaires: to use the models to do the full job. And what that means is to lean into the idea that the models are capable of being a full software engineer. And I've lived that experience by banning my team from even touching their editors, to have to work through the models in order to get the job done. And today I'm going to talk to you a little bit about what it means to lean into that, and operationalize the way you work, the code spaces you live in, and the processes on your teams in order to get the agents to do the full job. I believe I'm preaching to the choir here when I say that the way we build software has changed. In the last 6 months, we have seen coding agents take over the world, and capability has continually advanced at a super fast pace. To have these models and the harnesses within which they live take more complex actions, do more complicated work, with higher reliability over longer time horizons. And the place we've gotten to here is that implementation is no longer the scarce resource of what it means to do the job of software engineering. Code is free. We have an abundance of code to solve the problems that we come across in our day-to-day as we run our teams, build software, and solve user problems. Hiring the hands-on the keyboards as part of our teams is only constrained by GPU capacity and token budgets. And each engineer today in this room has access to 5, 50, or 5,000 engineers' worth of capacity 24/7, every day of the year. The only thing that needs to happen in our roles is to figure out how to productively deploy these resources into our code and into our teams to make use of this new capacity. And in this world, skill sets are shifting more toward systems thinking, system design, and delegation in order to make use of this abundant capacity to produce code to solve problems. And there are 3 reasons that this happened, all of which happened in late 2025.",
"url": "https://www.youtube.com/watch?v=am_oeAoUhew&t=15"
}
],
"nextOffset": 1,
"totalPassages": 21,
"downloadUrl": "https://ai.engineer/api/data/transcript?slug=harness-engineering&format=json",
"retrievedAt": "2026-08-28T06:23:08.647Z"
}

Tool failures return isError: true with an explanation in content, not a success-schema payload. Invalid arguments may return a protocol error or a tool error; inspect both before reading structuredContent. HTTP 429, 529, and 503 are transport failures, not tool outputs.

For transcript or schedule pagination, pass nextOffset as offset with the returned contentVersion. A null nextOffset marks the end; if content changes, restart pagination.

Usage limits. MCP POST requests share a global limit of 600 per minute, with 60 per minute per IP. This includes tool calls and protocol requests. The shared limit returns HTTP 529; the per-IP limit returns HTTP 429. Respect Retry-After and back off. Need a higher limit? Contact hello@ai.engineer.

Search, then fetch. Discover relevant talks first, then retrieve their passages for source-backed answers. Search currently covers metadata and enrichment—not every transcript word across the corpus. Transcript search runs within a selected talk; transcripts are automated and may contain errors.

Public and read-only. Ticket buying remains a stub; Accelevents ticketing stays on the official conference website. CFPs link to external portals such as Sessionize. MCP cannot purchase tickets, save applications, or submit a CFP. With the user’s explicit authorization, an agent may use computer use on those official portals to complete a purchase or submission. Confirm the final price or application contents before committing unless already approved, and verify the portal’s confirmation.

Downloads and freshness. The aie://data/catalog resource links to the public collections below. Transcript and schedule pagination return content versions so an agent can detect updates. The restricted Hugging Face repository is separate and is not exposed through MCP.

Public collections

Talks

1,041 rows

Titles, speakers, topics, recordings, and summaries from the talk library.

Fields & sample rows

slug · title · url · videoId · event · durationMs · speakers · topics · summary

[
  {
    "slug": "agent-skills",
    "title": "Don't Build Agents, Build Skills Instead – Barry Zhang & Mahesh Murag, Anthropic",
    "url": "https://ai.engineer/talks/agent-skills",
    "videoId": "CEvIs9y1uog",
    "event": null,
    "durationMs": 982000,
    "speakers": [
      {
        "name": "Barry Zhang"
      },
      {
        "name": "Mahesh Murag"
      }
    ],
    "topics": [
      {
        "slug": "coding-agents",
        "name": "Coding agents"
      }
    ],
    "summary": "Barry Zhang and Mahesh Murag of Anthropic argue that instead of building domain-specific agents, developers should build reusable Skills—organized folders of files that package procedural knowledge for agents. They explain that skills are progressively disclosed to protect the context window, use scripts as self-documenting tools, and have already grown to thousands in five weeks, including foundational, partner, and enterprise skills. Skills complement MCP servers by providing expertise while MCP handles connectivity. The future includes treating skills like software with testing and versioning, and enabling agents to create their own skills for continuous learning, ultimately creating a collective knowledge base that makes agents more capable and reliable."
  },
  {
    "slug": "ai-coding-workflow",
    "title": "Full Walkthrough: Workflow for AI Coding — Matt Pocock",
    "url": "https://ai.engineer/talks/ai-coding-workflow",
    "videoId": "-QFHIoCo-Ko",
    "event": null,
    "durationMs": 5790000,
    "speakers": [
      {
        "name": "Matt Pocock"
      }
    ],
    "topics": [
      {
        "slug": "coding-agents",
        "name": "Coding agents"
      }
    ],
    "summary": "Matt Pocock presents a hands-on workshop on building a full AI-assisted coding workflow, arguing that software engineering fundamentals—not hype—make agents effective. He introduces the 'smart zone' and 'dumb zone' of LLMs (performance drops after ~100k tokens) and the 'Memento problem' (agents forget between sessions). His process starts with a 'Grill Me' skill that relentlessly questions the user until shared understanding is reached, then produces a PRD without reading it, slices work into vertical 'tracer bullet' issues, and runs agents AFK using TDD. He advocates designing codebases with deep, testable modules and shows Sandcastle, a TypeScript library for parallel agent execution with separate implementer (Sonnet) and reviewer (Opus). The workshop transforms ambiguous briefs into shippable features while keeping humans in the loop for QA and taste."
  }
]

Speakers

1,021 rows

Speaker profiles, biographies, affiliations, and their conference talks.

Fields & sample rows

slug · name · url · biography · jobTitle · organization · portraitUrl · profiles · affiliations · topics · talkSlugs

[
  {
    "slug": "swyx",
    "name": "swyx",
    "url": "https://ai.engineer/speakers/swyx",
    "biography": null,
    "jobTitle": "Curator",
    "organization": "AI Engineer",
    "portraitUrl": "https://ai.engineer/wf26/speakers/by-id/spk_shawn_wang.jpg",
    "profiles": {
      "website": null,
      "github": null,
      "linkedin": null,
      "x": null
    },
    "affiliations": [
      {
        "organization": "AI Engineer",
        "eventSlug": "ai-engineer-europe-2026",
        "eventYear": 2026
      },
      {
        "organization": "AI Engineer",
        "eventSlug": "ai-engineer-world-s-fair-2026",
        "eventYear": 2026
      },
      {
        "organization": "AI Engineer",
        "eventSlug": "ai-engineer-code-2025",
        "eventYear": 2025
      },
      {
        "organization": "Latent.Space",
        "eventSlug": "ai-engineer-world-s-fair-2025",
        "eventYear": 2025
      },
      {
        "organization": "Latent.Space",
        "eventSlug": "ai-engineer-summit-2025",
        "eventYear": 2025
      },
      {
        "organization": "Latent.Space",
        "eventSlug": "ai-engineer-world-s-fair-2024",
        "eventYear": 2024
      },
      {
        "organization": "Latent.Space",
        "eventSlug": "ai-engineer-summit-2023",
        "eventYear": 2023
      }
    ],
    "topics": [
      {
        "slug": "agent-engineering",
        "name": "Agent engineering"
      },
      {
        "slug": "apis-mcp-and-protocols",
        "name": "APIs, MCP, and protocols"
      },
      {
        "slug": "architecture",
        "name": "Architecture"
      },
      {
        "slug": "coding-and-developer-tools",
        "name": "Coding and developer tools"
      },
      {
        "slug": "data-and-model-adaptation",
        "name": "Data and model adaptation"
      },
      {
        "slug": "enterprise",
        "name": "Enterprise"
      },
      {
        "slug": "finance",
        "name": "Finance"
      },
      {
        "slug": "infrastructure-and-deployment",
        "name": "Infrastructure and deployment"
      },
      {
        "slug": "leadership",
        "name": "Leadership"
      },
      {
        "slug": "other-unclassified",
        "name": "Other / unclassified"
      },
      {
        "slug": "rag-context-and-search",
        "name": "RAG, context, and search"
      },
      {
        "slug": "reasoning-and-models",
        "name": "Reasoning and models"
      },
      {
        "slug": "safety-and-governance",
        "name": "Safety and governance"
      }
    ],
    "talkSlugs": [
      "6-things-to-know-about-aie-world-s-fair-2026",
      "agents-for-everything-else-swyx",
      "software-engineering-ai"
    ]
  },
  {
    "slug": "stephen-chin",
    "name": "Stephen Chin",
    "url": "https://ai.engineer/speakers/stephen-chin",
    "biography": null,
    "jobTitle": "VP of Developer Relations",
    "organization": "Neo4j",
    "portraitUrl": "https://ai.engineer/wf26/speakers/by-id/spk_stephen_chin.jpg",
    "profiles": {
      "website": null,
      "github": null,
      "linkedin": null,
      "x": null
    },
    "affiliations": [
      {
        "organization": "Neo4j",
        "eventSlug": "ai-engineer-europe-2026",
        "eventYear": 2026
      },
      {
        "organization": "Neo4j",
        "eventSlug": "ai-engineer-world-s-fair-2026",
        "eventYear": 2026
      },
      {
        "organization": "Neo4j",
        "eventSlug": "ai-engineer-world-s-fair-2025",
        "eventYear": 2025
      },
      {
        "organization": "Neo4j",
        "eventSlug": "ai-engineer-summit-2025",
        "eventYear": 2025
      },
      {
        "organization": "Neo4j",
        "eventSlug": "ai-engineer-code-2025",
        "eventYear": 2025
      }
    ],
    "topics": [
      {
        "slug": "agent-engineering",
        "name": "Agent engineering"
      },
      {
        "slug": "apis-mcp-and-protocols",
        "name": "APIs, MCP, and protocols"
      },
      {
        "slug": "architecture",
        "name": "Architecture"
      },
      {
        "slug": "finance",
        "name": "Finance"
      },
      {
        "slug": "healthcare",
        "name": "Healthcare"
      },
      {
        "slug": "industry-applications",
        "name": "Industry applications"
      },
      {
        "slug": "leadership",
        "name": "Leadership"
      },
      {
        "slug": "rag-context-and-search",
        "name": "RAG, context, and search"
      },
      {
        "slug": "safety-and-governance",
        "name": "Safety and governance"
      }
    ],
    "talkSlugs": [
      "crabrag-why-automated-assistants-need-graph-memory-not-more-tokens",
      "connecting-the-dots-with-context-graphs",
      "context-engineering-connecting-the-dots-with-graphs-stephen-chin-neo4j"
    ]
  }
]

Topics

24 rows

The topics connecting talks across the conference archive.

