AI Engineer
← All AI Engineer talks

AI Engineer World's Fair 2026

Knowledge Systems: The New GTM Stack — Jeffrey Wang, Exa

Jeffrey Wang· exa18:49

Read the talk

Knowledge Systems: Turning Go-to-Market into an AI Engineering Problem

Jeffrey Wang explains how Exa combines market data, customer signals, interfaces and agents—and how permissions and forward deployed engineers keep that system usable.

From a talk by Jeffrey Wang

At a glance

Ideas worth remembering

  • A useful go-to-market data system connects market discovery with internal customer behavior, giving agents information they can act on.

  • Jeffbot separates voice from judgment: 760 emails supplied writing habits, while hundreds of decisions supplied evaluations for behavioral calibration.

  • Programmatic data access supports both agents and stable interfaces. Familiar graphical tools and flexible chat serve complementary needs.

  • Wang prioritizes customizability when choosing whether to buy or build; Exa combines Salesforce's existing sales structure with agent access through MCP.

  • Jeffbot's permissions depend on the caller: Wang can invoke reads and writes, while other employees receive drafting capabilities and restricted tool access.

  • FDEs support deals and improve the systems used to sell. Wang considers this effective with about eight or nine FDEs, while acknowledging that broader specialization may be needed as the team grows.

010:01 ↗

Engineers need to solve distribution too

Jeffrey Wang opens with a problem aimed at engineers: building a good product does not finish the job of building a company. Introducing Exa as a search engine that gives agents access to the web, he names Cursor and Cognition as users of its infrastructure. That technical product still needs a way to reach customers.

Wang rejects the argument that either product or distribution alone determines success. His position is practical: the product must work well, and the company must get it into people's hands. He recognizes the engineer's instinct to keep improving the thing being built, admitting that his own team initially did too little marketing and sales. Automation offers a way to address that gap using familiar engineering skills. Customer acquisition and support can become systems that one person can build and operate with agents.

0:120:13
Suggest correction

This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.

0:01 · section reference included

022:51 ↗

Build a live model of the world agents act on

Go-to-market work includes researching customers, identifying target companies, finding the right people inside them and building proofs of concept. Wang groups these activities around a common dependency: data. To decide whom to approach and what to demonstrate, a team needs to connect what its product does with what prospective customers need. His proposed foundation is a live model of that world that agents can act on.

That model draws on internal and external information. Internally, the company knows about its customers, employees and product usage. Externally, it can learn about companies, people and daily events. Wang describes the scale as over 60 million companies worldwide and over a billion people on LinkedIn. The design implication is to consider both the information available inside the business and the changing information outside it, then make those sources accessible to agents.

Wang traces this approach to Exa's launch in the middle of 2023, after GPT-4 appeared. He found that GPT-4 could already automate entire parts of go-to-market work, so agents became an early design assumption. He organizes the implementation around two interfaces and two kinds of agents: ways to inspect the business, and ways to do work using its data.

2:593:05
Suggest correction

This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.

2:51 · section reference included

035:26 ↗

The ICP dashboard maps the addressable market

The ICP dashboard answers a broad question: which customers and use cases matter to Exa? Wang says the team uses Exa to classify almost every company within its total addressable market. Categories include model providers, AI coding platforms such as Cursor, and go-to-market intelligence tools. The dashboard turns a market definition into groups of identifiable companies that the team can investigate.

Each company also has a detailed record. Wang uses SpaceX as an example: the team can inspect anticipated annual spend and company metadata. Anticipated spend is a prospective estimate; he does not provide its calculation or an accuracy measure. He also says some category revenue details are blurred. The demonstrated structure therefore supports understanding how the team organizes opportunities, without establishing the precision of its financial estimates or completeness of its coverage.

The underlying retrieval mechanism begins with crawling the web and training embeddings for web search. Wang describes Exa as embeddings over the internet: a representation that permits semantic filtering and grouping of web information. Exa uses that capability to generate the large list of potential customers feeding the dashboard. This explains the discovery layer, though the talk does not specify a classification algorithm, refresh schedule or validation procedure.

5:265:28
Suggest correction

This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.

5:26 · section reference included

046:59 ↗

Request Lens surfaces events; Slack agents support action

Request Lens focuses attention on meaningful customer events. It alerts the team when someone signs up, runs a large number of searches, stops searching or arrives from an account the company particularly cares about. These events make the customer model operational: a change in behavior becomes a notification that someone can act on. Wang does not describe numerical thresholds for significance or claim that the alerts automatically trigger outreach.

The team then uses agents for account investigation and customer demos. Wang describes perhaps a dozen agents available inside Slack, with access to substantial internal data. Account executives can use them to build demos, while other requests ask for deeper information about customers. He calls out high spending on Devin and other agents as evidence of heavy adoption, but gives no spending figure or measured return. The concrete operating change is that research and demo construction are available through tools the go-to-market team uses directly.

