sid_ships

Re:Show HN: Evaluate and improve your agent steering on Wednesday October 14, 2026 @04:55AM (#50084483)

We kept the 2 tools separate as we wanted to allow users to use either independently. If someone just wants to use session intelligence in their product, they can integrate it in their workflow/prodiuct with UI optional

Fair feedback on the agent desk having a prebuilt download as it would make it easier to try while preserving separation

Show HN: Evaluate and improve your agent steering

Posted by sid_ships on Tuesday October 13, 2026 @10:58PM
from the show-hn dept.

Hi HN, excited to be open sourcing two tools that we have built over past few months which helps to understand your own work with AI coding agentsAgent Desk is a local macOS app which allows you to browse your sessions across all top coding agents - Claude code, cursor, codex, github copilot, Kiro, Antigravity. You can find sessions by your projects, revisit those conversations, understand and...

( Read More... | 3 comments | 2 points | on HN )

Re:Why human syntax breaks LLMs (and how to fix agentic coding) on Wednesday September 09, 2026 @07:36AM (#49624769)

Interesting benchmarks. One thing I'd love to see separated out: how much of the gap is syntax vs. how much is the model just having seen far less of the "fixed" form in training. A simpler grammar with zero corpus behind it could easily perform worse in practice.

Re:Launch HN: Hyper (YC P26) – Company brain to power agentic development on Thursday June 25, 2026 @12:55AM (#48669080)

Congrats on the launch. The thing I keep wondering with "company brain" products is the staleness problem — context that's right on Monday is quietly wrong by Friday, and nobody notices until a decision gets made on it.

Re:Ask HN: What agentic directory structure do you use? on Monday June 22, 2026 @05:18AM (#48627779)

The missing primitive in most setups I've seen: per-task scope contracts. A CLAUDE.md covers what the codebase is, but a per-task declaration of what must not change and where the agent stops is a separate thing. I've started putting those as a header in the task description itself, separate from persistent context.