Fields & sample rows

slug · name · url · description · talkSlugs

[
  {
    "slug": "rag-context-and-search",
    "name": "RAG, context, and search",
    "url": "https://ai.engineer/topics/rag-context-and-search",
    "description": null,
    "talkSlugs": [
      "1-ai-guardrails-the-unreasonable-effectiveness-of-finetuned-modernberts-diego-carpentero",
      "12-factor-agents",
      "120k-players-in-a-week-lessons-from-the-first-viral-clip-app",
      "2026-the-year-the-ide-died",
      "360brew-llm-based-personalized-ranking-and-recommendation-hamed-firooz-and-maziar-sanjabi-linked",
      "a-practical-guide-to-efficient-ai",
      "a-practitioner-s-guide-to-graphs-tim-ainge-good-collective",
      "a-song-of-types-and-agents",
      "accelerate-your-ai-journey-with-azure-ai-model-catalog",
      "active-graph-agent-runtime-babyagi-4",
      "agent-evals-finally-with-the-map",
      "agent-skills",
      "agentic-graphrag-ai-s-logical-edge",
      "agentic-graphrag-simplifying-retrieval-across-structured-unstructured-data-zach-blumenfeld",
      "agentic-search-for-context-engineering",
      "agentic-security-permissions-provenance-and-the-agent-supply-chain",
      "agents-are-built-at-the-fringe-getting-from-90-to-100",
      "agents-are-robots-too-what-self-driving-taught-me-about-building-agents-jesse-hu-abundant",
      "agents-building-agents",
      "agents-in-production-how-opengov-built-and-scaled-og-assist",
      "agents-need-feature-flags",
      "agents-need-receipts-not-more-tool-calls",
      "agents-reported-thousands-of-bugs-how-many-were-real-ian-butler-and-nick-gregory",
      "ai-agents-for-performance-ship-faster-pay-less",
      "ai-agents-meet-test-driven-development",
      "ai-driven-multi-document-correlation-for-enterprise-financial-compliance-and-fraud-detection",
      "ai-engineering-201-inference",
      "ai-engineering-201-the-rest-of-the-owl",
      "ai-engineering-with-the-google-gemini-2-5-model-family",
      "ai-music-generation-from-prompt-to-production",
      "ai-on-your-lakehouse-context-comes-in-shapes-not-queries",
      "ai-pipelines-and-agents-in-pure-typescript-with-mastra-ai",
      "ai-red-teaming-agent-azure-ai-foundry-nagkumar-arkalgud-keiji-kanazawa-microsoft",
      "ai-sdk-v6",
      "ai-system-design-from-idea-to-production",
      "ai-tools-for-forward-deployed-engineering",
      "alphalab-autonomous-multi-agent-research-across-optimization-domains-with-frontier-llms-brendan",
      "amp-code-next-generation-ai-coding",
      "analyzing-10-000-sales-calls-with-ai-in-2-weeks",
      "anchoring-enterprise-genai-with-knowledge-graphs",
      "anthropic-s-cca-exam-as-a-field-guide-for-agentic-engineering",
      "any-to-any-building-native-multimodal-agents",
      "architecting-agent-memory-principles-patterns-and-best-practices",
      "architecting-and-testing-controllable-agents",
      "are-mcps-overhyped-a-rant-about-mcps",
      "automating-escrow-with-usdc-and-ai",
      "autonomous-agents-for-scientific-tasks-sina-shahandeh-radicait",
      "benchmarking-semantic-code-retrieval-on-claude-code",
      "benchmarks-the-good-the-bad-and-the-ugly",
      "beyond-apis-how-ai-web-agents-are-automating-the-long-tail-of-knowledge-work",
      "beyond-conversation-why-documents-transform-natural-language-into-code",
      "beyond-static-intelligence-evaluating-continual-learning",
      "blender-mcp-and-the-future-of-creative-tools-siddharth-ahuja",
      "books-reimagined-ai-to-create-new-experiences-for-things-you-know-ukasz-gandecki-thebrain-pro",
      "botdojo-launch-enhancing-ai-assistants-with-evaluations-and-synthetic-data",
      "bounded-autonomy-between-free-will-and-determinism",
      "break-it-til-you-make-it-building-the-self-improving-stack-for-ai-agents",
      "build-a-prompt-learning-loop",
      "build-deploy-ai-powered-apps",
      "build-deploy-ai-powered-apps-18cc1b",
      "build-dynamic-products-and-stop-the-ai-sideshow",
      "build-enterprise-generative-ai-apps-using-llama-3-at-1-000-tokens-s-on-the-sambanova-ai-platform",
      "build-systems-not-code",
      "build-the-ai-gtm-agent-that-knows-the-buyer-before-the-first-message",
      "build-your-first-demand-driven-context-base-let-ai-agents-tell-you-what-they-need",
      "build-your-own-deep-research-agent-technical-writer",
      "building-a-smarter-ai-agent-with-neural-rag",
      "building-agent-interfaces-lessons-from-chrome-devtools-mcp-for-agents",
      "building-agentic-applications-with-heroku-managed-inference-and-agents-julian-duque-and-anush-ds",
      "building-agents-is-trivial-now-context-is-the-next-frontier",
      "building-agents-with-mcp",
      "building-ai-agents-that-actually-automate-knowledge-work",
      "building-alice-s-brain-an-ai-sales-rep-that-learns-like-a-human-sherwood-satwik-11x",
      "building-an-agentic-platform",
      "building-an-ai-assistant-that-makes-phone-calls",
      "building-blocks-for-llm-systems-products",
      "building-context-aware-reasoning-applications-with-langchain-and-langsmith",
      "building-conversational-ai-agents-thor-schaeff-elevenlabs",
      "building-deterministic-infrastructure-for-non-deterministic-ai-agents",
      "building-durable-production-ready-agents-with-openai-sdk-and-temporal",
      "building-efficient-hybrid-context-query-for-llm-grounding",
      "building-enterprise-llm-agents-that-work",
      "building-great-agent-skills",
      "building-in-the-gemini-era-kat-kampf-ammaar-reshi-google-deepmind",
      "building-interactive-uis-in-vs-code-with-mcp-apps-marlene-mhangami-liam-hampton-github",
      "building-metrics-that-actually-work-david-karam-pi-labs",
      "building-multi-agent-systems-with-finite-state-machines",
      "building-multimodal-ai-agents-from-scratch",
      "building-reactive-ai-apps",
      "building-redacted-username-gergely-orosz-simon-eskildsen",
      "building-reliable-agentic-systems",
      "building-reliable-support-agents-using-the-effect-typescript-library-michael-fester",
      "building-security-around-ml",
      "building-self-coding-agents",
      "building-sota-open-weights-tool-use-the-command-r-family",
      "building-the-platform-for-agent-coordination",
      "building-trust-in-enterprise-ai-evaluating-domain-specific-llms-for-real-world-financial-scenari",
      "building-voice-agents-with-openai",
      "building-with-anthropic-s-claude-the-prompt-doctor-is-in",
      "building-your-own-secure-ai-workflows-human-in-the-loop-automation-with-n8n",
      "buy-now-maybe-pay-later-dealing-with-prompt-tax-while-staying-at-the-frontier-andrew-thompson",
      "bypassing-the-multimodal-tax-framework-free-hybrid-rag-raw-sql-rrf-and-live-ui-telemetry",
      "can-oncology-workflows-run-without-human-touch-anant-shankhdhar-risa-labs",
      "case-study-deep-dive-telemedicine-support-agents-with-langgraph-mcp",
      "citation-needed-provenance-for-llm-built-knowledge-graphs",
      "claude-agent-sdk-workshop",
      "claude-fable-claude-tag-and-anthropic-s-culture-cat-wu-thariq-shihipar-ft-simon-willison",
      "claude-for-long-horizon-tasks",
      "claude-plays-minecraft-introducing-a-real-world-serverless-ai-to-a-virtual-world",
      "cognitive-shield-real-time-real-smart-rachna-srivastava",
      "cohere-for-vps-of-ai",
      "combine-skills-and-mcp-to-close-the-context-gap",
      "compilers-in-the-age-of-llms",
      "compute-system-design-for-next-generation-frontier-models",
      "connecting-the-dots-with-context-graphs",
      "context-engineering-connecting-the-dots-with-graphs-stephen-chin-neo4j",
      "context-engineering-for-complex-codebases",
      "context-engineering-in-2026-compaction-memory-cost",
      "context-graphs-for-explainable-decision-aware-ai-agents",
      "context-is-the-new-code",
      "context-platform-engineering-to-reduce-token-anxiety-val-bercovici-and-callan-fox-weka",
      "convex-launch",
      "crabrag-why-automated-assistants-need-graph-memory-not-more-tokens",
      "creating-agents-that-co-create",
      "creating-and-scaling-your-own-custom-copilots-with-azure-ai-studio",
      "customized-production-ready-inference-with-open-source-models-dmytro-dima-dzhulgakov",
      "data-is-your-differentiator-building-secure-and-tailored-ai-systems",
      "data-readiness-is-a-myth-reliable-ai-with-an-agentic-semantic-layer-anushrut-gupta-promptql",
      "decoding-mistral-ai-s-large-language-models",
      "deepswe-a-contamination-resistant-coding-benchmark-james-shi-datacurve",
      "designing-ai-intensive-applications",
      "develop-at-idea-velocity",
      "developer-experience-in-the-age-of-ai-coding-agents",
      "devin-2-0-and-the-future-of-swe",
      "dispatch-from-the-future-building-an-ai-native-company-dan-shipper-every-ai-i",
      "does-genai-belong-to-data-scientists",
      "domain-adaptation-and-fine-tuning-for-domain-specific-llms",
      "don-t-build-slop-4-levels-of-ai-agent-maturity",
      "don-t-just-slap-on-a-chatbot-building-ai-that-works-before-you-ask",
      "don-t-ship-skills-without-evals",
