The AI Record
Think about this, like, you run it five times, and out of five, how many times does it succeed? And … maybe in several cases it hits 100% all the time, which is great, but in others not. And depending on how you change your context, it will influence which tests actually work or not. I find it personally helpful to think about this as error budgets, I give a set of tests … that I really care about, so it's only allowed … to fail minimally, and other pieces are okay. So that's how you have to think about testing context, you cannot do, like, exact testing all the time.

Patrick DeboisProduct DevRel Lead · Practitioner, Tessl

Context. Debois explains how he tests the instructions and skills given to a coding agent, because the same test run twice can give different results.

Talk: Context Is the New Code, AI Engineer (YouTube), May 3, 2026, at 13:04.

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 tools or services, 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, 2026-11-04).

Around 13:04 in whisper and captions. The ellipses cover 'you know,' and 'and error budgets'. Whisper's 'which tests actually work' matches the passage; the captions have 'test', which is a plain mishearing.

How to cite this passage

Patrick Debois (Tessl), “Context Is the New Code”, AI Engineer (YouTube), 2026-05-03, at 13:04. https://www.youtube.com/watch?v=bSG9wUYaHWU Archived at https://the-ai-record.com/passages/tessl-testing-context-run-five-times-error-budgets-2026

More from the same source

But the way that I see it is they're just the engine. If you give the engine the wrong fuel, which is context, they're not going to perform. So and you can't do anything on the LLMs, at least not me, right? I'm just using the coding agent, I'm using whatever they give me. But I can optimize my context. And that's I think the message, doing this more in an engineered way than just copy and … things and hoping for the best.

Patrick DeboisProduct DevRel Lead · Practitioner, Tessl

Context. Debois closes the talk by saying where he puts his effort when using a coding agent he did not build.

Talk: Context Is the New Code, AI Engineer (YouTube), May 3, 2026, at 23:45.

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

once you thought you were going to save time by writing actually your context instead of all your code, but if you take this rigorously, you're going to spend time … writing the right evals. And that's kind of like a lot of work … because now you don't only have one prompt that you're trying to get right, it's like all the prompts of the evals.

Patrick DeboisProduct DevRel Lead · Practitioner, Tessl

Context. Debois answers an audience question after the talk, about the effort that testing context takes.

Talk: Context Is the New Code, AI Engineer (YouTube), May 3, 2026, at 26:07.

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

I had large pieces of code that I was using, maybe some helpers and some other pieces, and I just turned them into a skill. We had that into our product. It was an onboarding from … AI agents. People have … Node.js, all the various things, then they have different tools for packaging, and it is impossible to actually code that. Like it will require a lot of coding. But if I just say a skill says, please first figure out what their package manager is, then figure out what their ecosystem is, and then do these steps together with the user, you know, it … solved a lot more problems that we could ever code.

Patrick DeboisProduct DevRel Lead · Practitioner, Tessl

Context. Debois describes turning code helpers into a skill for the onboarding of AI agents into Tessl's product.

Talk: Context Is the New Code, AI Engineer (YouTube), May 3, 2026, at 1:37.

Not yet checked [ Grade B ] Said in the last year Sells AI tools Passage page

Something wrong? Report a correction. JSON: /api/v1/passages/tessl-testing-context-run-five-times-error-budgets-2026.json