Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Agentic Engineering Patterns

simonwillison.net

Post reply on HN
Print view View original

241–250 of 341 posts

Re: Agentic Engineering Patterns

#241

Post by didgeoridoo »

lbreakjai wrote: post #109

We're going to do it again, aren't we? We're going to take something simple and sensible ("write tests first", "small composable modules", etc.), give it a fancy complicated name ("Behavior-Constrained Implementation Lifecycle pattern", "Boundary-Scoped Processing Constructs pattern", etc.), and create an entire industry of consultants and experts selling books and enterprise coaching around it, each swearing they ha…

I don’t know, Simon has had a pretty sane and level head on his shoulders on this stuff. To my mind he’s earned the right to be taken seriously when talking about approaches he has found helpful.

Re: Agentic Engineering Patterns

#242

Post by pc86 »

slaye wrote: post #168

Simon, if you're reading this, I'd be really curious to hear your thoughts on how to effectively conduct code reviews in a world where "code is cheap". One of the biggest struggles I have on my team is coworkers straight up vibing parts of the code and not understanding or guiding the architecture of subsystems. Or at least, not writing code in a way that is meant to be understood by others. Then when I go through th…

"It works, why change it?" is a horrible attitude but is an organizational and interpersonal problem, not a technical one. They're only 1/3 of the way done according to Kent Beck.¹

There are plenty of orgs using AI who still care about architecture and having easily human-readable, human-maintainable code. Maybe that's becoming an anachronism, and those firms will go the way of the Brontosaurus. Maybe it will be a competitive advantage. Who knows?

¹ "Make it work, make it right, make it fast."

Re: Agentic Engineering Patterns

#243

Post by xXSLAYERXx »

esafak wrote: post #193
slaye wrote: post #168

Simon, if you're reading this, I'd be really curious to hear your thoughts on how to effectively conduct code reviews in a world where "code is cheap". One of the biggest struggles I have on my team is coworkers straight up vibing parts of the code and not understanding or guiding the architecture of subsystems. Or at least, not writing code in a way that is meant to be understood by others. Then when I go through th…

Code review should be mandatory and reviewers should ask big PRs to be broken up, and its submitters to be able to defend every line of code. For when the computer is generating the code, the most important duty of the submitter is to vouch for it. To do otherwise creates the bad incentive of making others do all your QA, and nobody is going to be rewarded for that.

> Code review should be mandatory and reviewers should ask big PRs to be broken up

Always, even before all this madness. It sounds more like a function of these teams CR process rather than agents writing the code. Sometimes super large prs are necessary and I've always requested a 30 minute meeting to discuss.

I don't see this as an issue, just noise. Reduce the PR footprint. If not possible meet with the engineer(s)

Re: Agentic Engineering Patterns

#244

Post by fhd2 »

malexw wrote: post #195
simonw wrote: post #174

Earlier quoted context omitted.

This is genuinely one of the most interesting questions right now. I don't have solid answers yet, and I'm very keen to learn what people are finding works. If you accelerate the pace of code creation it inevitably creates bottlenecks elsewhere. Code review is by far the biggest of those right now. There may be an argument for leaning less on code review. When code is expensive to produce and is likely to stay in pro…

I think Martin Fowler's "Refactoring" might give a bit of insight here. One of my take-aways after reading that book is that the specific implementation of a function is not very important if you have tests. He argues that it can sometimes be easier to completely re-write a function than to take the time to understand it - as long as you can validate that your re-write performs the same way. This mindset lines up pre…

That's my experience with agentic development so far, a lot of extra time goes into testing.

Problem is, the way I've been trained to test isn't exactly antagonistic. QA does that kind of thing. Programmers writing tests are generally rather doing spot checks that only make sense if the code is generally understood and trustworthy. Code LLMs produce is usually broken in subtle, hard to spot ways.

Re: Agentic Engineering Patterns

#245

Post by atomicUpdate »

simonw wrote: post #174
slaye wrote: post #168

Simon, if you're reading this, I'd be really curious to hear your thoughts on how to effectively conduct code reviews in a world where "code is cheap". One of the biggest struggles I have on my team is coworkers straight up vibing parts of the code and not understanding or guiding the architecture of subsystems. Or at least, not writing code in a way that is meant to be understood by others. Then when I go through th…

This is genuinely one of the most interesting questions right now. I don't have solid answers yet, and I'm very keen to learn what people are finding works. If you accelerate the pace of code creation it inevitably creates bottlenecks elsewhere. Code review is by far the biggest of those right now. There may be an argument for leaning less on code review. When code is expensive to produce and is likely to stay in pro…

> When code is expensive to produce and is likely to stay in production for many years it's obviously important to review it very carefully. If code is cheap and can be inexpensively replaced maybe we can lower our review standards?