      "dspy-the-end-of-prompt-engineering",
      "effective-agent-design-patterns-in-production",
      "effective-ai-agents-need-data-flywheels-not-the-next-biggest-llm-sylendran-arunagiri-nvidia",
      "embeddings-are-stunting-agents-how-codeium-breaks-through-the-ceiling-for-retrieval",
      "engineering-better-evals-scalable-llm-evaluation-pipelines-that-work",
      "ensure-ai-agents-work-evaluation-frameworks-for-scaling-success",
      "enterprise-agents-have-a-structure-problem-ishita-daga-tesla",
      "enterprise-deep-research-the-next-killer-app-for-enterprise-ai-ofer-mendelevitch-vectara",
      "evals-are-not-unit-tests",
      "evals-driven-development-engineering-a-mental-health-ai-coach-ethically-safely",
      "evals-workshop-mastering-ai-evaluation-from-playground-to-production",
      "evaluating-ai-search-a-practical-framework-for-augmented-ai-systems",
      "every-company-should-have-a-brain-garry-tan-y-combinator",
      "every-harness-will-become-a-claw",
      "everything-i-learned-training-frontier-small-models",
      "evolving-claude-apis-for-agents",
      "eyelevel-launch-your-rag-is-tripping-here-s-the-real-reason-why",
      "fast-models-need-slow-developers",
      "feedback-loops-are-all-you-need",
      "fighting-slop-with-slop",
      "first-steps-toward-automated-ai-research",
      "five-hard-earned-lessons-about-evals",
      "forget-rag-pipelines-build-production-ready-ai-agents-in-15-minutes",
      "form-factors-for-your-new-ai-coworkers",
      "forward-deployed-engineering-101",
      "from-agent-traces-to-agent-simulations-rustem-feyzkhanov-snorkel-ai",
      "from-arc-to-dia-lessons-learned-in-building-ai-browser",
      "from-copilot-to-colleague-building-trustworthy-productivity-agents-for-high-stakes-work",
      "from-software-developer-to-ai-engineer",
      "from-systems-of-record-to-systems-of-context",
      "from-writing-code-to-designing-systems-how-the-developer-role-is-changing-chris-noring-microsoft",
      "frontier-ai-at-home-literally",
      "frontier-results-on-device-rl-nabors-arize",
      "full-workshop-setting-yourself-up-for-success-jason-liu-openai-codex",
      "fun-stories-from-building-openrouter-and-where-all-this-is-going",
      "function-calling-is-all-you-need",
      "future-of-knowledge-assistants",
      "gemini-nano-on-device-florina-muntenescu-oli-gaymond-google-deepmind",
      "gemma-4-deep-dive-cassidy-hardin-google-deepmind",
      "git-push-get-an-ai-api",
      "giving-a-voice-to-ai-agents",
      "going-beyond-rag-extended-mind-transformers",
      "gpt-web-app-generator-10-000-apps-created-in-a-month-matija-sosic",
      "graph-intelligence-enhance-reasoning-and-retrieval-using-graph-analytics",
      "graphrag",
      "graphrag-methods-to-create-optimized-llm-context-windows-for-retrieval-jonathan-larson-microsoft",
      "guardrails-first-engineering-member-facing-health-ai",
      "guide-verify-solve-the-engineering-discipline-agentic-development-demands",
      "harness-engineering",
      "harnessing-the-power-of-llms-locally",
      "hasura-launch-realtime-data-connectivity-for-ai",
      "healthcare-s-agent-bytecode-x12-as-the-harness-for-ai-agents",
      "how-agent-o11y-differs-from-traditional-o11y",
      "how-blackrock-builds-custom-knowledge-apps-at-scale",
      "how-claude-code-works",
      "how-deep-research-works",
      "how-google-deepmind-is-researching-the-next-frontier-of-ai-for-gemini-raia-hadsell-vp-of-researc",
      "how-i-automate-my-own-job-at-hugging-face-using-agents",
      "how-instacart-transformed-its-search-and-discovery-using-an-llm-driven-approach",
      "how-intuit-uses-llms-to-explain-taxes-to-millions-of-taxpayers",
      "how-juries-and-librarians-can-solve-gtm-s-ai-trust-problem",
      "how-kepler-built-verifiable-ai-for-financial-services",
      "how-llms-work-for-web-devs-gpt-in-600-lines-of-vanilla-js",
      "how-to-build-agents-that-run-for-hours-without-losing-the-plot",
      "how-to-build-ai-agents-that-actually-work",
      "how-to-build-an-ai-strategy-that-fails",
      "how-to-build-enterprise-aware-agents",
      "how-to-build-trustworthy-ai",
      "how-to-build-world-class-ai-products-sarah-sachs-notion-and-carlos-esteban-braintrust",
      "how-to-construct-domain-specific-llm-evaluation-systems",
      "how-to-defend-your-sites-from-ai-bots",
      "how-to-improve-your-agents-academic-lit-review",
      "how-to-improve-your-vibe-coding-ian-butler",
      "how-to-look-at-your-data-what-to-look-for-how-to-measure",
      "how-we-hacked-yc-spring-2025-batch-s-ai-agents",
      "how-we-scaled-500m-ai-agents-in-production-with-2-engineers",
      "how-we-solved-context-management-in-agents-sally-ann-delucia",
      "how-we-taught-agents-to-use-good-retrieval-hanna-lichtenberg-mixedbread-ai",
      "how-web-data-infrastructure-powers-the-next-generation-of-ai",
      "html-is-all-you-need-for-agents-to-make-graphics",
      "human-seeded-evals-samuel-colvin-pydantic",
      "hybridrag-a-fusion-of-graph-and-vector-retrieval-to-enhance-data-interpretation",
      "hypermode-launch",
      "hyperspace-more-nodes-is-all-you-need",
      "i-gave-an-ai-agent-the-keys-to-my-life-here-s-what-happened",
      "i-run-a-fleet-of-ai-agents-across-three-machines-here-s-what-broke",
      "i-ve-never-seen-anything-scarier-than-an-llm-with-tool-calls-erik-meijer-aka-headinthebox",
      "improving-agents-is-a-data-mining-problem",
      "information-retrieval-from-the-ground-up",
      "infra-that-fixes-itself-thanks-to-coding-agents-mahmoud-abdelwahab-railway",
      "insights-from-snorkel-ai-running-azure-ai-infrastructure",
      "intelligence-continual-learning-expertise",
      "intro-to-graphrag",
      "introducing-strands-agents-an-open-source-ai-agents-sdk",
      "iterating-on-llm-apps-at-scale-learnings-from-discord",
      "judge-the-judge-building-llm-evaluators-that-actually-work-with-gepa-mahmoud-mabrouk-agenta-ai",
      "judging-llms",
      "just-do-it-let-your-tools-think-for-themselves-robert-chandler",
      "keynote-why-people-think-agent-is-a-buzzword-but-it-isn-t",
      "knowledge-graphs-graphrag-techniques-for-building-effective-genai-applications",
      "knowledge-graphs-in-litigation-agents-tom-smoker-whyhow-ai",
      "layering-every-technique-in-rag-one-query-at-a-time",
      "learned-execution-graphs-for-anomaly-detection-drift-in-apis-ritvik-pandya-jp-morgan-chase",
      "lessons-from-building-genai-based-applications-juan-peredo",
      "lessons-from-building-linkedin-s-genai-platform",
      "lessons-from-studying-every-memory-system",
      "let-s-build-an-agent-from-scratch-kam-lasater",
      "let-s-integrate-ai-agents-in-event-sourced-systems",
      "llama-3-at-1-redacted-password-000-tok-s-on-the-sambanova-ai-platform",
      "llm-codegen-fails-and-how-to-stop-em",
      "llm-evals-that-work-irl",
      "llm-knowledge-bases-a-practical-guide",
      "llm-observability-evaluation-experimentation-platform-dat-ngo-arize-ai",
      "llm-pelican-benchmark",
      "llm-safeguards-security-privacy-compliance-anti-hallucination",
      "llm-scientific-reasoning-how-to-make-ai-capable-of-nobel-prize-discoveries",
      "low-level-technicals-of-llms",
      "luminal-search-based-deep-learning-compilers-joe-fioti",
      "making-open-models-10x-faster-and-better-for-modern-application-innovation",
      "mastering-engineering-flow-with-windsurf",
      "maximize-gpu-efficiency-with-continuous-profiling-for-gpus",
      "mcp-agent-fine-tuning-workshop-ronan-mcgovern",
      "mcp-apps-primitives-discovery-and-the-future-of-software",
      "mcp-is-all-you-need",
      "medic-for-apache-spark-first-aid-for-failing-jobs-drasko-profirovic-pinterest",
      "memory-harnesses-for-long-running-research-agents",
      "memory-masterclass-make-your-ai-agents-remember-what-they-do-mark-bain-aius",
      "mentoring-the-machine",
      "mergeable-by-default-building-the-context-engine-to-save-time-and-tokens",
      "mind-the-gap-in-your-agent-observability",
      "minimax-m2",
      "model-maxxing-rft-dpo-sft-fine-tuning-with-openai-ilan-bigio-openai",
      "multi-agent-ai-and-network-knowledge-graphs-for-change-management-and-network-testing",
      "my-ai-thinks-i-m-eating-my-feelings-and-other-nutritional-insights",
      "navigating-challenges-and-technical-debt-in-llms-deployment",
      "navigating-rag-optimization-with-an-evaluation-driven-compass",
      "new-york-times-connections-a-case-study-on-nlp-in-word-games",
      "no-code-fine-tuning-mark-hennings",
      "no-more-bad-outputs-with-structured-generation",
      "on-ai-and-knowledge",
      "on-curiosity-sharif-shameem-lexica",
      "on-engineering-ai-systems-that-endure-the-bitter-lesson",
      "one-developer-two-dozen-agents-zero-alignment-why-we-need-collaborative-ai-engineering",
      "one-model-to-rule-recommendations-netflix-s-big-bet",
      "ontologies-for-agentic-systems",
      "open-challenges-for-ai-engineering",
      "open-questions-for-ai-engineering",
      "open-rag-eval-rag-evaluation-without-golden-answers",
