Videos wpOA-UXynoM

How Forward Deployed Engineering is done at Factory — Eno Reyes

index_state ready data_status ok

AI Engineer· published 2026-07-28· 0:21:21· en-US· indexed 2026-08-10 19:38

Open on YouTube

52 shot(s).

keyframes kept every frame deduplicated

What was stored

cues: 187; whisperx 187
chunks: 36; from 187 cues
keyframes: 20; kept of 52 captured
frames with text: 20; 429 lines read
chapters: 12; from the source metadata
keyframe bytes: 6.2 MB; word timings on 187 cues

Provenance

Each pipeline stage, its state and the model that produced it
stage	state	model	started	took
`fetch`	done	—	2026-08-09 22:05	0s
`stt`	done	—	2026-08-09 05:33	22s
`chunk`	done	—	2026-08-09 05:33	0s
`text_embed`	done	—	2026-08-10 19:38	0s
`keyframe`	done	—	2026-08-09 05:33	2m 40s
`ocr`	done	—	2026-08-09 05:36	10s
`frame_embed`	done	—	2026-08-10 19:38	4s

Frames, and what the machine read

0:02 #0 done2 line(s)

shot 0·sharpness 454.1
1. AlEngineer0.95
2. World's Fair0.97
0:03 #1 done2 line(s)

shot 1·sharpness 665.2
1. AIEngineer0.95
2. World's Fair0.99
0:10 #2 done24 line(s)

shot 2·sharpness 2746.2
1. LAB & PLATINUM SPONSORS0.99
2. Amazon AGI Lab0.98
3. ANTHROP\C1.00
4. Google DeepMind1.00
5. MINIMAX0.94
6. OpenAI0.92
7. Akamai1.00
8. arize0.93
9. aws1.00
10. Braintrust bright data0.98
11. B1.00
12. Browserbase1.00
13. docker1.00
14. :neo4j0.92
15. ORACLE1.00
16. PayPal1.00
17. qodo1.00
18. reducto1.00
19. Sonar1.00
20. Makers of0.99
21. togetherai1.00
22. Unblocked1.00
23. WorkOS1.00
24. SonarQube1.00
0:16 #3 done2 line(s)

shot 3·sharpness 192.6
1. AlEngineer1.00
2. World's Fair0.99
0:55 #4 done2 line(s)

shot 4·sharpness 189.7
1. AlEngineer1.00
2. World's Fair0.99
1:37 #5 done26 line(s)

shot 5·sharpness 1605.3
1. View0.98
2. History1.00
3. Bookmarks Profiles Tab0.98
4. Window1.00
5. Help1.00
6. 品1.00
7. Tue Jun 30 10:44 AM0.98
8. AlEngineer0.99
9. World'sFair1.00
10. uetooth1.00
11. Not Playing1.00
12. 密0.51
13. AI ENGINEER WORLD'S FAIR1.00
14. Display1.00
15. How Deployed Engineering1.00
16. PRESENTED BY1.00
17. Microsoft1.00
18. works at Factory1.00
19. We don't do the work for you. We hand you a model for doing it yourself, then0.99
20. make it real on your own codebase.0.99
21. ENO REYES1.00
22. CO-FOUNDER & CTO, FACTORY0.99
23. 20261.00
24. 1/111.00
25. World's Fair0.95
26. Engineering the future of Al1.00
1:40 #6 done21 line(s)

shot 6·sharpness 1601.8
1. navigate1.00
2. z00m0.80
3. Do Not Disturb1.00
4. AlEngineer0.98
5. 01 - THE MISCONCEPTION0.96
6. World'sFair1.00
7. What people think “forward deployed” means0.98
8. 00.51
9. PRESENTED BY1.00
10. Microsoft1.00
11. The Palantir-era playbook: parachute elite engineers in to1.00
12. do the work on behalf of the customer.0.99
13. Write the integrations, ship the features, run the migration.1.00
14. Bodies in, output out0.98
15. A consultancy with better engineers. Revenue is linear in people.0.99
16. Value is the deliverable. The engineer is the product.0.99
17. Nothing compounds: when they leave, the capability leaves with them.1.00
18. Scales with headcount. Leaves when the contract does.1.00
19. 2/111.00
20. World's Fair0.96
21. Engineering the future of Al0.98
2:07 #7 done25 line(s)