6:597:02
Suggest correction

This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.

6:59 · section reference included

058:23 ↗

Jeffbot combines writing style, decision evaluations and access

Jeffbot began as Wang's attempt to build a digital version of himself during a week off in Mexico, using Opus 4.5. He first analyzed 760 of his emails to derive a writing voice. The resulting observations were specific: an average of 18 words per email and a preference for ending with “best” rather than “sincerely.” Those examples show how a personal writing assistant can be grounded in observed habits instead of a generic request to sound like its owner.

He treated judgment as a separate problem. Wang analyzed hundreds of past decisions, turned them into evaluations and used those evaluations to calibrate the agent's behavior against his own. This adds a behavioral target beyond writing style: the system should reach answers resembling his decisions as well as express them in his voice. He does not report evaluation scores, the scoring method or how examples were separated for calibration and testing, so the account explains the approach without measuring how faithfully Jeffbot reproduces his judgment.

The third component is access to company systems. Wang describes giving Jeffbot read and write access to the data he can personally access, which spans essentially the whole company. Employees can ask it to draft Slack messages containing answers or decisions, and the go-to-market team uses it to draft emails.

8:298:32
Suggest correction

This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.

8:23 · section reference included

0610:03 ↗

Programmatic access and familiar interfaces serve different needs

Wang describes Exa's go-to-market team as lean and productive, then draws out the design principles behind its tools. The first is that an agent-first company must be API-first. Both the agents and the graphical interfaces depend on reliable access to internal and external data. MCP, a CLI or another programmatic interface can provide that access; his emphasis is on making the data callable, rather than choosing one particular interface technology.

The second principle preserves a role for consistent graphical interfaces. AI can generate a new interface for a particular question, but repeated tasks benefit from a tool whose behavior users can learn over time. A stable dashboard retains that familiarity, while a chat agent provides flexibility for requests the dashboard does not anticipate. Wang therefore treats established interfaces and flexible chat as complementary components of the same system.

10:0810:10
Suggest correction

This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.

10:03 · section reference included

0711:53 ↗

Choose systems by how far you can customize them

Wang's third principle reframes the choice between buying SaaS and building software. His primary criterion is whether the system can be customized to do the work the company needs. Owning the code provides one route: the team can change it directly. Purchased software can also fit if it exposes enough capability for the team and its agents to adapt it. The relevant constraint is how much the system permits, rather than who originally built it.

Salesforce is his concrete example. Exa uses it as a database with established choices about how sales work should be organized—choices Wang does not want to recreate. He says the agents access Salesforce through MCP and the team uses that connection daily. The arrangement combines a purchased system's existing sales structure with programmatic access for custom workflows. His praise for extensive customizability is a selection principle, not a demonstration that every purchased product can support every desired change.

11:5611:57
Suggest correction

This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.

11:53 · section reference included

0813:36 ↗

Recover decisions from work history and assign tool ownership

The first audience question makes Jeffbot's evaluation method more concrete: where did the past decisions come from? Wang used Slack and email. He argues that enough company activity happens in Slack that reading substantial history can uncover hundreds of decisions. The examples therefore came from existing records of work, rather than requiring a previously maintained decision journal.

A second question asks how technical the go-to-market team needs to be. Wang distinguishes account executives who run deals, SDRs who help generate demand, and a separate forward deployed engineering organization. Staff outside FDE have learned to use AI well, but generally do not build the interfaces themselves. Training sessions help them understand and use the available tools. Effective adoption here includes sales expertise and tool fluency without requiring every salesperson to become an interface developer.

The FDE organization maintains and adds features to many of the AI systems while also running or supporting deals. That creates a direct connection between using the sales process and improving the software behind it. The same people who encounter friction in customer work can build tools to make subsequent work smoother.

13:3613:39
Suggest correction

This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.

13:36 · section reference included

0915:58 ↗

Jeffbot's permissions depend on who invokes it

An audience member identifies the security concern in a broadly accessible assistant with a cofounder's privileges: does everyone effectively get to see and change everything? Wang clarifies that Jeffbot's capabilities depend on the caller. When he invokes it, it can read and write across many systems. When someone else invokes it, it can only draft messages, and it does not receive access to all the MCPs and tools available in his own use.

This answer establishes two boundaries: what actions the assistant may perform and which tools it may access. Sharing Jeffbot does not mean sharing its full capability in every invocation. The explanation remains at the policy level, however; Wang does not describe identity verification, enforcement code or the exact data restrictions on drafts. It supports a caller-dependent permission model without demonstrating a complete security implementation.

16:0216:04
Suggest correction

This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.

15:58 · section reference included

1017:04 ↗

The FDE model combines customer work with system building

The final question asks how the FDE team came into existence. Wang answers with a hypothesis about the role's evolution. He points to Palantir's use of the FDE title and contrasts it with the solutions engineers, sales engineers and account executives familiar in other technology companies. His explanation centers on what AI allows a technical person supporting revenue to do: help with a deal and also build tooling that makes the work easier for themselves and the account executives.

