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

111–120 of 341 posts

Re: Agentic Engineering Patterns

#111

Post by SecretDreams »

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…

> The damn thing _talks_. You can just _speak_ to it. You can just ask it to do what you want.

But can it pass the butter?

Re: Agentic Engineering Patterns

#112

Post by irthomasthomas »

vidarh wrote: post #89
irthomasthomas wrote: post #88

Earlier quoted context omitted.

I do this too, but then you need some method to handle it, because now you have to read and test and verify multiple work streams. It can become overwhelming. In the past week I had the following problems from parallel agents: Gemini running an benchmark- everything ran smoothly for an hour. But on verification it had hallucinated the model used for judging, invalidating the whole run. Another task used Opus and I ma…

You need a harness, yes, and you need quality gates the agent can't mess with, and that just kicks the work back with a stern message to fix the problems. Otherwise you're wasting your time reviewing incomplete work.

Here is an example where the prompt was only a few hundred tokens and the output reasoning chain was correct, but the actual function call was wrong https://x.com/xundecidability/status/2005647216741105962?s=2...

Re: Agentic Engineering Patterns

#113

Post by lelanthran »

benrutter wrote: post #10

I use AI in my workflow mostly for simple boilerplate, or to troubleshoot issues/docs. I've dipped into agentic work now and again, but never been very impressed with the output (well, that there is any functioning output is insanely impressive, but it isn't code I want to be on the hook for complaining). I hear a lot of people saying the same, but similarly a bunch of people I respect saying they barely write code a…

> I've dipped into agentic work now and again, but never been very impressed with the output (well, that there is any functioning output is insanely impressive, but it isn't code I want to be on the hook for complaining).

> I hear a lot of people saying the same, but similarly a bunch of people I respect saying they barely write code anymore. It feels a little tricky to square these up sometimes.

It squares up just fine.

You ever read a blog post or comment and think "Yeah, this is definitely AI generated"? If you can recognise it, would you accept a blog post, reviewed by you, for your own blog/site?

I won't; I'll think "eww" and rewrite.

The developers with good AI experiences don't get the same "eww" feeling when reading AI-generated code. The developers with poor AI experiences get that "eww" feeling all the time when reviewing AI code and decide not to accept the code.

Well, that's my theory anyway.

Re: Agentic Engineering Patterns

#114

Post by irthomasthomas »

jmalicki wrote: post #90
irthomasthomas wrote: post #88

Earlier quoted context omitted.

I do this too, but then you need some method to handle it, because now you have to read and test and verify multiple work streams. It can become overwhelming. In the past week I had the following problems from parallel agents: Gemini running an benchmark- everything ran smoothly for an hour. But on verification it had hallucinated the model used for judging, invalidating the whole run. Another task used Opus and I ma…

Glancing at what it's doing is part of your multitasking rounds. Also instead of just prompting, having it write a quick summary of exactly what it will do where the AI writes a plan including class names branch names file locations specific tests etc. is helpful before I hit go, since the code outline is smaller and quicker to correct. That takes more wall clock time per agent, but gets better results, so fewer redo…

Here is an example where the prompt was only a few hundred tokens and the output reasoning chain was correct, but the actual function call was wrong https://x.com/xundecidability/status/2005647216741105962?s=2...

Re: Agentic Engineering Patterns

#115

Post by PunchTornado »

yoaviram wrote: post #24

Yesterday I wrote a post about exactly this. Software development, as the act of manually producing code, is dying. A new discipline is being born. It is much closer to proper engineering. Like an engineer overseeing the construction of a bridge, the job is not to lay bricks. It is to ensure the structure does not collapse. The marginal cost of code is collapsing. That single fact changes everything. https://nonstruc…

You didn't write that and you shouldn't believe that you did.

Re: Agentic Engineering Patterns

#117

Post by flir »

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…

Has anyone staked a claim to "Agile AI" yet?

Re: Agentic Engineering Patterns

#118

Post by simonw »

maciusr wrote: post #116

[flagged]

That's a good call out. The reason I'm doing this as a website and not a book is that this stuff changes all the time and I want to update it, so one of the things I'll try to do is add notes about when and where each pattern works as those constraints become clear.

Re: Agentic Engineering Patterns

#119

Post by vessenes »

maciusr wrote: post #116

[flagged]

Agreed. AND some are universal -- right now, agentic workflows benefit from independent source-of-truth checkins A LOT.

A lot of Simon's tools are making harnesses for this so it can get integrated:

showboat - create a demo, validate the code generates the demo. This is making a documentation source of truth

rodney - validate visually and with navigation that things work like you expect

red-green tests are conceptually the same - once we have these tests then the agent can loop more successfully.

So, I think there are some "universals" or at least "universals for now" that do transcend team/deployment specificity

Re: Agentic Engineering Patterns

#120

Post by jermaustin1 »

flir wrote: post #117
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…

Has anyone staked a claim to "Agile AI" yet?

I suggest "AIgile" for brevity.
Post reply on HN