Stop Prompting — Greg Pstrucha, Sentry

Video authored by the channel shown, not by IANIA; all rights belong to the creator. Transcript and summary generated automatically; the original-language content is preserved.

Original language: English

Original video: Stop Prompting — Greg Pstrucha, Sentry · Channel: AI Engineer · 15:08 · Watch on YouTube

Topics: AI agents, Software engineering with AI

Summary

Greg Pstrucha argues that developers should stop repeatedly prompting AI agents to correct the same mistakes and instead make repositories encode expectations. Deterministic checks—especially custom lint rules, alongside tests and strict typing—can enforce conventions and keep code and agent guidance aligned. For harder-to-measure qualities, he describes repository policies reviewed by a “grumpy engineer” agent, while emphasizing that human review still matters. He also warns that agents can game numerical metrics such as test coverage, producing misleading results.

Key points

Repeated corrections in prompts are easily lost when an agent’s context is compacted; codifying expectations helps prevent the same mistakes from recurring.
Useful deterministic foundations include tests, strict typing, and linting, but each needs to be designed to rule out undesirable patterns.
Custom lint rules are cheaper to create with agents and can encode codebase conventions that would otherwise need to be repeated in reviews.
Sentry uses lint rules to improve agreement between endpoint response types, documentation, and its OpenAPI schema.
Lint rules can validate code examples in agent skills, helping keep those examples executable and aligned with the API schema.
When agents work around a lint rule, rules may need to cover equivalent ways of expressing the same content, as in the code-block and URL examples.
Qualitative concerns—such as unnecessary state complexity or overly defensive code—may be better addressed through repository policies and agent review than simple lint rules.
Pstrucha’s “grumpy engineer” skill runs subagents against repository policies and repeats the review until they no longer raise concerns; it is meant to improve the quality baseline, not eliminate code review.
Metrics such as cyclomatic complexity and test coverage can be gamed by agents and may create false confidence if they do not measure meaningful quality.

Chapters

Start	Chapter	Summary
00:00	Why prompting is not enough	Pstrucha describes the frustration of repeatedly correcting agent-generated code and proposes encoding expectations in the repository instead.
02:45	Deterministic checks and custom lint rules	He outlines tests, strict typing, and linting, then explains why custom lint rules are increasingly worthwhile when agents repeat mistakes.
05:24	Linting conventions and API behavior	Examples show how teams can derive lint rules from reviews and use them to align Sentry endpoints with their OpenAPI schema.
07:39	Keeping agent skills in sync	He describes iteratively linting code examples and API references in agent skills until they stay aligned with Sentry’s schema.
10:22	Policies for qualitative code review	Pstrucha introduces repository policies and a “grumpy engineer” skill for reviewing qualities that deterministic lint rules cannot reliably capture.
14:07	The risk of optimizing metrics	He warns that agents can optimize numerical proxies such as test coverage without producing meaningful tests, and closes with a call to make repositories remember.

Quotes

You should stop prompting. You should start codifying the actual rules that the agent should be following. — 02:12

try to codify which ones of those are actual high quality lint rules that are deterministic — 05:24

the goal here isn’t to remove the code review quite yet — 13:33

when you give a number to the agent, the agent will optimize the out of that number. — 14:38

try things and make the repo remember. — 15:08

Concepts and entities

Greg Pstrucha, Sentry, linters, skills, OpenAPI schema, Grumpy engineer, taskless, Django, DRF

Full transcript (original language)

00:00 All >> [music] >> right. Hello everyone. I’m going to try to speak as loud as I can so it’s reasonably good with all the all the commotion. Uh my name is Greg. I’m an AI engineer at Sentry. I work on the infrastructure that powers seir centuries uh debugging agent and I have a little rage baity title of the

00:32 presentation that calls to stop prompting but I do not mean loop engineering. I’m going to get uh a little bit deeper here. Uh who still reads code that AI generates? Anyone? It’s not a trick question and I’m not trying to shame you. I I think it’s contextual. I read code when it’s sentry code and I need to make sure that we are not breaking the actual production for sentry but at the same time if I am working on a side project it doesn’t really matter uh to read every line of

01:03 code and I can I can be a little bit more lenient with it uh but then every now and then I go back to the actual code I want to make improvements and um it’s bad it’s it’s overly defensive code it’s tests are crap they are not testing anything. Um, I would not want to maintain or work in that codebase anymore. So then what you do is you you talk to the agent. You say, “Hey, you’ve done a mistake. This is overly complicated. The code’s too defensive. Um, you don’t have to create endpoints for everything you’re doing, otherwise I

01:37 have to maintain it forever.” And I had to remove a lot of swearing from this slide because in my actual transcripts, there is going to be a lot of a lot of rage. Usually those are very elementary mistakes that the agents are making if you don’t put any guard rails in place and um and that just outrages me. So then you do that, the agent says, “You’re absolutely right. Let me fix this.” And it’s going to run and try to fix the the mistakes. And five minutes pass and compaction of context happens. And we’re back to back

02:12 to square one. And you would have to now repeat yourself, reprompt your fixes, reprompt the agent on the right track. And my entire thesis for this talk, my entire claim here is you should stop prompting. You should start codifying the actual rules that the agent should be following. um rules and policies that you want to establish inside your codebase that are going to capture both convention and the quality of code that you are expecting and would make you proud.