In Wang's framing, AI lets work that previously amounted to two jobs fit into one role—in theory. He immediately qualifies the model's scalability. Exa has about eight or nine FDEs at the time of the talk, and he doubts that everyone will continue doing everything as the team grows. A follow-up establishes that the company has about 115 people. The ending leaves a useful limit on the organizational lesson: combining deal support and tooling is a working model at this size, not a claim that the same division of labor will scale indefinitely.

17:0417:07
Suggest correction

This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.

17:04 · section reference included

Read the complete timestamped transcript
  1. 0:01

    [music]

  2. 0:12

    >> Hey everybody, I'm Jeff. I guess I was

  3. 0:13

    introduced, but I'm the co-founder of

  4. 0:15

    Exa, and today going to give a talk on

  5. 0:19

    turning go-to-market into an AI

  6. 0:20

    engineering problem in the spirit of

  7. 0:21

    this

  8. 0:22

    AI engineering fair. And just a quick

  9. 0:24

    show of hands just to like understand

  10. 0:26

    the audience, like raise your hand if

  11. 0:27

    you're a technical.

  12. 0:30

    Okay, great. Okay, so I kind of

  13. 0:32

    oriented this talk around like

  14. 0:34

    go-to-market

  15. 0:36

    as presented to to engineers. So, happy

  16. 0:39

    that I did that.

  17. 0:40

    Cool. So, first just to like ground the

  18. 0:43

    ground like what what Exa is cuz it's

  19. 0:44

    sort of relevant inside of this

  20. 0:46

    presentation. Exa is a Exa is a search

  21. 0:48

    engine for agents.

  22. 0:49

    Think like agents are really smart, but

  23. 0:52

    they don't have access to the web. We're

  24. 0:53

    like this web MCP web tool that agents

  25. 0:55

    can access. We power Cursor, we power

  26. 0:56

    Cognition, we power a lot of the AI

  27. 0:58

    ecosystem at this point.

  28. 1:00

    And

  29. 1:01

    before we start, I also just want to

  30. 1:02

    like talk about, you know, especially to

  31. 1:03

    the technical audience, like why should

  32. 1:05

    you even care?

  33. 1:06

    Like why should you care about

  34. 1:07

    go-to-market? I guess this audience

  35. 1:08

    cares about go-to-market cuz you chose

  36. 1:09

    to go to this

  37. 1:11

    go-to-market talk, but I think there's

  38. 1:12

    this like funny narrative right now,

  39. 1:14

    which is like people are like, "Oh, like

  40. 1:15

    product is the only thing that matters."

  41. 1:17

    Or "Distribution is the only thing that

  42. 1:19

    matters." And there's all sort of like

  43. 1:20

    all sorts of like Twitter flame wars

  44. 1:22

    like like oh, is Glean going to succeed

  45. 1:24

    because they're really good at

  46. 1:25

    distribution, but they're like what what

  47. 1:26

    the heck is their product? And then and

  48. 1:28

    other people are like, "Oh, the like the

  49. 1:29

    the product needs to be super good cuz

  50. 1:31

    agents

  51. 1:32

    you know, agents shop for the product,

  52. 1:33

    so they'll shop the for the best

  53. 1:34

    product." And so, my view and my

  54. 1:36

    experience in the last few years is that

  55. 1:39

    you just kind of have to do both. Like I

  56. 1:41

    think you have to get product right and

  57. 1:42

    you have to get go-to-market right. Like

  58. 1:44

    you got to build this thing, it's got to

  59. 1:45

    be good, and then you got to get it into

  60. 1:47

    people's hands. If you don't do both

  61. 1:49

    things, then you don't have a company.

  62. 1:51

    So, that's kind of my view on the

  63. 1:53

    matter. And I I say like a really funny

  64. 1:56

    thing also is like as a technical person

  65. 1:58

    when you start a company or you start

  66. 2:00

    some some sort of project, like very

  67. 2:02

    much so the bias is like, "Hey, I'm

  68. 2:04

    going to just build the thing. I'm going

  69. 2:06

    to make it really really freaking good,

  70. 2:08

    right?" Like that's kind of like the

  71. 2:09

    bias you have as like an engineer.

  72. 2:10

    That's the bias we had when we started

  73. 2:12

    X.ai and we were like honestly pretty

  74. 2:14

    bad at go-to-market. Like we

  75. 2:15

    >> [laughter]

  76. 2:16

    >> we were not doing enough marketing, we

  77. 2:17

    were not doing enough sales.