shot 7·sharpness 1909.2
1. Ffullscreen·navigate · zoom0.91
2. AlEngineer0.98
3. World'sFair1.00
4. 01 - THE MISCONCEPTION0.98
5. What people think “forward deployed"0.99
6. means1.00
7. 00.66
8. PRESENTED BY1.00
9. The Palantir-era playbook: parachute elite1.00
10. Microsoft1.00
11. engineers in to do the work on behalf of the0.99
12. customer.1.00
13. Bodies in, output out0.98
14. Write the integrations, ship the features, run the0.99
15. migration.1.00
16. A consultancy with better engineers. Revenue is linear in1.00
17. people. Nothing compounds: when they leave, the capability1.00
18. Value is the deliverable. The engineer is the product.1.00
19. leaves with them.0.98
20. Scales with headcount. Leaves when the contract1.00
21. does.1.00
22. 2/111.00
23. Word's Fair0.91
24. TRACK 8· JUNE 30, 20260.96
25. Forward Deployed Engineering1.00
2:20 #8 skipped

shot 8·duplicate of #7
2:57 #9 done16 line(s)

shot 9·sharpness 2306.1
1. Ffullscreen·navigate0.96
2. zoom0.99
3. AlEngineer0.96
4. World'sFair1.00
5. 02- THE REFRAME0.97
6. Forward deployed at Factory1.00
7. is not a services business0.97
8. They are not there to do your work. They are there to install a new model of how0.99
9. software gets built — and prove it on your real systems.0.99
10. That difference is why we don't call them FDEs. We call them Deployed1.00
11. Engineers — they install a model, they don't staff your backlog.0.98
12. The goal is to work yourself out of a job. That is the point, and it compounds.0.99
13. 3/111.00
14. World'sFair0.95
15. TRACK 8·JUNE 30,20260.98
16. Forward Deployed Engineering1.00
3:30 #10 skipped

shot 10·duplicate of #9
3:39 #11 skipped

shot 11·duplicate of #9
4:01 #12 done20 line(s)

shot 12·sharpness 1256.7
1. fullscreen· navigate· zoom0.90
2. AlEngineer0.97
3. World'sFair1.00
4. 03 - THE MODEL WE INSTALL0.98
5. The software factory1.00
6. Not one agent that codes. An integrated system of agents across every stage of the fifecycle,0.98
7. sharing context, governed by humans. Signal in, software out.0.99
8. m0.51
9. SIGNAL1.00
10. TRIAGE1.00
11. PLAN1.00
12. EXECUTE1.00
13. VALIDATE1.00
14. SHIP1.00
15. MONITOR1.00
16. Step one of the job: get the customer to see their org as a factory, not a backlog.0.99
17. 4/111.00
18. World's Fair0.97
19. TRACK 8· JUNE 30, 20260.96
20. Forward Deployed Engineering0.99
4:07 #13 done36 line(s)

shot 13·sharpness 2161.8
1. Ffullscreen0.99
2. navigate0.95
3. zoom0.81
4. AlEngineer0.98
5. World'sFair1.00
6. 04 - THE FEEDBACK LOOP0.97
7. Forward deployed is the tip of the spear of0.98
8. the product.1.00
9. 00.55
10. Living and breathing with a company's engineering leadership isn't just delivery0.99
11. — it's our sharpest R&D signal. What we learn at the edge flows straight back0.99
12. into the product.1.00
13. SELF-ASSEMBLY1.00
14. CANONICAL WORKFLOWS1.00
15. ROI & ANALYTICS1.00
16. Every deployment teaches us how0.99
17. The workflows we design at one0.99
18. Proximity to engineering leadership0.99
19. Factory should assemble itself1.00
20. customer become canonical, pre-1.00
21. sharpens our ROl storytelling and1.00
22. inside a company — informing the0.98
23. built missions — then roll out to0.97
24. analytics — we learn what outcomes0.99
25. agentic workflows that let the1.00
26. hundreds of thousands of engineers0.98
27. leaders actually measure, and build0.99
28. platform stand up faster and deeper0.99
29. who never had to discover them.1.00
30. the product to prove them.1.00
31. the next time.0.99
32. The edge of the deployment is the leading edge of the roadmap.0.99
33. 5/111.00
34. World's Fair0.91
35. TRACK 8· JUNE 30, 20260.96
36. Forward Deployed Engineering1.00
4:46 #14 skipped

