What I've seen is that when we started introducing … and loops and eventually more autonomous work within the whole organization, a new technical path opened. All of a sudden, we were helping the agent with tooling, building tooling for the agent and that kind of reignited some of the developers … kind of felt that it wasn't for them. Not all of a sudden, they were like, yes, we can do this, we have that knowledge, we're like somehow helping this even with a kind of programmatic way.

Patrick DeboisProduct DevRel Lead · Practitioner, Tessl

Context. Debois, who says earlier in the talk that his observations include Tessl, is describing developers' reaction to prompting and spec-writing and then to building harnesses; the speaker does not say which team 'we' is.

Talk: Coding Agents Don't Scale Themselves. Neither Do Your Teams. The Rise of Agent Enablement, AI Engineer World's Fair 2026 (YouTube), July 2, 2026, at 03:53.

Checked against the source [ Grade B ] Said in the last year Sells AI tools

Filed under

Who is speaking

Patrick Debois, Product DevRel Lead. Speaks from developer-relations work at Tessl and from teams he has seen adopt coding agents; a vendor employee, so he describes other organizations' practice second-hand and promotional framing is possible.

Tessl sells AI or agent tooling, so it has a reason to publish flattering numbers about AI. The passage stays in the archive; read it with that in mind.

How this was checked

Checked against the source by a first reader, then confirmed independently by a second reader who fetched the source without seeing the first reader's notes (Independent review agent (Claude Sonnet), blind second pass from passage text and citation only, no repository access, 2026-10-31).

Matched in the whisper transcript, about lines 36 to 41. The first … stands in for the word 'hardness' and the second for 'who'. Remaining wording is exact, including the speaker's garbled grammar. Speaker is Patrick Debois.

How to cite this passage

Patrick Debois (Tessl), “Coding Agents Don't Scale Themselves. Neither Do Your Teams. The Rise of Agent Enablement”, AI Engineer World's Fair 2026 (YouTube), 2026-07-02, at 03:53. https://www.youtube.com/watch?v=zCJtYuqwm7E Archived at https://the-ai-record.com/passages/tessl-building-tooling-for-agent-reignited-developers-2026

More from the same source

I think what I hear from most companies is they say, first step is we give them an exercise and we want them to really go nuts on the … to solve this. … Now, after they pass this, you do a walkthrough and you actually say, please explain me what happened. Why is this a good idea?

Patrick DeboisProduct DevRel Lead · Practitioner, Tessl

Context. Debois relays what he hears from companies about interviewing engineers in the age of coding agents; it is his account of other companies' practice, not Tessl's.

Talk: Coding Agents Don't Scale Themselves. Neither Do Your Teams. The Rise of Agent Enablement, AI Engineer World's Fair 2026 (YouTube), July 2, 2026, at 16:09.

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

One is you start measuring how many human touches you still do to have the agent do the right thing. That's supposed to go down.

Patrick DeboisProduct DevRel Lead · Practitioner, Tessl

Context. Debois names the first of two metrics he has come to believe in for judging how productive a team is with coding agents.

Talk: Coding Agents Don't Scale Themselves. Neither Do Your Teams. The Rise of Agent Enablement, AI Engineer World's Fair 2026 (YouTube), July 2, 2026, at 09:38.

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

What I started seeing in some of the more advanced kind of teams is that … rituals of, Hey, we're doing a planning and we're doing a retro in a team that they weren't about like, Hey, we had issues with the code, but we're seeing we had issues with the system. So on the retro part is like, Hey, the agent went over and over hit this problem. Can we fix the system? That's something you'll learn in the retro.

Patrick DeboisProduct DevRel Lead · Practitioner, Tessl

Context. Debois describes what he has seen in advanced teams adopting coding agents; he does not name the teams.

Talk: Coding Agents Don't Scale Themselves. Neither Do Your Teams. The Rise of Agent Enablement, AI Engineer World's Fair 2026 (YouTube), July 2, 2026, at 07:07.

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

Something wrong? Report a correction. JSON: /api/v1/passages/tessl-building-tooling-for-agent-reignited-developers-2026.json