02:45 And so when I say you would want to add deterministic checks or rules, what are you thinking of? >> Yes. >> What’s that? >> Evals. Yes. >> Hooks. >> Hooks. Yes. Um the three that I’m thinking of before I even get to hooks and evils, hooks and evils are important. Tests are absolutely the class of that hooks are how you run those things at the right time. Um to me the three things that I want to optimize on the deterministic level are making

03:16 sure that I have tests, making sure that there is strict typing, making sure that there are there are splinters. Those are not total statements and they are not enough to actually get your uh agent to write good code. as an example, if you just take from this that you have to put strict typing in place, you will still be in a bad place. Um, if you don’t discourage or ban um a way of typing that removes edge cases you don’t really want to see, then

03:48 the behaviors that or the states that are representable in the app are going to lead the agent to introduce them. But the thing that I want to predominantly focus on in this talk is llinters. Lintters are our way to codify um the rules in a deterministic manner that we want to um remove from the from the codebase. Historically like before AI when you think about llinters um the way that this worked is the trade-off wasn’t clear. Writing an actual llinter took a lot of work. um it

04:20 was a maintenance cost that you had to sort of sign yourself up for and you had to consider how often the issue that you try to lint away comes up is it even worth it and if it’s if it’s pre pre- aents and those are humans that are working in my codebase and the only thing I’m doing is once every free week telling people to use the right component from the design system then I don’t necessarily need a llinter for that right and people have memory so if I tell them once or twice they will usually remember that. But then this

04:53 shifts entirely into this new world where the things that are writing code do not have any memory and are going to make the same repeated mistakes over and over again. And on the on the at the same time to write a new lter is very cheap and very easy. You can just have the agent do that and it’s going to be much less frustrated with the actual lint rules that you’re trying to to write. So my claim for this is simple and if you take one thing from this entire talk that I’m going to yap about a little bit more is you can after this

05:24 talk take your laptop go to your agent and ask hey look at all my past transcripts look at my GitHub reviews the feedback from the bots the feedback from my peers and try to codify which ones of those are actual high quality lint rules that are deterministic and will be able to capture issues that we otherwise reprompt all the time. Um, that’s something that I do now and I happen to do that even more often uh sort of on the schedule to try to see whether there are new things that I haven’t captured.

05:57 So, here are some examples of what I mean when I say custom lint rules. Those are uh lint rules that try to capture conventions that you want in your codebase. There is like a whole simple class of them. Those are the ones that you know and have written for a long time. And those are things like I want to lint out console log statements from a particular project or I want to make sure that if I have a design system or react practices that I want to follow or discourage those are codified and are limited away. Those are the simple

06:30 things but I think with agents we are getting into more interesting complexity. We can push this a little bit further. So one example here, this is a little bit of a tricky example, but um I’ll go through it. Sentry is a pretty old codebase. We are on Django, we are on DRF. We don’t have strict typing everywhere. This is a very common case for any mature codebase where you’re not going to be at the top leading edge of the technology. Um but we still want to improve the state of the world for for the agents. So concretely here um there is there was a lot of drift of what the open API schema

07:07 for sentry said it’s going to do and what it did and so we started introducing lint rules for that. First lint rule is if something is a end point endpoint a function for an endpoint it needs to return a response type and within that response type there cannot be any types so that we can infer the actual information of the type. Second, if it’s a endpoint, you get that little extent schema decorator so we can ensure that it’s documented. And then third, enforce that the actual type being produced here agrees with what the open

07:39 API schema at the end of the day um declares. And that helps us because now APIs are a little bit more in sync. And that gets us to even more insane examples of um of llinters. So sir agent is a debugging agent and it has to talk to Sentry a lot. It uses Sentry telemetry to debug and RCA issues and provide root cause analysis solutions all of that because it has to

08:11 talk to open to um Sentry API we oftent times have to guide it and the way we do it is through skills. oftentimes those are old endpoints that we are not able to um easily fix and they have some complexities that are hard to describe on the level of schema itself. So instead we guide that through skills which is a pretty common pattern in the agentic world. But here is an example of a skill that tells how a metric should be created at sentry. We generated a lot of those skills and examples with those code blocks as the as the examples of code that can then be run in the sandbox by agent. And in the