shot 14·duplicate of #13
5:16 #15 skipped

shot 15·duplicate of #12
5:40 #16 skipped

shot 16·duplicate of #12
5:56 #17 skipped

shot 17·duplicate of #12
6:29 #18 skipped

shot 18·duplicate of #12
7:02 #19 done21 line(s)

shot 19·sharpness 1424.0
1. F fullscreen· navigate zoom0.92
2. AlEngineer0.98
3. World'sFair1.00
4. 03 - THE MODEL WE INSTALL0.97
5. The software factory1.00
6. Not one agent that codes. An integrated system of agents across every stage of the fifecycle,0.99
7. sharing context, governed by humans. Signal in, software out.1.00
8. PRESENTED BY1.00
9. Microsoft1.00
10. SIGNAL1.00
11. TRIAGE1.00
12. PLAN1.00
13. EXECUTE1.00
14. VALIDATE1.00
15. SHIP1.00
16. MONITOR1.00
17. Step one of the job: get the customer to see their org as a factory, not a backlog.0.99
18. 4/111.00
19. World's Fair0.92
20. TRACK 8·JUNE 30,20260.98
21. Forward Deployed Engineering1.00
7:13 #20 skipped

shot 20·duplicate of #7
7:41 #21 skipped

shot 21·duplicate of #12
8:11 #22 skipped

shot 22·duplicate of #12
8:48 #23 skipped

shot 23·duplicate of #13

Transcript

187 cues· 3,642 words· 20,292 chars

chunk 0 · 0:12–0:55 · 132 words · 815 chars
0:12 This is the forward deployed engineering track, in case you're in the wrong room.
0:16 As you already know, forward deployed engineering is one of the hottest topics in AI.
0:20 The most important companies on the planet are building out massive FTE teams.
0:24 So think OpenAI, Anthropic, Google DeepMind, you get the idea.
0:28 Forward Deployed Engineering was pioneered by Palantir many years ago to embed really strong software engineers directly into their customers' orgs to implement and customize their platforms around the nuances of the real world.
0:40 So today we brought in some amazing speakers from Anthropic, Cursor, Factory, RAMP, Decagon, and many more to talk about the current state of Forward Deployed Engineering, how it works at their companies, and where it's going.
chunk 1 · 0:52–1:07 · 47 words · 298 chars
0:52 Our first speaker
0:54 Our first speaker is Eno Reyes.
0:56 He's the co-founder and CTO at Factory, which is building autonomous software engineering agents for enterprise teams.
1:01 Previously, he worked in machine learning and software engineering roles at Hugging Face and Microsoft.
1:06 Let's give it up for Eno.
chunk 2 · 1:11–1:47 · 109 words · 544 chars
1:11 yeah hey everyone excited to chat today um and you know basically i my hope is that at the end of this you guys get a sense of some of the work that we're doing on behalf of our customers and with our customers and the role of what we call a deployed engineer should hopefully be a little bit clearer since i think that there are honestly tons of different models um for uh for how this should actually operate inside of an org and so
1:40 I think that when we start, I do think that there are some nuances in sort of like the Palantir era playbook.
chunk 3 · 1:47–2:31 · 134 words · 729 chars
1:47 And generally the way that Forward Deployed goes is I see that there are lots of different takes on sort of where Forward Deployed sits within the org, how much it interfaces with the actual product team or the engineering team, how much work is done on behalf
2:02 half of the customers versus with them and how much work is done on code itself or basically like in the software system versus with the humans and sort of strategizing, right?
2:13 And so generally I think in this older model, a lot of the way that software needed to be built was you needed to go and access that code base.
chunk 4 · 2:23–3:08 · 121 words · 712 chars
2:23 You needed to integrate directly into data streams or software or products that basically you could only access behind the curtain of the customer.
2:32 And so if you were building something that was heavily integrated into their environment, you kind of had the need to send and sort of parachute in individuals into the org.
2:42 But really, that has transformed over time into a role that sort of forks out.
2:49 And you see a lot of people who are sort of quote unquote forward deployed engineers or deployed engineers or applied AI engineers.
