Hacker News: gburgett

New comment by gburgett in "Components of a Coding Agent"

gburgett — Sun, 05 Apr 2026 00:41:41 +0000

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...

New comment by gburgett in "Components of a Coding Agent"

gburgett — Sun, 05 Apr 2026 00:07:37 +0000

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?

Pushing Claude Code Further with Spec Driven Development

gburgett — Fri, 03 Apr 2026 20:35:20 +0000

Article URL: http://gordonburgett.net/posts/2026/03_spec-driven-development/

Comments URL: https://news.ycombinator.com/item?id=47631904

Points: 3

# Comments: 0

New comment by gburgett in "Qwen3.6-Plus: Towards real world agents"

gburgett — Thu, 02 Apr 2026 18:01:09 +0000

Looking forward to when this gets on Bedrock. I built an app with a niche AI agent and to this point only Sonnet is really good enough for our use case, but its expensive!

New comment by gburgett in "LinkedIn is searching your browser extensions"

gburgett — Thu, 02 Apr 2026 13:45:04 +0000

The “how it works” page suggests it only works on chrome based browsers. Anyone able to determine if firefox or safari are affected too?

New comment by gburgett in "Do your own writing"

gburgett — Tue, 31 Mar 2026 02:29:51 +0000

Im in a slight disagreement with our CTO about the value of writing acceptance criteria yourself. When I write my own acceptance criteria its a useful tool forcing me to think through how the system ought to work. Definitely in agreement that writing is an important tool for clarifying thinking, not just generating context.

New comment by gburgett in "The ladder is missing rungs – Engineering Progression When AI Ate the Middle"

gburgett — Tue, 31 Mar 2026 01:50:57 +0000

We hired on a software engineer fresh out of college this January, and we are a very claude heavy shop. We have noticed and have explained to him that we still have to do the real engineering work: requirements decomposition, interface design, verification and integration. Claude is helpful but he is still responsible for his output. He’s been doing well so far! Theres still plenty of things for him to bang his head on and grow.

New comment by gburgett in "Judge blocks Pentagon effort to 'punish' Anthropic with supply chain risk label"

gburgett — Fri, 27 Mar 2026 02:33:25 +0000

We are certainly moving that direction (small defense sub)