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

Components of a Coding Agent

magazine.sebastianraschka.com

Post reply on HN
Print view View original

71–80 of 120 posts

Re: Components of a Coding Agent

#71

Post by gburgett »

beshrkayali wrote: post #14

> long contexts are still expensive and can also introduce additional noise (if there is a lot of irrelevant info) I think spec-driven generation is the antithesis of chat-style coding for this reason. With tools like Claude Code, you are the one tracking what was already built, what interfaces exist, and why something was generated a certain way. I built Ossature[1] around the opposite model. You write specs describ…

Totally agreed! Ive had good success using claude code with Cucumber, where I start with the spec and have claude iterate on the code. How does ossature compare to that approach?

Re: Components of a Coding Agent

#74

Post by gburgett »

Loved this writeup. I have built an agent for a specific niche use case for my clients (not a coding agent) but the principles are similar. ive only implemented 1-4 so far. Going to work on long term memory next, but I worry about prompt injection issues when allowing the LLM to write its own notes.

Since my agent works over email, the core agent loop only processes one message then hits the send_reply tool to craft a response. Then the next incoming email starts the loop again from scratch, only injecting the actual replies sent between user and agent. This naturally prunes the context preventing the long context window problem.

I also had a challenge deciding what context needs injecting into the initial prompt vs what to put into tools. Its a tradeoff between context bloat and cost of tool lookups which can get expensive paying per token. Theres also caching to consider here.

Full writeup is here if anyone is interested: https://www.healthsharetech.com/blog/building-alice-an-empow...

Re: Components of a Coding Agent

#76

Post by xrd »

beshrkayali wrote: post #14

> long contexts are still expensive and can also introduce additional noise (if there is a lot of irrelevant info) I think spec-driven generation is the antithesis of chat-style coding for this reason. With tools like Claude Code, you are the one tracking what was already built, what interfaces exist, and why something was generated a certain way. I built Ossature[1] around the opposite model. You write specs describ…

This is really fascinating and lines up with my way of development.

I notice you support ollama. Have you found it effective with any local models? Gemma 4?

I'm definitely going to play with this.

Re: Components of a Coding Agent

#78

Post by alfiedotwtf »

beshrkayali wrote: post #14

> long contexts are still expensive and can also introduce additional noise (if there is a lot of irrelevant info) I think spec-driven generation is the antithesis of chat-style coding for this reason. With tools like Claude Code, you are the one tracking what was already built, what interfaces exist, and why something was generated a certain way. I built Ossature[1] around the opposite model. You write specs describ…

How does this differ from Superpowers?

Re: Components of a Coding Agent

#79

Post by alfiedotwtf »

armcat wrote: post #3

I still find it incredible at the power that was unleashed by surrounding an LLM with a simple state machine, and giving it access to bash

I found replacing bash with python to be more useful… that way, it can craft whatever it desires without having to pipe a billion pieces of gum together
Post reply on HN