chunk 5 · 2:56–3:35 · 111 words · 616 chars
2:56 And it's always a little bit unclear.
2:59 Are they doing maybe professional services work on behalf of their customer?
3:03 Are they transforming the product around an individual customer?
3:08 Are they just building entirely net new things in the customer's environment, maybe on top of your product?
3:14 And I think that, at least at Factory, we definitely do not want to be doing professional services work on behalf of a customer.
3:23 So if a customer says, I want to do a modernization of a code base, and I just got quoted from all of the big consulting firms, it's going to cost this much, could you do this consulting work for us?
chunk 6 · 3:36–4:07 · 106 words · 540 chars
3:36 our goal is not to go and actually do that migration on their behalf, even if we happen to be using our product, right?
3:44 And that is because we don't think that that actually makes our product that much better.
3:48 And ultimately, that is a great way to get, I'd say, a decent amount of revenue.
3:52 But I don't think that that's the way that you can scale a business out enormously, right?
3:56 And so what we've done is we've instead said, we need deployed engineers to be the tip of the spear of the product.
4:03 And I'm going to do this and then go back.
chunk 7 · 4:07–4:47 · 120 words · 711 chars
4:07 But really when we say the tip of the spear, what we mean is that deployed engineers are basically the stream of information from our largest and most critical customers of the engineering leadership in that org, the on the ground tactical engineers, their thought process about how software development and AI is actually happening at that org.
4:27 and then flowing all of that information back into our product to then rapidly adjust our product in order to then fit into the customer's environment better, right?
chunk 8 · 4:37–5:22 · 133 words · 762 chars
4:37 And so factory really should be, when it gets deployed, and I'll talk about what factory is in a second, but we want that to be effectively self-assembled inside of our customer's environment, right?
4:48 And then there's a lot of work that goes into understanding that customer's environment, the flows that happen, and ultimately the ROI story.
4:57 And what factory really is to our customers is a set of building blocks for building a software factory, right?
5:06 And so when we say software factory, what we mean is there's this implicit process that every organization in the world sits on top of.
chunk 9 · 5:13–5:53 · 117 words · 699 chars
5:13 where signals from the outside world flow in on one side.
5:17 And those signals could be a lot of different things.
5:19 It could be customer conversations.
5:21 It could be bug reports.
5:22 It could be internal Slack or Teams conversations.
5:25 It could be an executive saying, we're going to build this thing, right?
5:28 All of these are signals.
5:30 Some of them have higher weight than others.
5:32 And those signals flow in, and humans, implicitly or explicitly, then choose to then prioritize, triage, and build plans around those signals.
5:42 Those plans are then converted, typically by software developers, into changes into some source of truth, a code base, an engineering system.
chunk 10 · 5:51–6:36 · 126 words · 752 chars
5:51 And as those changes are actually executed on,
5:54 they flow through a validation stage where people maybe review the code, they QA, they assess the security implications, they pass it through automated validation like SAS tools, linters, type checkers, and ultimately, when everything passes, they then ship and deploy.

Chapters

0:00 Introduction: where forward deployed sits
2:08 The role inside the customer's environment
3:49 The tip of the spear of the product
5:03 The software factory: signals in, outcomes out
6:57 Why you own the agent harness
8:11 Air gapping Droid inside the customer
10:08 The autonomy maturity model
12:05 Making a codebase agent ready
14:53 Migrating 40 million line codebases
16:38 The city of the future analogy
18:34 Constrained autonomy and legal droid
20:04 Redefining the forward deployed role