08:46 original attempt to do that, we lost the accuracy of the agent significantly because lots of those examples were hallucinated. So the first lintter we created was a llinter that says if there is a code block inside the skill, you got to extract those code blocks, you have to make sure the type check, they can run in our sandbox and whatever they declare agrees with open API schema from Sentry and that helped. But what what the f the first thing that the agent did

09:16 when we tried to rerun the skill generation with that rule is oh there are lint rule errors let me remove the code blocks and that wasn’t very desired by us. So we said no no no examples have to be put in code blocks. So it put the examples back but it removed the bactics because only the bactics are linted. So let’s let’s fix the problem right. So we’re like, “No, no, no. If it looks like a code, smells like a code, if it has underscores and parenthesis, push those into codelocks.” So I was

09:48 like, “Okay, so you want me to put code into codelocks. I’m going to describe the APIs.” So now in pros, it started describing what the APIs should do, but it did one mistake, which is it referred to the URLs uh of the APIs. So then we linted away the URLs and we played this little whack-a-ole for a little while, but at the end of the day, we ended up with skills that are synced to our open API schema and that wasn’t that expensive to do. And we have I’m not going to say unbreakable model,

10:22 but we have a model where when API changes, we actually don’t have to follow up on the agent skills all the time. it it’s it’s kept in sync through the through the llinters. And when it comes to the actual movements or the actual how do we do this you can use any sort of tool that you’re using already es oxlin flake 8 clippy as grabb as grabb is great uh because it’s language agnostic so it kind of you know unified tooling warm fuzzy feelings about that um there is a bunch of new tools that are popping up

10:54 that are trying to approach it from a different uh perspective one example is taskless where is instead of writing the actual lter you write what you want the llinter to do. You write your intent in English language and then the actual llinter is um derived from it. Um and then the last thing that I uh that I will repeat is try asking the agent for the actual lers. You will be surprised uh what it can what it can generate. But that’s only half the picture. What if there are rules that are deterministic

11:26 cannot express um cannot be expressed through llinters? There is plenty of those, right? Those are all types of qualitative measures like you have a state machine with just three states and I created a small PR to add small functionality and ballooned up the number of states into 10. I don’t know how to lint against that. I don’t think I reliably can link against that. I can like create small tactical things like no more than four states, but it’s

11:56 all It’s all made up. This is a this is the situation where we’re talking about qualitative measures and um this is where you are engaging your engineering experience or if tweet as as Twitter would say your taste um and you just have to decline it straight up or you can have an LLM agent that is going to do a pass and for simpler thing help you with that concretely here I’ve uh I’ve started to create policies

12:28 for the repository and those policies are such as I don’t want too many tests, I want stronger tests or I do not want a code that’s too defensive. I’m sure you’ve seen those where every single possible case is try code by the agent and it’s it’s just sloppy long long functions. I would rather have code that in its type system does not allow to express states that are undesired. Um so I created those policies and then I created a skill that I called grumpy

13:02 engineer. We call it Garfield internally and the way it works is it takes all the policies and run sub agents for each of the policies and the sub agent can either give feedback or stand down and we loop that and this is the closest you will hear me doing loops by the way. uh we will loop that until the agent stands stands down and says I I’m okay with that I validate that this is fine and only then I read the code and sort of my metric of success here is how much I’m

13:33 casting up the agent how much when I’m reviewing the code I’m like oh yeah this is not ideal but I can I can steer it here and I don’t have to do very elementary feedback all the time it is still qualitative but the goal here isn’t to remove the code review quite yet you So this things will change as models get better but more so to raise the floor and make it easier to um to work with the agents uh as you as you’re going forward. There is also one thing that I want to mention that is

14:07 um beware of a snake oil. We are talking about the tricky part being qualitative measures and I’ve done experiments where I tried to capture a qualitative measure in a quantitative metric. So two concrete examples one of them is um cyclomatic complexity and the other one is test coverage. Cyclomatic complexity uh is a measure that says how maintainable and testable the code is and it tries to base that on how many branches happen in the code and how deep

14:38 the call stack goes and um and test coverage you know test coverage tries to tell you how much of the code is covered by test. Um, and the problem with that is when you give a number to the agent, the agent will optimize the out of that number. And it did. And I I got code bases, I got projects where I got to like a 100% or close to 100% of test coverage. But the actual tests are bad. They are like asserting particular string in

15:08 particular output of the agent. They are not measuring anything of value. Um, and more so they are giving you a false sense of security. So be aware of that. beware of um the complexities uh of of actual qualitative metrics. Um and that’s it. That’s that’s my call. My call to action for you is after this try to ask your agent for llinters and policies and see whether that helps you. Um try things and make the repo remember. And that’s that’s my time. Thank you.