I don't care how cheap it is to replace the incorrect code when it's modifying my bank account or keeping my lights on.

Re: Agentic Engineering Patterns

#246

Post by esafak »

cma256 wrote: post #192
simonw wrote: post #174

Earlier quoted context omitted.

This is genuinely one of the most interesting questions right now. I don't have solid answers yet, and I'm very keen to learn what people are finding works. If you accelerate the pace of code creation it inevitably creates bottlenecks elsewhere. Code review is by far the biggest of those right now. There may be an argument for leaning less on code review. When code is expensive to produce and is likely to stay in pro…

> There may be an argument for leaning less on code review. When code is expensive to produce and is likely to stay in production for many years it's obviously important to review it very carefully. If code is cheap and can be inexpensively replaced maybe we can lower our review standards? Agree with everything else you said except this. In my opinion, this assumes code becomes more like a consumable as code-producti…

It assumes that bugs are rare and easy to fix. A look at Claude Code's issue tracker (https://github.com/anthropics/claude-code/issues) tells you that this is not so. Your product could be perpetually broken, lurching from one vibe coded bug to another.

Re: Agentic Engineering Patterns

#247

Post by bluemario »

The "human in the loop at key checkpoints" pattern has been the most practically useful for us. We found that giving the agent full autonomy end-to-end produces subtly broken code that passes tests but violates implicit invariants you never thought to write down. Short loops with a human sanity check at decision forks catches that class of failure early.

The thing I keep wrestling with is where exactly to place those checkpoints. Too frequent and you've just built a slow pair programmer. Too infrequent and you're doing expensive archaeology to figure out where it went sideways. We've landed on "before any irreversible action" as a useful heuristic, but that requires the agent to have some model of what's irreversible, which is its own can of worms.

Has anyone found a principled way to communicate implicit codebase conventions to an agent beyond just dumping a CLAUDE.md or similar file? We've tried encoding constraints as linter rules but that only catches surface stuff, not architectural intent.

Re: Agentic Engineering Patterns

#248

Post by benmathes »

simonw wrote: post #174
slaye wrote: post #168

Simon, if you're reading this, I'd be really curious to hear your thoughts on how to effectively conduct code reviews in a world where "code is cheap". One of the biggest struggles I have on my team is coworkers straight up vibing parts of the code and not understanding or guiding the architecture of subsystems. Or at least, not writing code in a way that is meant to be understood by others. Then when I go through th…

This is genuinely one of the most interesting questions right now. I don't have solid answers yet, and I'm very keen to learn what people are finding works. If you accelerate the pace of code creation it inevitably creates bottlenecks elsewhere. Code review is by far the biggest of those right now. There may be an argument for leaning less on code review. When code is expensive to produce and is likely to stay in pro…

One model I've seen is moving the review stage to the designs, not the code itself.

I.e. have a `planning/designs/unbuilt/...` folder that contains markdown descriptions of features/changes that would have gotten a PR. Now do the review at the design level.

Re: Agentic Engineering Patterns

#249

Post by TeeWEE »

slaye wrote: post #168

Simon, if you're reading this, I'd be really curious to hear your thoughts on how to effectively conduct code reviews in a world where "code is cheap". One of the biggest struggles I have on my team is coworkers straight up vibing parts of the code and not understanding or guiding the architecture of subsystems. Or at least, not writing code in a way that is meant to be understood by others. Then when I go through th…

We make the creator of the PR responsible for the code. Meaning they must understand it.

Also, we only allow engineers to commit (agent generated) code. Designers just come up with suggestions, engineers take it and ensure it fits our architecture.

We do have a huge codebase. We are teaching Claude Code with CLAUDE.md's and now also .spec.md (often a summary of the implementation plan).

In the end, engineers are responsible.

Re: Agentic Engineering Patterns

#250

Post by esafak »

ornornor wrote: post #198
slaye wrote: post #168

Simon, if you're reading this, I'd be really curious to hear your thoughts on how to effectively conduct code reviews in a world where "code is cheap". One of the biggest struggles I have on my team is coworkers straight up vibing parts of the code and not understanding or guiding the architecture of subsystems. Or at least, not writing code in a way that is meant to be understood by others. Then when I go through th…

I’m running into this problem as well with juniors slinging code that takes me a very long time to understand and review. I’m iterating on an AGENTS.md file to share with them because they aren’t going to stop using AI and I’m a little tied of always saying the same things (Claude loves to mock everything and assert that spies were called X times with Y arguments which is a great recipe for brittle tests, for example…

Have an AI reviewer take the first crack at it after pointing it to your rules file (e.g., AGENTS) so you don't have to repeat yourself. Gemini does this fairly well, for example. https://developers.google.com/gemini-code-assist/docs/review...
Post reply on HN