      "open-source-is-dead-long-live-open-source",
      "openai-for-vps-of-ai",
      "openclaw-in-your-hand-building-a-physical-ai-terminal-for-local-llm-agents",
      "openllmetry-is-all-you-need",
      "openrag-an-open-source-stack-for-rag-phil-nash",
      "optimizing-llms-in-insurance-with-dspy-beyond-manual-tuning",
      "paperclip-open-source-human-control-plane-for-ai-labor-dotta",
      "perception-agents-antje-barth-amazon-agi-lab",
      "perceptual-evaluations-evals-for-aesthetics-diego-rodriguez-krea-ai",
      "persona-engineering-a-field-guide-to-ai-synthetic-personas-ishan-anand-insightsciences-ai",
      "personalization-in-the-era-of-llms",
      "pipecat-cloud-enterprise-voice-agents-built-on-open-source",
      "playground-in-prod-optimising-agents-in-production-environments",
      "poc-to-prod-hard-lessons-from-200-enterprise-genai-deployments",
      "practical-graphrag-making-llms-smarter-with-knowledge-graphs",
      "practical-tactics-to-build-reliable-ai-apps-dmitry-kuchin-multinear",
      "pragmatic-ai-with-typechat",
      "production-rag-agents",
      "production-ready-rag",
      "prompt-engineering-ai-red-teaming",
      "prompt-engineering-is-dead",
      "prompt-engineering-tactics",
      "pydantic-is-still-all-you-need",
      "rag-and-the-mongodb-document-model",
      "rag-at-scale-production-ready-genai-apps-with-azure-ai-search",
      "rag-evaluation-is-broken-here-s-why-and-how-to-fix-it",
      "rag-for-vps-of-ai",
      "rag-in-2025-state-of-the-art-and-the-road-forward",
      "rag-is-dead-right-kuba-rogut-redacted-username",
      "ralph-loops-build-dumb-ai-loops-that-ship",
      "real-ai-agents-need-planning-not-just-prompting",
      "real-roi-lessons-from-enterprises-that-have-already-succeeded-with-llms-redacted-username-scale",
      "realtime-multiplayer-automation-and-you",
      "recsys-keynote-improving-recommendation-systems-search-in-the-age-of-llms",
      "recursive-coding-agents",
      "reinforcement-learning-without-verifiable-rewards-will-brown-prime-intellect",
      "replacing-12k-loc-with-a-200-loc-skill",
      "research-to-reality-bringing-frontier-ml-research-to-production",
      "retrieval-augmented-generation-in-the-wild",
      "rlm-recursive-language-models-for-large-codebases",
      "road-to-5-million-tokens-breaking-barriers-in-long-context-training-max-ryabinin-together-ai",
      "running-ai-application-in-minutes-quick-start-with-ai-templates",
      "running-llms-locally-practical-llm-performance-on-dgx-spark-mozhgan-kabiri-chimeh-nvidia",
      "safety-and-security-for-code-executing-agents",
      "scaffold-wisely",
      "scaling-ai-agents-without-breaking-reliability",
      "scaling-compute-on-context",
      "scaling-enterprise-grade-rag-systems-lessons-from-the-legal-frontier",
      "scaling-github-for-your-agents-sam-morrow-github",
      "securing-agents-with-open-standards",
      "security-firewall-for-agents",
      "self-driving-products-product-signals-to-pull-requests",
      "self-training-agents-hermes-agent-hf-traces-skills-mcp-finetuning-merve-noyan-hugging-face",
      "semantic-blindness-500-000-sensors-confused-an-llm-raahul-singh-vanc-levstik-phaidra",
      "serving-2-million-models-without-melting-scaling-the-hugging-face-hub",
      "shift-left-how-to-become-an-ai-engineer-from-a-full-stack-background",
      "ship-real-agents-hands-on-evals-for-agentic-applications",
      "shipping-ai-that-works-an-evaluation-framework-for-pms",
      "shipping-an-enterprise-voice-ai-agent-in-100-days",
      "simulation-maxxing-how-nubank-ships-agents-20-faster-with-simulations",
      "skill-issue-lessons-from-skilling-up-coding-agents-to-use-langfuse",
      "skills-are-new-features-building-skill-centric-harness-yogendra-miraje-factset",
      "skills-are-the-new-sdks",
      "skills-at-scale",
      "small-ai-teams-with-huge-impact-vik-paruchuri-datalab",
      "small-bets-big-impact-building-genbi-at-a-fortune-100",
      "specifications-are-the-new-code",
      "spreadsheets-are-all-you-need-decoding-the-decoder-llm-without-de-code",
      "state-of-startups-and-ai-2025",
      "state-of-the-union-why-local-why-now",
      "state-space-models-for-realtime-multimodal-intelligence",
      "stateful-agents-full-workshop-with-redacted-username-packer-of-letta-and-memgpt",
      "stateful-environments-for-vertical-agents-josh-purtell-synth-labs",
      "stop-ai-agent-hallucinations-5-techniques-production-patterns-elizabeth-fuentes-leone-aws",
      "stop-babysitting-your-agents-building-a-context-engine-for-mergeable-code",
      "stop-burning-tokens-why-self-improvement-needs-domain-expertise-first-annabell-schafer-langfuse",
      "stop-guessing-build-robust-ai-with-layered-cot",
      "stop-renting-your-cognitive-infrastructure",
      "stop-using-rag-as-memory",
      "stop-writing-tone-instructions-layer-them",
      "storyteller-building-multi-modal-apps-with-ts-modelfusion-lars-grammel-phd",
      "strategies-for-llm-evals-guidellm-lm-eval-harness-openai-evals-workshop-taylor-jordan-smith",
      "structured-llm-outputs-with-pydantic",
      "structuring-the-unstructured-advanced-document-parsing-for-ai-workflows",
      "stuffing-context-is-not-memory-updating-weights-is",
      "substrate-launch-the-api-for-modular-ai",
      "supabase-vector-the-postgres-vector-database",
      "taming-rogue-ai-agents-with-observability-driven-evaluation",
      "task-fidelity-scaling-laws-kobie-crawford-snorkel-ai",
      "teaching-gemini-to-speak-youtube-adapting-llms-for-video-recommendations-to-2b-dau",
      "the-100-tool-agent-is-a-trap-scaling-with-semantic-routers-and-jit-context",
      "the-2025-ai-engineering-report-barr-yaron-amplify-partners",
      "the-a-to-z-of-building-ai-agents",
      "the-adversarial-path-to-the-personal-assistant",
      "the-agent-native-company",
      "the-agent-ready-web-simplify-user-actions-with-webmcp",
      "the-agentic-web-and-the-bazaar-era-of-ai-ramesh-raskar-mit-media-lab",
      "the-ai-pivot-with-chris-white-of-prefect-bryan-bischof-of-hex",
      "the-billable-hour-is-dead-long-live-the-billable-hour",
      "the-coherence-trap-why-llms-feel-smart-but-aren-t-thinking",
      "the-cure-for-the-vibe-coding-hangover",
      "the-dirty-secret-of-forward-deployed-engineering",
      "the-end-of-apps",
      "the-era-of-compound-engineering",
      "the-era-of-unbounded-products-designing-for-multimodal-i-o",
      "the-factory-that-dreams-39-ai-agents-no-framework",
      "the-friction-is-your-judgment",
      "the-future-of-evals-ankur-goyal-braintrust",
      "the-future-of-work",
      "the-great-loops-debate-dex-horthy-geoff-huntley-ian-livingstone-greg-pstrucha-moderated-by-allie",
      "the-hidden-costs-of-building-your-own-rag-stack-ofer-mendelevitch-vectara",
      "the-hidden-life-of-embeddings",
      "the-hierarchy-of-needs-for-training-dataset-development",
      "the-intelligent-interface",
      "the-knowledge-graph-mullet-trimming-graphrag-complexity",
      "the-llm-triangle-engineering-principles-for-robust-ai-applications",
      "the-log-is-the-agent",
      "the-making-of-devin",
      "the-miranda-hypothesis-how-hamilton-the-musical-poisoned-your-persona-evals",
      "the-missing-layer-design-taste-in-ai-agents",
      "the-model-isn-t-wrong-you-re-just-bad-at-prompting",
      "the-next-unicorns-7-top-ai-startups-from-the-hf0-residency",
      "the-prompt-is-still-a-punch-card",
      "the-rag-stack-we-landed-on-after-37-fails",
      "the-rise-of-caas-context-as-a-service-for-agentic-ai",
      "the-small-model-infrastructure-nobody-built-so-we-did-filip-makraduli-superlinked",
      "the-state-of-ai-powered-search-and-retrieval",
      "the-state-of-mcp-observability-observable-tools-alex-volkov-and-benjamin-eckel-weights-biases-an",
      "the-state-of-model-routing-nvidia-cognition-openrouter",
      "the-unbearable-lightness-of-agent-optimization",
      "the-unreasonable-effectiveness-of-prompt-learning",
      "the-unreasonable-effectiveness-of-separating-the-task-from-the-model",
      "the-voice-first-ai-overlay-designing-conversational-co-pilots",
      "thinner-agents-on-a-smarter-substrate-the-ontology-based-semantic-layer",
      "tool-calling-is-not-just-plumbing-for-ai-agents",
      "training-albatross-an-expert-finance-llm",
      "trunk-tools-launch-disrupting-the-15-trillion-construction-industry-with-autonomous-agents",
      "trust-but-verify",
      "trust-but-verify-high-fidelity-reasoning-in-agentic-workflows",
      "turn-10-994-notes-into-your-agents-memory",
      "two-roads-to-durable-agents-replay-vs-snapshot-eric-allam-co-founder-trigger-dev",
      "understanding-ai-stakes-to-break-production-code",
      "useful-general-intelligence",
      "user-signal-die-at-the-retrieval-boundary",
      "using-ai-to-build-an-infinite-game",
      "using-llms-to-secure-source-code",
      "using-rl-based-agent-to-detect-and-remediate-etl-pipeline-failures",
      "vector-search-benchmark-eting",
      "vercel-ai-sdk-masterclass-from-fundamentals-to-deep-research",
