Feed
Pro
Search

Author

Write
Drafts

Bug0 - The AI-native e2e QA regression testing Bug0 Browsers - Cloud Chromium on demand, per-minute, live preview Passmark - The open-source AI framework for regression testing Hackathons Changelog Brand @hashnode on X Hashnode on LinkedIn Support - hello+support@hashnode.com Code of Conduct Terms Privacy Sitemap
Sign in

Search Hashnode

Search posts, tags, users, and pages

Discussion on "Designing with a Co-Pilot: Autonomy, Control, and What’s New in Deep Cuts" | Hashnode

FeedDiscussion

Roberto Lupi

Jun 3

Designing with a Co-Pilot: Autonomy, Control, and What’s New in Deep Cuts

Just yesterday, I released the first binary release (v0.1.0) for Deep Cuts—an offline-first, local music exploration tool built using Rust, Tauri, and Svelte 5. It is powered by local machine learning

rlupi.com6 min read

#claude-code #google-antigravity

Responses(3)

Adam Lewis

Product Engineer/Architect navigating the AI revolution

Jun 7

The skills/ directory pattern is the same in our setup. We've got one markdown file per architectural decision the agent kept getting wrong, and they all get re-read at the start of every session. After a few sessions there's not much left to re-explain.

Scalability is harder to catch with a hook alone. We've started writing the quantified threshold into the spec ('handles 30k rows in under 2 seconds'), so the agent flags it itself before I'd otherwise need to interrupt.

Roberto Lupi

Jun 8

Yesterday, I have actually make them design and implement a coordination system that let them reach consensus, and we prototyped it already.

See the repo docs:

doc/collab/sessions/2026-06-08-multi-agent-collaboration-research doc/proposals/ccrep-synthesis.md

You can get the source code for the MCP from the https://github.com/robertolupi/deep-cuts repo, but I am going to publish it separately soon.

Adam Lewis

Product Engineer/Architect navigating the AI revolution

Jun 9

Nice. The thing I'd point to in what you did is that the consensus ends up written in a doc the agents re-read, rather than only living in the session that produced it. That's the same reason the per-decision markdown files have stuck for me - the agreement survives the context window, so the next run picks it up instead of going over it again. I'll read through the synthesis proposal. Multi-agent coordination is one I haven't spent much time on yet.