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

The Agentic AI Handbook: Production-Ready Patterns

nibzard.com

Post reply on HN
Print view View original

141–150 of 151 posts

Re: The Agentic AI Handbook: Production-Ready Patterns

#141

Post by 0xbadcafebee »

galaxyLogic wrote: post #139
0xbadcafebee wrote: post #41

You should definitely read the whole thing, but tl;dr - Generate a stable sequence of steps (a plan), then carry it out. Prevents malicious or unintended tool actions from altering the strategy mid-execution and improves reliability on complex tasks. - Provide a clear goal and toolset. Let the agent determine the orchestration. Increases flexibility and scalability of autonomous workflows. - Have the agent generate,…

Could I ask the AI to create me a set of template-files as described by you above? Or if there is an example set of template files somewhere then ask the AI to do its thing based on those? Or ask the AI to create me such a set of template files for it to work on? I mean why do I need to read from HN what to do, if AI is so knowledgable and even agentic?

Yeah absolutely. But you'll need to modify it until it works better for your use case. It's all still highly flawed, but also highly capable. Like a very fast janitor that occasionally uses chocolate syrup instead of soap to mop the floor.

Re: The Agentic AI Handbook: Production-Ready Patterns

#142

Post by kaycey2022 »

alkonaut wrote: post #20

All of this might as well be greek to me. I use ChatGPT and copy paste code snippets. Which was bleeding edge a year or two ago, and now it feels like banging rocks together when reading these types of articles. I never had any luck integrating agents, MCP, using tools etc. Like if I'm not ready to jump on some AI-spiced up special IDE, am I then going to just be left banging rocks together? It feels like some of the…

I’m not as behind as that. But i cant figure out this loop thing. We have engineers here saying they are reviewing 100k lines of code a day, slinging 10 agents simultaneously. I just cannot figure out how that is humanly possible.

Agentic coding has come a long way though. What you are describing sounds like a trust issue more than a skill issue. Some git scumming should fix that. Maybe what I’m going through is also a trust issue.

Re: The Agentic AI Handbook: Production-Ready Patterns

#143

Post by kaycey2022 »

alkonaut wrote: post #97
embedding-shape wrote: post #26

Earlier quoted context omitted.

> I never had any luck integrating agents What exactly do you mean with "integrating agents" and what did you try? The simplest (and what I do) is not "integrating them" anywhere, but just replace the "copy-paste code + write prompt + copy output to code" with "write prompt > agent reads code > agent changes code > I review and accept/reject". Not really "integration" as much as just a workflow change.

I installed the copilot extension in my IDE, and switched on Agent mode. I don't really get how the workflow is supposed to work, but I think it's mostly due to how the tool is made. It has like some sort of "change stack" similar to git commits/staging but which keeps conflicting with anything I manually edit. Perhaps it's just this particular implementation (Copilot integration in VS) which is bad, and others are b…

Copilot in vs code is definitely trash. That aside the workflow is simple. If you are familiar with the code base then make sure to refer the files where a newb has to look if you were assigning the task to them. Tell it to ask questions. Usually framing the spec into a conversation will make things clearer in your own mind.

Re: The Agentic AI Handbook: Production-Ready Patterns

#144

Post by theshrike79 »

Bewelge wrote: post #99
CurleighBraces wrote: post #28

Earlier quoted context omitted.

Yeah if you've not used codex/agent tooling yet it's a paradigm shift in the way of working, and once you get it it's very very difficult to go back to the copy-pasta technique. There's obviously a whole heap of hype to cut through here, but there is real value to be had. For example yesterday I had a bug where my embedded device was hard crashing when I called reset. We narrowed it down to the tool we used to flash…

- We narrowed it down to the tool we used to flash the code. - I downloaded the repository, jumped into codex, explained the symptoms and it found and fixed the bug in less than ten minutes. Change the second step to: - I downloaded the repository, explained the symptoms, copied the relevant files into Claude Web and 10 minutes later it had provided me with the solution to the bug. Now I definitely see the ergonomic…

Why would you copy files anywhere?

My daily process is like this:

Claude plans (Opus 4.5)

Claude implements (Opus at work, Sonnet at home - I only have the $20 plan personally :P )

After implementation the relevant files are staged

Then I start a codex tab, tell it to review the changes in the staged files

I read through the review, if it seems valid or has critical issues ->

Clear context on Claude, give it the review and ask it to evaluate if it's valid.

Contemplate on the diff of both responses (Codex is sometimes a bit pedantic or doesn't get the wider context of things) and tell Claude what to fix

If I'm at home and Claude's quota is full, I use ampcode's free tier to implement the fix.

Re: The Agentic AI Handbook: Production-Ready Patterns

#145

Post by theshrike79 »

embedding-shape wrote: post #106
alkonaut wrote: post #97

Earlier quoted context omitted.