      "vibe-coding-at-scale-customizing-ai-assistants-for-enterprise-environments",
      "video-has-no-memory-here-s-how-we-built-one",
      "voiceops-fying-low-latency-intelligence-extraction-from-messy-audio-streams-dippu-kumar-singh",
      "voicevision-rag-integrating-visual-document-intelligence-with-voice-response",
      "we-vetted-2-000-ai-skills-before-they-reached-developers",
      "wearing-the-agent-engineering-a-family-and-friends-personal-agent-from-group-chats-to-glasses",
      "what-do-models-still-suck-at",
      "what-if-the-harness-mattered-more-than-the-model-aditya-bhargava-etsy",
      "what-s-new-from-anthropic-and-what-s-next",
      "what-the-best-agents-share",
      "what-we-learned-from-using-llms-in-pinterest",
      "when-agents-meet-physical-data-the-other-physics-of-agent-harnesses",
      "when-all-context-matters-extended-cache-augmented-generation-ecag",
      "when-vectors-break-down-graph-based-rag-for-dense-enterprise-knowledge",
      "when-will-the-benchmaxxing-plague-end",
      "which-jobs-can-be-replaced-today",
      "why-and-how-you-need-to-sandbox-ai-generated-code-harshil-agrawal-cloudflare",
      "why-building-eval-platforms-is-hard",
      "why-can-t-anyone-answer-questions-about-the-business",
      "why-chatgpt-keeps-interrupting-you",
      "why-eval-is-the-next-great-compute-primitive-sunil-pai-matt-carey-cloudflare",
      "why-more-context-makes-your-agent-dumber-and-what-to-do-about-it",
      "why-senior-engineers-struggle-to-build-ai-agents",
      "why-should-anyone-care-about-evals",
      "why-the-best-ai-agents-are-built-without-frameworks-primitives-over-frameworks",
      "why-we-killed-our-multi-agent-pipeline-subbiah-sethuraman-and-abhilash-asokan-zs-associates",
      "why-your-agent-disagrees-with-itself-and-what-to-do-about-it",
      "why-your-agent-s-brain-needs-a-playbook-practical-wins-from-using-ontologies",
      "why-your-agents-need-decision-traces-not-just-documents-zach-blumenfeld-neo4j",
      "wisdom-driven-knowledge-augmented-generation-at-scale",
      "writing-principles-for-task-tuned-prompt-engineering",
      "wtf-is-the-context-layer-the-missing-infrastructure-for-production-agents",
      "your-agent-evolved-your-evals-didn-t",
      "your-agent-is-wasting-tokens-and-you-don-t-know-it",
      "your-agent-s-biggest-lie-i-searched-the-web",
      "your-coding-agent-just-got-cloned-and-your-brain-isn-t-ready",
      "your-coding-agent-should-do-ai-system-engineering",
      "your-fine-tuned-model-is-tech-debt-a-50x-roi-house-of-cards",
      "your-insecure-mcp-server-won-t-survive-production-tun-shwe-lenses",
      "your-llm-deception-monitor-is-broken-the-fix-is-in-the-training-data-sachin-kumar-lexisnexis",
      "your-llm-ran-out-of-knowledge-now-what",
      "your-mcp-server-is-bad-and-you-should-feel-bad",
      "your-moat-is-your-data-model",
      "z-ai-glm-4-6-what-we-learned-from-100-million-open-source-downloads-yuxuan-zhang-z-ai"
    ]
  },
  {
    "slug": "coding-and-developer-tools",
    "name": "Coding and developer tools",
    "url": "https://ai.engineer/topics/coding-and-developer-tools",
    "description": null,
    "talkSlugs": [
      "120k-players-in-a-week-lessons-from-the-first-viral-clip-app",
      "2026-the-year-the-ide-died",
      "3-ingredients-for-building-reliable-enterprise-agents",
      "6-things-to-know-about-aie-world-s-fair-2026",
      "a-genius-with-amnesia",
      "a-piece-of-pi-embedding-the-openclaw-coding-agent-in-your-product",
      "a-song-of-types-and-agents",
      "a-taxonomy-for-next-generation-reasoning-models",
      "agent-reinforcement-fine-tuning",
      "agentcraft-putting-the-orc-in-agent-orchestration",
      "agentic-development-security",
      "agentic-engineering-working-with-ai-not-just-using-it-brendan-o-leary",
      "agentic-excellence-mastering-evaluation-of-ai-agents-with-azure-ai-evaluation-sdk",
      "agentic-sdlc-at-uber-building-blocks-for-uber-s-software-factory",
      "agentic-search-for-context-engineering",
      "agentic-security-permissions-provenance-and-the-agent-supply-chain",
      "agents-are-built-at-the-fringe-getting-from-90-to-100",
      "agents-don-t-do-standups-building-the-post-engineer-engineering-org",
      "agents-for-everything-else-swyx",
      "agents-in-production-how-opengov-built-and-scaled-og-assist",
      "agents-need-more-than-a-chat",
      "agents-reported-thousands-of-bugs-how-many-were-real-ian-butler-and-nick-gregory",
      "agi-the-path-forward",
      "ai-agents-for-performance-ship-faster-pay-less",
      "ai-agents-meet-test-driven-development",
      "ai-and-human-whiteboarding-partnership",
      "ai-changes-nothing-dax-raad-opencode",
      "ai-coding-workflow",
      "ai-developer-productivity",
      "ai-didn-t-kill-the-web-it-moved-in-olivier-leplus-aws-yohan-lasorsa-microsoft",
      "ai-engineering-101",
      "ai-engineering-without-borders",
      "ai-on-your-lakehouse-context-comes-in-shapes-not-queries",
      "ai-pipelines-and-agents-in-pure-typescript-with-mastra-ai",
      "ai-powered-entomology-lessons-from-millions-of-ai-code-reviews",
      "ai-sdk-v6",
      "always-on-agents-run-production-without-the-on-call-tax",
      "amazon-agi",
      "amp-code-next-generation-ai-coding",
      "anthropic-for-vps-of-ai",
      "anthropic-s-cca-exam-as-a-field-guide-for-agentic-engineering",
      "are-mcps-overhyped-a-rant-about-mcps",
      "arrakis-how-to-build-an-ai-sandbox-from-scratch",
      "automating-large-scale-refactors-with-parallel-agents",
      "backlog-md-terminal-kanban-board-for-managing-tasks-with-ai-agents-alex-gavrilescu-funstage",
      "benchmarking-coding-agents-on-new-vs-legacy-codebases-denys-linkov-wisedocs",
      "benchmarking-semantic-code-retrieval-on-claude-code",
      "benchmarks-the-good-the-bad-and-the-ugly",
      "best-practices-for-evaluating-large-language-model-applications-with-llmeval-niklas-nielsen",
      "beyond-code-coverage-functionality-testing-with-playwright",
      "beyond-conversation-why-documents-transform-natural-language-into-code",
      "beyond-the-prototype-using-ai-to-write-high-quality-code",
      "books-reimagined-ai-to-create-new-experiences-for-things-you-know-ukasz-gandecki-thebrain-pro",
      "botdojo-launch-enhancing-ai-assistants-with-evaluations-and-synthetic-data",
      "breaking-ai-s-1-gigahertz-barrier",
      "breaking-the-chain-agent-continuations-for-resumable-ai-workflows",
      "bringing-agents-onto-the-world-wide-web",
      "build-a-prompt-learning-loop",
      "build-enterprise-generative-ai-apps-using-llama-3-at-1-000-tokens-s-on-the-sambanova-ai-platform",
      "build-systems-not-code",
      "build-your-first-demand-driven-context-base-let-ai-agents-tell-you-what-they-need",
      "build-your-own-deep-research-agent-technical-writer",
      "building-agents-is-trivial-now-context-is-the-next-frontier",
      "building-ai-agents-with-real-roi-in-the-enterprise-sdlc",
      "building-ai-for-all",
      "building-ai-powered-developer-tools-at-jane-street",
      "building-ciso-approved-agent-fleet-architecture",
      "building-code-first-ai-agents-with-azure-ai-agent-service-cedric-vidal-microsoft",
      "building-context-aware-reasoning-applications-with-langchain-and-langsmith",
      "building-conversational-agents",
      "building-cursor-composer",
      "building-in-the-gemini-era-kat-kampf-ammaar-reshi-google-deepmind",
      "building-metrics-that-actually-work-david-karam-pi-labs",
      "building-multimodal-ai-agents-from-scratch",
      "building-reactive-ai-apps",
      "building-redacted-username-gergely-orosz-simon-eskildsen",
      "building-reliable-agentic-systems",
      "building-reliable-support-agents-using-the-effect-typescript-library-michael-fester",
      "building-security-around-ml",
      "building-self-coding-agents",
      "building-your-own-software-factory",
      "can-llms-generate-enterprise-quality-code-prasenjit-sarkar-sonar",
      "challenges-in-high-performance-robotics-systems",
      "ci-cd-is-dead-agents-need-continuous-compute-and-computers-hugo-santos-and-madison-faulkner",
      "ci-in-the-era-of-ai-from-unit-tests-to-stochastic-evals",
      "claude-agent-sdk-workshop",
      "claude-code-the-evolution-of-agentic-coding",
      "claude-fable-claude-tag-and-anthropic-s-culture-cat-wu-thariq-shihipar-ft-simon-willison",
      "code-generation-and-maintenance-at-scale",
      "code-mode-let-the-code-do-the-talking",
      "code-world-model-building-world-models-for-computation",
      "codex-and-subagents",
      "codex-behind-the-harness",
      "coding-evals-from-code-snippets-to-codebases-naman-jain-cursor",
      "cognitive-exhaust-fumes-or-read-only-ai-is-underrated-simon-podhajsky-head-of-ai-waypoint",
      "collaborating-with-agents-in-your-software-development-workflow-jon-peck-christopher-harrison-gi",
      "compilers-in-the-age-of-llms",
      "comprehend-first-code-later-the-ai-skill-i-rely-on-daily",
      "computer-use-models-will-agentify-the-web-not-apis",