  78. 2:18

    Um but I think the cool thing about

  79. 2:21

    about um go-to-market particularly in

  80. 2:23

    2026 is you can treat go-to-market like

  81. 2:26

    an engineering problem and particularly

  82. 2:28

    an AI engineering problem. And so I

  83. 2:30

    think that's like a super exciting

  84. 2:31

    thing. Like it's like more fun for

  85. 2:33

    engineers than ever to do go-to-market

  86. 2:36

    cuz you can automate things. You can you

  87. 2:38

    can do so much as one person and uh

  88. 2:41

    etc. Also um I want to make this

  89. 2:44

    interactive. If if anybody has questions

  90. 2:45

    at any point, please please ask cuz I'm

  91. 2:47

    aware there's a lot of talks and

  92. 2:49

    I don't want to bore you.

  93. 2:51

    Cool. So um cool. So so the hypothesis I

  94. 2:54

    have is if you're an engineer or or if

  95. 2:56

    you're anyone, you can treat

  96. 2:57

    go-to-market like an engineering

  97. 2:58

    problem. So first, I guess like what

  98. 2:59

    does what do go-to-market teams do? So I

  99. 3:01

    have like a laundry list of things here

  100. 3:04

    of things that go-to-market teams do,

  101. 3:05

    but here are a few. Like one is you got

  102. 3:06

    to research

  103. 3:08

    like your customer, right? You got to

  104. 3:09

    research your targets. You have to find

  105. 3:11

    out information about your about

  106. 3:13

    targets. You have to find the right

  107. 3:15

    people at particular companies. You have

  108. 3:17

    to build POCs. Um there's like a just a

  109. 3:19

    ton of stuff you have to do, right? Um

  110. 3:22

    so you know, I'm not going to I'm not

  111. 3:24

    going to list everything here, but like

  112. 3:25

    what is the grand unifying theme? Well,

  113. 3:27

    go-to-market is a data problem, right?

  114. 3:30

    So you have all you have this like

  115. 3:31

    entire world of uh of of what your

  116. 3:35

    product does and then and this entire

  117. 3:37

    world of like all your potential

  118. 3:38

    customers and you're just going to like

  119. 3:40

    learn and figure out what your world

  120. 3:44

    looks like. And so this is my this is my

  121. 3:46

    uh proposal. It's a data problem and we

  122. 3:48

    have to solve from a data perspective.

  123. 3:51

    Cool. So okay, so what is data that is

  124. 3:53

    relevant? Uh I propose that you need

  125. 3:56

    basically a live model of your world

  126. 3:58

    that agents can act on. And so, what

  127. 4:01

    does that mean? Okay, well, one is you

  128. 4:02

    have a ton of internal data, right?

  129. 4:04

    There's all this information that you

  130. 4:05

    know about your customers, about people

  131. 4:08

    that are at your company,

  132. 4:11

    uh

  133. 4:12

    data about how people use the product.

  134. 4:14

    That's like internal data that you know.

  135. 4:16

    And then there's all sorts of external

  136. 4:17

    data, right? Like there's over 60

  137. 4:19

    million companies in the world, and

  138. 4:21

    there's like billions of people, like

  139. 4:23

    over a billion that are on LinkedIn, for

  140. 4:24

    example, and all sorts of stuff are is

  141. 4:27

    is like happening every day, right? Like

  142. 4:28

    there's all this news. And so, when

  143. 4:31

    you're building like this data

  144. 4:33

    go-to-market system, um it's important

  145. 4:35

    to keep in mind just like all the

  146. 4:37

    different sources that exist and and and

  147. 4:39

    uh

  148. 4:40

    and are available to your agents.

  149. 4:42

    And cool. So, I'm going to like go

  150. 4:44

    through, hopefully pretty fast, just all

  151. 4:47

    the different components of what we've

  152. 4:49

    built at Exa. And just for like context,

  153. 4:53

    uh I've been really passionate about

  154. 4:54

    this for a long time. So, like Exa was

  155. 4:56

    launched in

  156. 4:58

    uh the middle of 2023, and so we were

  157. 5:00

    post-GPT-4. And

  158. 5:02

    GPT-4 was really incredible, cuz it

  159. 5:04

    could actually, even then, even though

  160. 5:06

    it's way worse than like Fable or

  161. 5:08

    whatever, like it could actually just

  162. 5:09

    automate entire

  163. 5:11

    parts of go-to-market. And so, from the

  164. 5:12

    beginning, I've been thinking about our

  165. 5:13

    go-to-market from

  166. 5:14

    from a very, very uh AI agent-first

  167. 5:16

    perspective. And so, we're going to go

  168. 5:18

    over two interfaces that we have that

  169. 5:19

    help us, and then two agents.

  170. 5:22

    Cool.

