← All popular talks

Popular talk #13

12-Factor Agents: Patterns of reliable LLM applications — Dex Horthy, HumanLayer

Dex Horthy17:06

Now playing

Agent Builder's Journey

0:00

Join the discussionComment on this moment0:00

Synced transcript

Follow the talk

Agent Builder's Journey
Pattern Recognition
JSON & Tools
Control Flow
Pause & Resume
Prompts & Context
Human Contact
Micro Agents
Stateless Agents
Summary

Community discussion

What did you agree with—or push back on?

Specific reactions make these talks more useful. Draft here, add the moment you’re discussing, then choose the direct-post pilot or the YouTube handoff.

Automated overview

What this talk covers

Dex Horthy, founder of HumanLayer, presents the 12-Factor Agents framework for building reliable LLM-powered applications, arguing that production-grade agents are primarily deterministic software with targeted LLM steps rather than fully autonomous loops. He distills patterns: own prompts and context windows, treat tools as JSON and code, use small focused agents with three to ten steps, contact humans via tool calls. Horthy emphasizes context engineering—LLMs are pure functions—and shows how to compact errors, unify state, and add pause/resume via APIs. He shares a DevOps agent that became a bash script, and advocates for outer-loop agents. The framework, which gained 4,000 GitHub stars in two months, treats agents as stateless reducers that meet users on any channel, with engineers controlling the inner loop of token and control flow.

This overview is derived from the transcript and has not been independently fact-checked by AI Engineer.

Chapters

  1. 0:00Agent Builder's Journey
  2. 1:38Pattern Recognition
  3. 3:24JSON & Tools
  4. 5:01Control Flow
  5. 7:20Pause & Resume
  6. 8:37Prompts & Context
  7. 11:20Human Contact
  8. 12:21Micro Agents
  9. 14:25Stateless Agents
  10. 15:09Summary