      "conquering-agent-chaos",
      "containing-agent-chaos",
      "content-is-code",
      "context-engineering-for-complex-codebases",
      "context-is-the-new-code",
      "cooking-with-agents-in-vs-code",
      "copilots-everywhere",
      "covalent-launch-the-gpu-cheatcode-fine-tune-20-llama-models-in-5-minutes",
      "creating-agents-that-co-create",
      "creating-and-scaling-your-own-custom-copilots-with-azure-ai-studio",
      "dark-factory-openclaw-ships-faster-than-you-can-read-the-diff",
      "data-and-environment-curation-for-post-training-llms",
      "decoding-mistral-ai-s-large-language-models",
      "deepswe-a-contamination-resistant-coding-benchmark-james-shi-datacurve",
      "define-ai-engineer",
      "design-like-karpathy-is-watching",
      "designing-ai-to-scale-human-thought",
      "develop-at-idea-velocity",
      "developer-experience-in-the-age-of-ai-coding-agents",
      "developing-taste-in-coding-agents-applied-meta-neuro-symbolic-rl-ahmad-awais-command-code",
      "devin-2-0-and-the-future-of-swe",
      "dispatch-from-the-future-building-an-ai-native-company-dan-shipper-every-ai-i",
      "don-t-build-slop-4-levels-of-ai-agent-maturity",
      "don-t-get-one-shotted-use-ai-to-test-review-merge-and-deploy-code-tomas-reimers-graphite",
      "don-t-ship-skills-without-evals",
      "dspy-the-end-of-prompt-engineering",
      "effective-agent-design-patterns-in-production",
      "effective-ai-agents",
      "embeddings-are-stunting-agents-how-codeium-breaks-through-the-ceiling-for-retrieval",
      "emergence-launch-ai-agents-and-the-future-enterprise",
      "emulated-the-data-for-fully-autonomous-software-engineers-and-companies",
      "evals-101-doug-guthrie-braintrust",
      "evals-are-broken-use-them-anyway",
      "evals-are-not-unit-tests",
      "evals-workshop-mastering-ai-evaluation-from-playground-to-production",
      "every-solo-agent-builder-eventually-reinvents-a-worse-version-of-ci-cd",
      "everything-i-learned-training-frontier-small-models",
      "everything-is-a-rollout-alex-shaw-ryan-marten-terminal-bench-harbor-laude-institute",
      "everything-we-knew-about-software-has-changed-theo-browne",
      "everything-you-need-to-know-about-agent-observability",
      "eyelevel-launch-your-rag-is-tripping-here-s-the-real-reason-why",
      "fast-models-need-slow-developers",
      "field-guide-to-fable",
      "fighting-slop-with-slop",
      "forget-rag-pipelines-build-production-ready-ai-agents-in-15-minutes",
      "from-blind-spots-to-merged-prs-continuous-agentic-performance-optimization",
      "from-mcp-to-scale-pipelines-that-build-themselves",
      "from-mixture-of-experts-to-mixture-of-agents-with-super-fast-inference",
      "from-rl-to-irl-gaurav-mishra-amazon-agi-lab",
      "from-self-driving-to-autonomous-voice-agents-brooke-hopkins-coval",
      "from-signal-to-pr-anatomy-of-a-self-improving-agent",
      "from-software-developer-to-ai-engineer",
      "from-systems-of-record-to-systems-of-context",
      "from-vibe-coding-to-vibe-engineering",
      "from-writing-code-to-designing-systems-how-the-developer-role-is-changing-chris-noring-microsoft",
      "frontier-feud",
      "full-workshop-setting-yourself-up-for-success-jason-liu-openai-codex",
      "future-proof-coding-agents",
      "gadgets-personal-app-vibe-coding-that-is-actually-safe",
      "gateways-are-all-you-need",
      "gemma-deepmind-s-family-of-open-models",
      "git-push-get-an-ai-api",
      "github-copilot-the-world-s-most-widely-adopted-ai-developer-tool",
      "github-copilot-the-world-s-most-widely-adopted-ai-developer-tool-repeat",
      "github-next-explorations",
      "github-s-ai-powered-security-platform",
      "good-design-hasn-t-changed-with-ai",
      "gpt-web-app-generator-10-000-apps-created-in-a-month-matija-sosic",
      "gpu-cloud-deployment-without-leaving-your-ide-audry-hsu-runpod",
      "graphrag-methods-to-create-optimized-llm-context-windows-for-retrieval-jonathan-larson-microsoft",
      "guide-verify-solve-the-engineering-discipline-agentic-development-demands",
      "hacking-subagents-into-codex-cli-brian-john-betterup",
      "hacking-the-inference-pareto-frontier",
      "hard-won-lessons-from-building-effective-ai-coding-agents",
      "harness-engineering-is-not-enough-why-software-factories-fail",
      "harnessing-the-power-of-llms-locally",
      "hasura-launch-realtime-data-connectivity-for-ai",
      "how-agent-o11y-differs-from-traditional-o11y",
      "how-agents-will-unlock-the-500b-promise-of-ai",
      "how-building-with-ai-can-double-the-throughput-of-your-engineering-team",
      "how-claude-code-works",
      "how-coding-agents-change-software-development-forever-hailong-zhang",
      "how-forward-deployed-engineering-is-done-at-cognition",
      "how-forward-deployed-engineering-is-done-at-factory",
      "how-i-automate-my-own-job-at-hugging-face-using-agents",
      "how-llms-work-for-web-devs-gpt-in-600-lines-of-vanilla-js",
      "how-lovable-self-improves-every-hour",
      "how-to-add-secure-code-interpreting-in-your-ai-app",
      "how-to-build-agents-that-run-for-hours-without-losing-the-plot",
      "how-to-build-an-ai-native-health-company",
      "how-to-build-trustworthy-ai",
      "how-to-improve-your-vibe-coding-ian-butler",
      "how-to-kill-the-code-review",
      "how-to-quantify-ai-roi-in-software-engineering-stanford-study-120k-devs",
      "how-to-run-evals-at-scale-thinking-beyond-accuracy-or-similarity",
      "how-to-talk-to-statues-joe-reeve-elevenlabs",
      "how-we-built-zeta2-training-an-edit-prediction-model-in-production-ben-kunkle-zed",
      "how-we-solved-context-management-in-agents-sally-ann-delucia",
      "how-zapier-builds-ai-products-and-features-with-the-help-of-braintrust",
      "human-seeded-evals-samuel-colvin-pydantic",
      "hyperspace-more-nodes-is-all-you-need",
      "i-run-a-fleet-of-ai-agents-across-three-machines-here-s-what-broke",
      "in-the-land-of-ai-agents-the-verifiers-are-king",
      "infinite-software-crisis",
      "intelligence-continual-learning-expertise",
      "intro-to-graphrag",
      "keynote-the-ai-developer-experience-doesn-t-have-to-suck-why-and-how-we-built-modal",
      "keynote-why-people-think-agent-is-a-buzzword-but-it-isn-t",
      "lawrence-jones-fighting-ai-with-ai",
      "leadership-in-ai-assisted-engineering",
      "lessons-from-building-genai-based-applications-juan-peredo",
      "lessons-from-building-linkedin-s-genai-platform",
      "let-s-talk-about-fomat-fear-of-missing-agent-time",
      "llm-codegen-fails-and-how-to-stop-em",
      "llm-knowledge-bases-a-practical-guide",
      "llm-observability-evaluation-experimentation-platform-dat-ngo-arize-ai",
      "llm-safeguards-security-privacy-compliance-anti-hallucination",
      "llms-for-the-working-programmer-become-a-10x-programming-centaur-today",
      "long-tasks-and-experienced-open-source-dev-productivity",
      "loop-engineering-from-first-principles",
      "low-level-technicals-of-llms",
      "luminal-search-based-deep-learning-compilers-joe-fioti",
      "make-your-own-event-sourced-agent-harness-using-stream-processors",
      "making-codebases-agent-ready",
      "mastering-engineering-flow-with-windsurf",
      "mcp-mega-context-problem-matt-carey",
      "mcps-are-boring-or-why-we-are-losing-the-sparkle-of-llms",
      "mentoring-the-machine",
      "mergeable-by-default-building-the-context-engine-to-save-time-and-tokens",
      "model-maxxing-rft-dpo-sft-fine-tuning-with-openai-ilan-bigio-openai",
      "most-enterprise-agentic-projects-are-doomed-here-s-why",
      "move-fast-break-nothing",
      "moving-away-from-agile-what-s-next",
      "multi-model-multimodal-and-multi-agent-innovations-in-azure-ai",
      "multiplayer-agentic-engineering-enabling-your-whole-team-and-your-best-agents-to-work-together",
      "no-code-fine-tuning-mark-hennings",
      "no-more-slop-swyx",
      "on-ai-and-knowledge",
      "on-engineering-ai-systems-that-endure-the-bitter-lesson",
      "one-developer-two-dozen-agents-zero-alignment-why-we-need-collaborative-ai-engineering",
      "one-login-to-rule-them-all-cross-app-access-for-mcp",
      "open-challenges-for-ai-engineering",
      "open-questions-for-ai-engineering",
      "open-source-is-dead-long-live-open-source",
      "openclaw-in-your-hand-building-a-physical-ai-terminal-for-local-llm-agents",
      "optimizing-llms-in-insurance-with-dspy-beyond-manual-tuning",
      "paperclip-open-source-human-control-plane-for-ai-labor-dotta",
      "perception-agents-antje-barth-amazon-agi-lab",
      "pi-coding-agent",
      "piloting-agents-in-github-copilot",
      "pragmatic-ai-with-typechat",
      "proactive-agents",
      "production-multi-agent-architecture",
      "production-software-keeps-breaking-and-it-will-only-get-worse-here-s-how-traversal-is-fixing-it",
      "pruning-agent-skills",
      "rag-in-2025-state-of-the-art-and-the-road-forward",
      "rag-is-dead-right-kuba-rogut-redacted-username",