  171. 5:26

    Cool. Okay, the first is what we call

  172. 5:28

    our ICP dashboard. And the ICP dashboard

  173. 5:32

    is a product that we have internally

  174. 5:33

    that answers the question, like what is

  175. 5:35

    our world? Like what is the world of

  176. 5:38

    customers and use cases that we care

  177. 5:40

    about? And what we actually do is we go

  178. 5:44

    ahead and use Exa, and again, Exa is

  179. 5:47

    this like uh

  180. 5:49

    arbitrarily powerful search engine for

  181. 5:50

    AIs essentially. And we just classify

  182. 5:53

    basically like every possible company

  183. 5:54

    that is inside of our total addressable

  184. 5:56

    market. And I kind of blurred out some

  185. 5:59

    of the details on like how much money we

  186. 6:00

    make from each category and stuff like

  187. 6:03

    that. But yeah, we have like categories

  188. 6:04

    like model providers, AI coding

  189. 6:06

    platforms like say Cursor, go-to-market

  190. 6:07

    intelligence tools.

  191. 6:09

    And this makes up our TAM and we have an

  192. 6:11

    understanding of literally like

  193. 6:13

    almost every company within those

  194. 6:14

    segments.

  195. 6:16

    And then for each of those companies we

  196. 6:18

    can deep dive, right? So here's the

  197. 6:19

    example of SpaceX. We can see how much

  198. 6:22

    annual spend we could anticipate them to

  199. 6:23

    have then all this like metadata about

  200. 6:25

    the company. So we have a list of all

  201. 6:26

    the companies and then a ton of data

  202. 6:28

    about each company.

  203. 6:29

    How do we do this? Again, we're able to

  204. 6:32

    do this because Exa is this search

  205. 6:33

    engine. We take the internet, we crawl

  206. 6:35

    it, we train we train embeddings to do

  207. 6:38

    web search really well. And so basically

  208. 6:40

    from a technical perspective you can

  209. 6:41

    think about Exa as like embeddings over

  210. 6:43

    the internet. And when you have

  211. 6:45

    embeddings over the internet you have

  212. 6:46

    this like arbitrarily powerful semantic

  213. 6:49

    filtering and slicing and dicing of any

  214. 6:51

    type of data that you want. And so we

  215. 6:53

    use that to generate this this like

  216. 6:54

    gigantic list of potential ICPs.

  217. 6:59

    Cool. Next, we have a tool we call

  218. 7:02

    Request Lens. Request Lens, what is

  219. 7:04

    Request Lens? Well, it's basically a

  220. 7:05

    system where anytime something

  221. 7:07

    significant happens with any of our

  222. 7:08

    customers, we're alerted.

  223. 7:10

    Someone signed up, someone used a ton of

  224. 7:13

    searches, someone stopped using

  225. 7:14

    searches, someone showed up that we

  226. 7:16

    really really care about. All these

  227. 7:18

    things are signals that we are notified

  228. 7:20

    about and that our team can act on.

  229. 7:28

    Cool.

  230. 7:29

    So those are the two interfaces that we

  231. 7:31

    have and then I'll go over two types of

  232. 7:33

    agents that we have. So

  233. 7:34

    one is coding agents. So our

  234. 7:37

    go-to-market team

  235. 7:38

    is crazy crazy crazy deep on agents. So

  236. 7:42

    like like our our our engineering team

  237. 7:44

    uses a lot of agents, but our

  238. 7:45

    go-to-market team is like like you could

  239. 7:46

    look you could look at some of their

  240. 7:47

    like devin spend and like other agent

  241. 7:49

    spend. It's really freaking high. And

  242. 7:50

    that's because everybody on our

  243. 7:52

    go-to-market team is constantly asking

  244. 7:54

    agents about our customers.

  245. 7:57

    Uh we have like

  246. 7:58

    like account executives that build demos

  247. 8:01

    for our customers. Like it's just this

  248. 8:03

    crazy ecosystem where we have like maybe

  249. 8:05

    a dozen different agents inside of our

  250. 8:07

    Slack and anybody can use any of them.

  251. 8:09

    They all have access to tons and tons of

  252. 8:10

    our internal data. And uh yeah. Anytime

  253. 8:13

    we want to dig deeper on account,

  254. 8:15

    anytime we want to make a demo, etc., we

  255. 8:17

    depend heavily on agents.

  256. 8:23

    Cool. And then I want to talk about

  257. 8:24

    another really cool agent that I'm

  258. 8:25

    pretty proud of. We call it Jeff Bots.

  259. 8:27

    Uh or I call it Jeff Bots. Uh Jeff Bots

  260. 8:29

    is an AI clone of myself. Uh as much as

  261. 8:32

    possible. So, what is it? Well,

  262. 8:34

    basically

  263. 8:35

    this winter break uh

  264. 8:38

    I'm sure a lot of you spent that break

  265. 8:39

    playing with Opus 4.5. And I was no

  266. 8:42

    different. So, I was in Puerto No, I was

  267. 8:44

    in Mexico. I was in Mexico and I would I

  268. 8:46

    had a week off. And so, my goal with

  269. 8:49

    that week and with Opus 4.5 was to uh

  270. 8:52

    just try to make a digital clone of

  271. 8:53

    myself. And so, I did things like

  272. 8:54

    analyze

  273. 8:55

    like 760 of my emails to figure out what

  274. 8:59

    my email voice is. Like, oh, I use 18

  275. 9:01

    words on average per email and I like to

  276. 9:03

    end emails with best and not sincerely.