I installed the copilot extension in my IDE, and switched on Agent mode. I don't really get how the workflow is supposed to work, but I think it's mostly due to how the tool is made. It has like some sort of "change stack" similar to git commits/staging but which keeps conflicting with anything I manually edit. Perhaps it's just this particular implementation (Copilot integration in VS) which is bad, and others are b…

Hm, yeah maybe. I've tried Cursor once, but the entire experience was so horrible, and it was really hard to know what's going on. The workflow I have right now, is something like what I put before, and I do it with Codex and Claude Code, both work the same. Maybe try out one of those, if you're comfortable with the terminal? It basically opens up a terminal UI, can read current files, you enter a prompt, wait, then…

Instead of "asking to refactor", you might get better results by defining your standards in a ... standard way.

Give the agent tools to determine whether code is up to your standards, an executable or script it can run that checks for code style and quality. This way it won't stop the agent loop until the checks pass - saving you time.

Re: The Agentic AI Handbook: Production-Ready Patterns

#146

Post by theshrike79 »

vidarh wrote: post #96
franze wrote: post #52

Earlier quoted context omitted.

I am on the other side, I have given the complete control of my computer to Claude Code - Yolo Mode. Sudo. It just works. My servers run the same. I SSH into Claude Code there and let them do whatever work they need to do. So my 2 cents. Use Claude Code. In Yolo mode. Use it. Learn with it. Whenever I post something like this I get a lot of downvots. But well ... end of 2026 we will not use computer the way we use th…

> end of 2026 we will not use computer the way we use them now. I think it will take much longer than that for most people , but I disagree with the timeline, not where we're headed. I have a project now where the entirety of the project fall into these categories: - A small server that is geared towards making it easy to navigate the reports the agents produce. This server is 100% written by Claude Code - I have not…

Depending on your threat model, I'd lean more into building permanent tooling that's not dependent on an external AI API provider.

The more you can offload to deterministic tools (script), the easier it will be to move to local LLMs when the AI bubble bursts =)

Re: The Agentic AI Handbook: Production-Ready Patterns

#147

Post by theshrike79 »

darkwater wrote: post #77
photios wrote: post #56

Earlier quoted context omitted.

Copilot's agent mode is a disaster. Use better tools: try Claude Code or OpenCode (my favorite). It's a new ecosystem with its own (atrocious!) jargon that you need to learn. The good news is that it's not hard to do so. It's not as complex or revolutionary as everyone makes it look like. Everything boils down to techniques and frameworks of collecting context/prompt before handing it over to the model.

Yep, basically this. In the end it helps having the mental model that (almost) everything related to agents is just a way to send the upstream LLM a better and more specific context for the task you need to solve at that specific time. i.e Claude Code "skills" are simply a markdown file in a subdirectory with a specific name that translates to a `/SKILL_NAME` command in Claude and a prompt that is injected each time…

Skills can (and IMO should) also contain scripts custom made for that skill.

Like a code review skill would have scripts that read the actual code.

Re: The Agentic AI Handbook: Production-Ready Patterns

#148

Post by darkwater »

theshrike79 wrote: post #147
darkwater wrote: post #77

Earlier quoted context omitted.

Yep, basically this. In the end it helps having the mental model that (almost) everything related to agents is just a way to send the upstream LLM a better and more specific context for the task you need to solve at that specific time. i.e Claude Code "skills" are simply a markdown file in a subdirectory with a specific name that translates to a `/SKILL_NAME` command in Claude and a prompt that is injected each time…

Skills can (and IMO should) also contain scripts custom made for that skill. Like a code review skill would have scripts that read the actual code.

Thanks for the correction, TIL.

Re: The Agentic AI Handbook: Production-Ready Patterns

#149

Post by ryanhecht »

alkonaut wrote: post #100
photios wrote: post #56

Earlier quoted context omitted.

Copilot's agent mode is a disaster. Use better tools: try Claude Code or OpenCode (my favorite). It's a new ecosystem with its own (atrocious!) jargon that you need to learn. The good news is that it's not hard to do so. It's not as complex or revolutionary as everyone makes it look like. Everything boils down to techniques and frameworks of collecting context/prompt before handing it over to the model.

Sadly we have some partnership meaning it's Copilot or nothing.

Give Copilot CLI a try if you haven't in a while! The team's been working really hard to improve the harness, and we're taking as much community feedback as we can get! Let me know if you run into any problems :)

https://github.com/github/copilot-cli

Re: The Agentic AI Handbook: Production-Ready Patterns

#150

Post by ryanhecht »

JeremyNT wrote: post #128
alkonaut wrote: post #100

Earlier quoted context omitted.

Sadly we have some partnership meaning it's Copilot or nothing.

If you can use the Copilot CLI, it's highly likely you can use OpenCode with the same API key. It's worth doing a little research. The CLI tool matters. If you're not using opencode/claude you're missing out. But the latest OpenAI models are really quite good.

The Copilot CLI team has been making great strides towards improving our agentic harness! I'm curious, what have you found are the biggest shortcomings with it these days?
Post reply on HN