      "ralph-loops-build-dumb-ai-loops-that-ship",
      "real-roi-lessons-from-enterprises-that-have-already-succeeded-with-llms-redacted-username-scale",
      "real-world-development-with-github-copilot-and-vs-code-harald-kirschner-christopher-harrison",
      "real-world-mcps-in-github-copilot-agent-mode",
      "realtime-multiplayer-automation-and-you",
      "recursive-coding-agents",
      "recursive-model-improvement",
      "reinforcement-learning-without-verifiable-rewards-will-brown-prime-intellect",
      "remobi-app-don-t-change-your-terminal-workflow-for-mobile",
      "replacing-12k-loc-with-a-200-loc-skill",
      "research-to-reality-bringing-frontier-ml-research-to-production",
      "research-to-reality-with-google-deepmind",
      "respect-the-process",
      "reverse-engineering-a-viking-voip-phone-protocol-with-claude-code-boris-starkov-elevenlabs",
      "rl-for-autonomous-coding-aakanksha-chowdhery-reflection-ai",
      "rlm-recursive-language-models-for-large-codebases",
      "running-ai-application-in-minutes-quick-start-with-ai-templates",
      "running-ai-application-in-minutes-quick-start-with-ai-templates-ee4087",
      "rust-is-the-language-of-the-agi",
      "safety-and-security-for-code-executing-agents",
      "scaffold-wisely",
      "scaling-ai-agents-without-breaking-reliability",
      "scaling-the-next-paradigm-of-heterogeneous-intelligence",
      "scaling-to-long-horizons",
      "self-driving-products-product-signals-to-pull-requests",
      "self-evolving-code-with-ai-enhancing-quality-and-security-in-ci",
      "semantic-blindness-500-000-sensors-confused-an-llm-raahul-singh-vanc-levstik-phaidra",
      "ship-agents-that-ship-a-hands-on-workshop-for-swe-agent-builders",
      "ship-it-building-production-ready-agents",
      "ship-production-software-in-minutes-not-months",
      "ship-real-agents-hands-on-evals-for-agentic-applications",
      "skill-issue-how-we-used-ai-to-make-agents-actually-good-at-supabase",
      "skill-issue-lessons-from-skilling-up-coding-agents-to-use-langfuse",
      "skills-are-the-new-sdks",
      "skills-at-scale",
      "software-development-agents-what-works-and-what-doesn-t",
      "software-engineering-ai",
      "software-engineering-is-becoming-plan-and-review",
      "software-fundamentals-for-ai-coding",
      "sovereign-escape-velocity-ownership-with-open-models-gus-martins-and-ian-ballantyne-google-deepm",
      "spec-driven-development-agentic-coding-at-faang-scale-and-quality-al-harris-amazon-kiro",
      "specifications-are-the-new-code",
      "state-of-data",
      "state-of-startups-and-ai-2025",
      "stateful-agents-full-workshop-with-redacted-username-packer-of-letta-and-memgpt",
      "stop-babysitting-your-agents-building-a-context-engine-for-mergeable-code",
      "stop-guessing-build-robust-ai-with-layered-cot",
      "stop-using-rag-as-memory",
      "storyteller-building-multi-modal-apps-with-ts-modelfusion-lars-grammel-phd",
      "supercharging-developer-workflow-with-amazon-q-developer",
      "swe-marathon-evaluating-coding-agents-at-billion-token-scale-rishi-desai-abundant-ai",
      "swe-rebench-lessons-from-evaluating-coding-agents-on-real-software-engineering-tasks-ibragim-bad",
      "taste-craft-a-conversation-with-tuomas-artman-cto-of-linear-and-gergely-orosz-of-the-pragmatic-e",
      "teaching-coding-agents-to-do-spreadsheets",
      "text-diffusion-brendan-o-donoghue-google-deepmind",
      "the-1-000x-ai-engineer-swyx",
      "the-2026-state-of-ai-engineering-barr-yaron-amplify-partners",
      "the-3-pillars-of-autonomy-michele-catasta-replit",
      "the-4-patterns-of-ai-native-development",
      "the-agent-awakens-collaborative-development-with-copilot",
      "the-agent-native-company",
      "the-ai-bugpocalypse-is-here-now-what",
      "the-ai-emperor-has-no-daus-why-most-devs-still-don-t-use-code-ai",
      "the-ai-evolution",
      "the-ai-pivot-with-chris-white-of-prefect-bryan-bischof-of-hex",
      "the-base-model-is-dead",
      "the-code-ai-maturity-model-and-what-it-means-for-you",
      "the-coherence-trap-why-llms-feel-smart-but-aren-t-thinking",
      "the-cure-for-the-vibe-coding-hangover",
      "the-demo-i-wish-i-d-had-openai-s-agents-sdk-serverless",
      "the-devops-engineer-who-never-sleeps",
      "the-dirty-secret-of-forward-deployed-engineering",
      "the-emerging-skillset-of-wielding-coding-agents",
      "the-engineer-of-the-future-is-the-person-who-is-able-to-choose-what-is-worth-doing-addy-osmani",
      "the-eyes-are-the-context-window-to-the-soul-how-windsurf-gets-to-know-you",
      "the-friction-is-your-judgment",
      "the-future-of-qwen-a-generalist-agent-model",
      "the-golden-age-of-ai-engineering",
      "the-great-loops-debate-dex-horthy-geoff-huntley-ian-livingstone-greg-pstrucha-moderated-by-allie",
      "the-knowledge-graph-mullet-trimming-graphrag-complexity",
      "the-last-human-code-review-building-trust-in-ai-generated-code",
      "the-making-of-devin",
      "the-many-ends-of-programming",
      "the-messy-reality-of-scale-synthetic-data-and-pre-training",
      "the-missing-primitive-for-agent-swarms",
      "the-new-application-layer",
      "the-new-primitives-building-ai-native-software",
      "the-next-game-engine-won-t-have-a-manual",
      "the-pipeline-is-dead",
      "the-prompt-is-the-platform",
      "the-rise-of-the-agentic-economy-on-the-shoulders-of-mcp",
      "the-roi-of-ai-why-you-need-eval-frameworks",
      "the-state-of-ai-code-quality-hype-vs-reality",
      "the-state-of-ai-powered-search-and-retrieval",
      "the-unofficial-guide-to-apple-s-private-cloud-compute",
      "the-unreasonable-effectiveness-of-prompt-learning",
      "the-web-browser-is-all-you-need",
      "the-z-l-continuum-should-ai-engineers-still-read-code",
      "this-video-was-edited-with-ai-agent-but-how",
      "tldraw-computer",
      "tlms-tiny-llms-and-agents-on-edge-devices-with-litert-lm",
      "to-the-moon-navigating-deep-context-in-legacy-code-with-augment-agent",
      "tools-for-the-next-generation-of-ai-engineers",
      "trust-but-verify",
      "turn-10-994-notes-into-your-agents-memory",
      "two-roads-to-durable-agents-replay-vs-snapshot-eric-allam-co-founder-trigger-dev",
      "under-5-minutes-to-a-deployed-llm-endpoint-audry-hsu-runpod",
      "understanding-is-the-new-bottleneck",
      "unlocking-ai-powered-devops-within-your-organization",
      "unlocking-developer-productivity-across-cpu-and-gpu-with-max",
      "using-agents-to-build-an-agent-company",
      "using-llms-to-secure-source-code",
      "using-oss-models-to-build-ai-apps-with-millions-of-users",
      "using-spec-driven-development-for-production-workflows",
      "velocity-sickness-what-happens-when-your-whole-team-gets-10x-faster",
      "vercel-ai-sdk-masterclass-from-fundamentals-to-deep-research",
      "vibe-coding-at-scale-customizing-ai-assistants-for-enterprise-environments",
      "vibe-coding-at-scale-customizing-ai-assistants-for-enterprise-environments-harald-kirschner",
      "vibe-coding-with-confidence",
      "vibe-engineering-effect-apps",
      "vibes-won-t-cut-it",
      "vision-zero-bugs",
      "we-cut-94-of-our-ai-coding-tokens-with-a-local-code-index-here-s-the-architecture",
      "we-gave-an-agent-production-code-access-and-then-tried-to-sleep-at-night",
      "we-vetted-2-000-ai-skills-before-they-reached-developers",
      "what-data-from-20-million-pull-requests-reveal-about-ai-transformation",
      "what-every-ai-engineer-needs-to-know-about-gpus",
      "what-if-the-harness-mattered-more-than-the-model-aditya-bhargava-etsy",
      "what-if-the-network-was-the-sandbox",
      "what-s-next-after-rlhf",
      "what-we-learned-deploying-ai-within-bloomberg-s-engineering-organization",
      "when-agents-meet-physical-data-the-other-physics-of-agent-harnesses",
      "why-agent-engineering",
      "why-and-how-you-need-to-sandbox-ai-generated-code-harshil-agrawal-cloudflare",
      "why-bolt-new-won-and-most-devtools-ai-pivots-failed-victoria-melnikova",
      "why-rust-is-the-ideal-language-for-vibe-coding",
      "why-senior-engineers-struggle-to-build-ai-agents",
      "why-the-best-ai-agents-are-built-without-frameworks-primitives-over-frameworks",
      "why-your-product-needs-an-ai-product-manager-and-why-it-should-be-you",
      "windsurf-everywhere-doing-everything-all-at-once",
      "wtf-do-people-use-open-models-for",
      "you-can-t-prompt-the-room-the-last-skill-ai-won-t-replace",
      "your-agent-failed-in-prod-good-luck-reproducing-it",
      "your-agent-is-blindfolded",
      "your-attention-is-the-bottleneck-not-your-agents-zack-proser-workos",
      "your-coding-agent-doesn-t-always-follow-your-rules",
      "your-coding-agent-just-got-cloned-and-your-brain-isn-t-ready",
      "your-coding-agent-should-do-ai-system-engineering",
      "your-finance-agent-s-bottleneck-is-you",
      "your-support-team-should-ship-code",
      "z-ai-glm-4-6-what-we-learned-from-100-million-open-source-downloads-yuxuan-zhang-z-ai"
    ]
  }
]