  277. 9:05

    Like all all that type of stuff, right?

  278. 9:06

    So, I made like a like a voice for

  279. 9:09

    myself.

  280. 9:10

    And then I also made a decision-making

  281. 9:13

    framework. So, I made like a

  282. 9:14

    decision-making framework where I

  283. 9:16

    analyzed hundreds of decisions I've made

  284. 9:17

    in the past.

  285. 9:19

    And I I analyzed them and I created

  286. 9:21

    evals. So, I actually created evals from

  287. 9:23

    those decisions and calibrated this

  288. 9:25

    agent system to behave like myself.

  289. 9:29

    And then finally I gave it like read and

  290. 9:30

    write access to all the data that I

  291. 9:32

    personally have. And there's a cool

  292. 9:34

    advantage to this because like I

  293. 9:35

    basically have access to every single

  294. 9:37

    system at the company

  295. 9:39

    uh cuz I'm in the the the nice seat

  296. 9:41

    of of having that and so like um yeah,

  297. 9:45

    this thing has access to like

  298. 9:46

    everything. And basically what happens

  299. 9:48

    is anybody at the company can use

  300. 9:49

    Jeffbot to create drafts of Slack

  301. 9:52

    messages that are basically like answers

  302. 9:54

    or decisions that are made. And this is

  303. 9:56

    a huge great thing. Like our

  304. 9:57

    go-to-market team uses it to like draft

  305. 9:59

    emails, for example.

  306. 10:03

    Cool. Um

  307. 10:05

    all right, so those those are the

  308. 10:06

    systems that uh

  309. 10:08

    that we have at at Exa. It works pretty

  310. 10:10

    well. Our go-to-market team is very

  311. 10:11

    lean, but very productive.

  312. 10:14

    Um and so yeah, I just want to cover

  313. 10:15

    like

  314. 10:16

    lastly just a few principles

  315. 10:19

    um

  316. 10:20

    principles I have

  317. 10:22

    around what it means to be an

  318. 10:23

    agent-first company.

  319. 10:25

    So firstly, to be agent-first you must

  320. 10:27

    be API-first, right? So like all these

  321. 10:29

    systems that we built, whether they were

  322. 10:30

    those whether it was those agents or

  323. 10:32

    whether it was those GUIs that we have,

  324. 10:35

    like if there did not exist really good

  325. 10:37

    APIs on top of any internal and external

  326. 10:39

    data

  327. 10:40

    we'd be we'd be out of luck, right? Like

  328. 10:42

    you need to create really good APIs. If

  329. 10:44

    you don't have really good APIs your

  330. 10:46

    agents are not going to be able to have

  331. 10:48

    data access. So you can think about this

  332. 10:50

    as MCP, CLI, whatever, right? Like it

  333. 10:52

    doesn't really matter. Uh you just need

  334. 10:53

    some interface that's programmatic.

  335. 10:57

    Secondly is like I I think there's like

  336. 10:58

    still this mistake in

  337. 11:00

    the agent world which is made that's

  338. 11:02

    like hey, does everything

  339. 11:04

    need to be a chatbot?

  340. 11:06

    Uh

  341. 11:07

    I think the answer is no. Like I think

  342. 11:09

    I think both GUIs and chatbots are are

  343. 11:12

    both super useful and have their own

  344. 11:16

    benefits. Like uh I don't know how many

  345. 11:19

    people in this room have thought about

  346. 11:19

    dynamic user interfaces

  347. 11:21

    but like yes, dynamic user interfaces

  348. 11:24

    are amazing. Like yes, technically AI

  349. 11:26

    can just produce a new UI for any use

  350. 11:28

    case that you have. Like

  351. 11:30

    just to answer a question, it could

  352. 11:31

    produce like an HTML markdown file,

  353. 11:32

    right? But I think there is something

  354. 11:34

    really nice about being able to visit

  355. 11:36

    the same consistent UX for the same use

  356. 11:39

    cases over time so that you can like

  357. 11:41

    learn how to use some tool. Um so yeah,

  358. 11:43

    I think like having crystallized UIs and

  359. 11:45

    then also arbitrarily powerful flexible

  360. 11:47

    chat agents are both important

  361. 11:49

    components of being agent first.

  362. 11:53

    And then finally,

  363. 11:55

    uh

  364. 11:56

    you know, there's this question like,

  365. 11:57

    "Hey, should you like shop for like

  366. 11:59

    Salesforce

  367. 12:00

    or should you like build your own CRM or

  368. 12:03

    something, right?" I actually think this

  369. 12:05

    is like a false dichotomy. It's like

  370. 12:08

    like there it's not a choice. Like we

  371. 12:10

    don't live in a world where the choice

  372. 12:11

    is between purchasing SaaS and building

  373. 12:13

    things yourself. Like the way I like to

  374. 12:15

    think about it is like

  375. 12:18

    you should just be using something that

  376. 12:20

    is arbitrarily customizable, right? Like

  377. 12:22

    whether you like obviously if you build

  378. 12:24

    something yourself, then it's

  379. 12:25

    arbitrarily customizable cuz you can

  380. 12:26

    write code and make it better at any

  381. 12:28

    given point.

  382. 12:29

    But also if you procure SaaS, um if you

  383. 12:33

    can make that SaaS work on your behalf

  384. 12:35

    and

  385. 12:36

    be arbitrarily customizable, then that

  386. 12:38

    works too, right? Like you don't need to

  387. 12:39

    build this like

  388. 12:41

    GUI and like have a proactive roadmap as

  389. 12:44

    to like what features would make really

  390. 12:45

    great sense inside of some system. Like

  391. 12:47

    if you can arbitrarily customize the

  392. 12:49

    system, even if it's a system you've

  393. 12:50

    purchased, then you're like pretty good,

  394. 12:52

    right? So like for example, we use

  395. 12:53

    Salesforce. Like we use Salesforce at

  396. 12:55

    X.ai and uh it's great because uh it's a

  397. 12:58

    really good good database. It's made a

  398. 13:00

    lot of amazing choices around what sales

  399. 13:03

    should look like, choices that we don't

  400. 13:04

    want to make ourselves. And then it

  401. 13:06

    exposes MCP. So all of our agents have

  402. 13:08

    access to Salesforce MCP. Works really

  403. 13:10

    well. Our team uses it every day.

  404. 13:11

    And so yeah, I think infinite

  405. 13:13

    customizability um is is really the

  406. 13:15

    highest order bit.

  407. 13:19

    Cool. Um

  408. 13:21

    that's that's all I had.

  409. 13:23

    Uh

  410. 13:24

    Yeah, does anyone have any questions?

  411. 13:26

    >> Oh, we have time for a few questions.

  412. 13:28

    Okay, coming.

  413. 13:36

    >> Hey, um so you said you uh took all your

  414. 13:39

    past decisions. Can you elaborate a bit

  415. 13:41

    about that?

  416. 13:43

    What What artifacts are those?

  417. 13:45

    Usually people don't save like their

  418. 13:47

    decisions. Is it Slack? Is it email? Is

  419. 13:49

    it other other artifacts?

  420. 13:52

    >> Yeah, good question. I looked at

  421. 13:53

    decisions I made within Slack and email.

  422. 13:56

    I mean, a surprisingly large amount of

  423. 13:59

    everything that goes on a company is

  424. 14:01

    is is on Slack, right? So like if you

  425. 14:03

    just read like a ton of Slack history,

  426. 14:04

    like you can definitely find hundreds of

  427. 14:07

    decisions that you made in the past.

  428. 14:09

    >> Awesome. Quick question uh over here. Uh

  429. 14:12

    so your go-to-market team, what's the

  430. 14:13

    split between uh are they just all like

  431. 14:17

    AI cracked or do they also have like the

  432. 14:19

    domain expertise, too? What's the split

  433. 14:21

    between

  434. 14:22

    technical and non-technical? Because

  435. 14:24

    obviously you need them to like know how

  436. 14:26

    to do marketing, sales, etc. But then do

  437. 14:28

    they also are they also upskilling in

  438. 14:30

    terms of using AI systems? Are you

  439. 14:31

    handing them tools or they building

  440. 14:33

    their own?

  441. 14:35

    >> That's a very good question. So our

  442. 14:37

    go-to-market team

  443. 14:39

    is comprised of like there's there's

  444. 14:42

    account executives which like run the

  445. 14:44

    deals.

  446. 14:45

    There are like sales like SDRs that help

  447. 14:49

    with uh demand generation.

  448. 14:51

    And then there are separately they're

  449. 14:54

    separate like a FDE org. So forward

  450. 14:56

    deployed engineering organization.

  451. 14:58

    And

  452. 14:59

    what I'll say is that like

  453. 15:02

    everyone that's Okay, everyone that's uh

  454. 15:04

    not not in FDE

  455. 15:06

    is like

  456. 15:08

    has learned how to use AI really well.

  457. 15:11

    So like

  458. 15:12

    the answer is like they're not vibe

  459. 15:13

    coding. They're not generally with you

  460. 15:16

    know, in some there's some exceptions.