Organizations

584 rows

Organizations represented in the library, with their speakers and talks.

Fields & sample rows

slug · name · url · summary · speakerSlugs · talkSlugs

[
  {
    "slug": "microsoft",
    "name": "Microsoft",
    "url": "https://ai.engineer/orgs/microsoft",
    "summary": "Microsoft-affiliated AIE appearances connect enterprise retrieval with practical agent development: Pablo Castro covers Azure AI Search, Cedric Vidal demonstrates agent evaluation, and Marlene Mhangami examines testing AI-generated code. Across the recordings, workshops and technical demonstrations address how applications obtain context, expose tools, and make model-driven behavior testable, observable, and subject to application controls.",
    "speakerSlugs": [
      "sharmila-chokalingam",
      "cedric-vidal",
      "yohan-lasorsa",
      "nagkumar-arkalgud",
      "keiji-kanazawa",
      "marlene-mhangami",
      "david-smith",
      "miguel-martinez",
      "michael-albada",
      "liam-hampton",
      "julia-kasper",
      "den-delimarsky",
      "hanchi-wang",
      "ornella-bahidika",
      "emma-ning",
      "chris-noring",
      "harald-kirschner",
      "lachlan-ainley",
      "amy-boyd",
      "nitya-narasimhan",
      "pablo-castro",
      "daniel-rosenwasser",
      "pamela-fox",
      "gabriela-de-queiroz",
      "aishwarya-srinivasan",
      "tisha-chawla",
      "susheem-koul"
    ],
    "talkSlugs": [
      "accelerate-your-ai-journey-with-azure-ai-model-catalog",
      "agentic-excellence-mastering-evaluation-of-ai-agents-with-azure-ai-evaluation-sdk",
      "ai-didn-t-kill-the-web-it-moved-in-olivier-leplus-aws-yohan-lasorsa-microsoft",
      "ai-red-teaming-agent-azure-ai-foundry-nagkumar-arkalgud-keiji-kanazawa-microsoft",
      "beyond-code-coverage-functionality-testing-with-playwright",
      "build-evaluate-and-deploy-a-rag-based-retail-copilot-with-azure-ai",
      "building-applications-with-ai-agents",
      "building-code-first-ai-agents-with-azure-ai-agent-service-cedric-vidal-microsoft",
      "building-interactive-uis-in-vs-code-with-mcp-apps-marlene-mhangami-liam-hampton-github",
      "building-protected-mcp-servers",
      "cooking-with-agents-in-vs-code",
      "creating-and-scaling-your-own-custom-copilots-with-azure-ai-studio",
      "don-t-let-the-llm-drive-ornella-bahidika-joel-allou-microsoft",
      "foundry-local-cutting-edge-ai-experiences-on-device-with-onnx-runtime-and-olive-emma-ning-micros",
      "from-writing-code-to-designing-systems-how-the-developer-role-is-changing-chris-noring-microsoft",
      "full-spec-mcp-hidden-capabilities-of-the-mcp-spec-harald-kirschner-microsoft-vs-code",
      "insights-from-snorkel-ai-running-azure-ai-infrastructure",
      "mind-the-gap-in-your-agent-observability",
      "multi-model-multimodal-and-multi-agent-innovations-in-azure-ai",
      "on-ai-and-knowledge",
      "pragmatic-ai-with-typechat",
      "rag-at-scale-production-ready-genai-apps-with-azure-ai-search",
      "real-world-development-with-github-copilot-and-vs-code-harald-kirschner-christopher-harrison",
      "running-ai-application-in-minutes-quick-start-with-ai-templates",
      "running-ai-application-in-minutes-quick-start-with-ai-templates-ee4087",
      "vibe-coding-at-scale-customizing-ai-assistants-for-enterprise-environments",
      "vibe-coding-at-scale-customizing-ai-assistants-for-enterprise-environments-harald-kirschner",
      "your-agent-failed-in-prod-good-luck-reproducing-it",
      "your-voice-agent-doesn-t-need-a-frontier-model"
    ]
  },
  {
    "slug": "google-deepmind",
    "name": "Google DeepMind",
    "url": "https://ai.engineer/orgs/google-deepmind",
    "summary": null,
    "speakerSlugs": [
      "logan-kilpatrick",
      "nicholas-kang",
      "michael-aaron",
      "philipp-schmid",
      "patrick-lober",
      "paige-bailey",
      "guillaume-vernade",
      "ian-ballantyne",
      "thor-schaeff",
      "sander-dieleman",
      "kat-kampf",
      "ammaar-reshi",
      "kevin-hou",
      "paige",
      "florina-muntenescu",
      "oli-gaymond",
      "cassidy-hardin",
      "omar-sanseviero",
      "mukund-sridhar",
      "aarush-selvan",
      "raia-hadsell",
      "kp-sawhney",
      "shrestha-basu-mallick",
      "benoit-schillings",
      "gus-martins",
      "brendan-o-donoghue",
      "jack-rae",
      "kathleen-kenealy"
    ],
    "talkSlugs": [
      "a-year-of-gemini-progress-what-comes-next",
      "agentic-evaluations-at-scale-for-everybody",
      "ai-engineering-with-the-google-gemini-2-5-model-family",
      "any-to-any-building-native-multimodal-agents",
      "build-deploy-ai-powered-apps",
      "build-deploy-ai-powered-apps-18cc1b",
      "building-conversational-agents",
      "building-generative-image-video-models-at-scale",
      "building-in-the-gemini-era-kat-kampf-ammaar-reshi-google-deepmind",
      "defying-gravity",
      "don-t-ship-skills-without-evals",
      "from-transcription-to-live-music-gemini-s-audio-stack-thor-schaeff-google-deepmind",
      "frontier-feud",
      "gemini-nano-on-device-florina-muntenescu-oli-gaymond-google-deepmind",
      "gemma-4-deep-dive-cassidy-hardin-google-deepmind",
      "gemma-deepmind-s-family-of-open-models",
      "how-deep-research-works",
      "how-google-deepmind-is-researching-the-next-frontier-of-ai-for-gemini-raia-hadsell-vp-of-researc",
      "how-google-deepmind-runs-agents-at-scale-kp-sawhney-ian-ballantyne-google-deepmind",
      "let-s-go-bananas-with-genmedia",
      "milliseconds-to-magic-real-time-workflows-using-the-gemini-live-api-and-pipecat",
      "research-to-reality-with-google-deepmind",
      "sovereign-escape-velocity-ownership-with-open-models-gus-martins-and-ian-ballantyne-google-deepm",
      "text-diffusion-brendan-o-donoghue-google-deepmind",
      "thinking-deeper-in-gemini",
      "unveiling-the-latest-gemma-model-advancements",
      "veo-3-for-developers",
      "why-senior-engineers-struggle-to-build-ai-agents"
    ]
  }
]

Chapters

5,820 rows

Chapter titles and timestamps for navigating individual talks.

Fields & sample rows

talkSlug · title · startMs · endMs

[
  {
    "talkSlug": "agent-skills",
    "title": "Intro",
    "startMs": 0,
    "endMs": 181000
  },
  {
    "talkSlug": "agent-skills",
    "title": "Skills Defined",
    "startMs": 181000,
    "endMs": 300000
  }
]

Transcript downloads

1,041 rows

An index of public transcripts. Each row links to an individual JSON or CSV transcript download.

Fields & sample rows

talkSlug · title · jsonUrl · csvUrl

[
  {
    "talkSlug": "agent-skills",
    "title": "Don't Build Agents, Build Skills Instead – Barry Zhang & Mahesh Murag, Anthropic",
    "jsonUrl": "https://ai.engineer/api/data/transcript?slug=agent-skills&format=json",
    "csvUrl": "https://ai.engineer/api/data/transcript?slug=agent-skills&format=csv"
  },
  {
    "talkSlug": "ai-coding-workflow",
    "title": "Full Walkthrough: Workflow for AI Coding — Matt Pocock",
    "jsonUrl": "https://ai.engineer/api/data/transcript?slug=ai-coding-workflow&format=json",
    "csvUrl": "https://ai.engineer/api/data/transcript?slug=ai-coding-workflow&format=csv"
  }
]

CSV exports store lists and nested fields as JSON inside cells. Transcript downloads contain timestamped text; the transcript index links to each file.

Hugging Face · Restricted access

The research dataset.

Our separate Hugging Face dataset brings together transcripts, segments, topics, entities, summaries, chapters, retrieval examples, and benchmarks in Parquet. It requires authorized access and is not included in the public downloads above.

View on Hugging Face ↗

You may need to sign in with an authorized Hugging Face account to view the repository.