  461. 15:17

    They're not generally vibe coding these

  462. 15:18

    interfaces that we have. Um but they're

  463. 15:20

    using the tools really really well. And

  464. 15:22

    like we make sure that we have training

  465. 15:24

    sessions and like just make sure that

  466. 15:25

    people

  467. 15:26

    really understand how to use these

  468. 15:28

    tools. And then this funny we have this

  469. 15:30

    funny thing which is like our four

  470. 15:31

    deployed engineering organization is

  471. 15:33

    actually the one that like does a lot of

  472. 15:35

    the maintenance and feature building

  473. 15:37

    uh of these AI systems. And so they're

  474. 15:39

    both running deals and like like

  475. 15:42

    supporting deals

  476. 15:43

    um but then also making

  477. 15:46

    everything smoother by like

  478. 15:48

    doing sales but then also building the

  479. 15:51

    sales system. Like it's it's kind of

  480. 15:54

    it's kind of a funky thing we have going

  481. 15:55

    on. Yeah.

  482. 15:58

    >> How do you think about uh

  483. 16:00

    different security?

  484. 16:02

    >> Oh.

  485. 16:02

    >> Hey. How do you think about different uh

  486. 16:04

    security boundaries within your

  487. 16:05

    enterprise? What do you What you said

  488. 16:07

    suggested that you've got Jeffbot which

  489. 16:09

    had runs with all of your full

  490. 16:11

    privileges and then it's available to

  491. 16:13

    everybody which suggests that there's

  492. 16:14

    one security level and everyone can see

  493. 16:16

    everything all the time. Is that what

  494. 16:18

    you're going with or

  495. 16:19

    is there some uh other guardrails in

  496. 16:21

    place?

  497. 16:22

    >> Yeah, that's a good question. We we pay

  498. 16:24

    pretty special we we pay pretty careful

  499. 16:26

    attention to guardrails. So for example

  500. 16:29

    um in the case of Jeffbot

  501. 16:31

    um

  502. 16:32

    when I use Jeffbot and I call Jeffbot

  503. 16:34

    has access to

  504. 16:36

    a ton of systems and it can for example

  505. 16:38

    do reads and writes. However, when

  506. 16:40

    anybody else calls Jeffbot all can do is

  507. 16:42

    draft messages and also I don't give

  508. 16:45

    Jeffbot

  509. 16:46

    permissions to

  510. 16:48

    all of our MCPs and tools in the case

  511. 16:50

    where other people call it. And so in

  512. 16:52

    short it's like pretty

  513. 16:54

    it's pretty well defined or we we we do

  514. 16:56

    pay some care to the security.

  515. 16:58

    Yeah.

  516. 16:59

    >> Okay, last question.

  517. 17:04

    >> Um, can you can you share the origin

  518. 17:07

    story of the FDE team? Did that just

  519. 17:10

    happen organically or did you

  520. 17:11

    intentionally do it? I'm just really

  521. 17:13

    curious like how that came to exist.

  522. 17:16

    >> Yeah, for sure. I mean,

  523. 17:18

    uh

  524. 17:19

    my

  525. 17:20

    my philos- my my hypothesis on this is

  526. 17:22

    like, once upon a time the FDE role

  527. 17:24

    didn't really exist. Like, Palantir

  528. 17:26

    started calling some people FDEs, but it

  529. 17:28

    that was really it. And what tech

  530. 17:30

    companies had was like solutions and

  531. 17:32

    sales engineers.

  532. 17:34

    And then, like account executives.

  533. 17:37

    >> I was a solutions engineer.

  534. 17:38

    >> Got it. Yeah, yeah. The thing The thing

  535. 17:40

    that I think has changed is that um

  536. 17:42

    because of AI, as like

  537. 17:46

    en- as a technical person that is

  538. 17:48

    supporting revenue generation,

  539. 17:51

    you can actually not only support the

  540. 17:52

    revenue generation, but then very easily

  541. 17:54

    build the tooling

  542. 17:55

    to smooth everything over.

  543. 17:58

    And make your own life easier, make the

  544. 18:00

    lives of AEs easier. Like, because of

  545. 18:01

    AI, this is just possible now. Like,

  546. 18:03

    that's like two

  547. 18:04

    Before that was like two jobs, and now

  548. 18:05

    it's like one job.

  549. 18:07

    Um in theory. Like, now when our team

  550. 18:09

    grows, like right now it's about eight

  551. 18:11

    or nine FDEs, like what will will it

  552. 18:13

    scale such that everyone does

  553. 18:14

    everything? Probably not. But, at least

  554. 18:16

    right now that's what we have, and I

  555. 18:17

    think that's a really good working model

  556. 18:18

    to get pretty far.

  557. 18:20

    >> Eight out of how many?

  558. 18:22

    >> Uh eight Oh, eight of like how big is

  559. 18:23

    our go-to-market org?

  560. 18:24

    >> Or eight You have eight FDEs, and the

  561. 18:26

    size of the company right now is how

  562. 18:28

    many?

  563. 18:28

    >> Oh, the We're about 115 people.

  564. 18:31

    >> Okay.

  565. 18:31

    >> Yeah.