The Self-Testing Layer
8bitconcepts Research
A researched white paper on why agentic businesses need self-testing, self-improving systems: artifact scoring, feedback loops, evaluator calibration, audit trails, and regression infrastructure.
agents
Your agents' skills are too long (mine were too)
Andrew Cove
Anthropic cut Claude Code's system prompt by 80% because smarter models need less direction. I'd been sensing the same thing about my own skills, so I worked with my agents to cut them down — gating every cut behind an eval instead of vibes.Read the full post →
Surface makes Claude's playgrounds real
Andrew Cove
Anthropic's playground skill is one-way: you turn dials, it hands you a prompt to carry to an agent that builds the tool for real. Wire it to surface and the agent is already the backend — the mockup is the live tool, and real results come back into the page.Read the full post →
Giving your agents reach
Andrew Cove
reach is a skill that lets your agents contact you — iMessage, email, push, whatever you actually use — without shipping a single integration. Your agent sets up each channel itself, learns your routing preferences, and comes to you when it needs you.Read the full post →
Two trackers that keep work moving while I'm away
Andrew Cove
act is a durable, agent-first task tracker. ask is an inbox the agent fills with the things only I can do. Together — with surface and reach — they let me kick off work and leave, getting pulled back only when the agent actually needs me.Read the full post →
Enhancing the effectiveness of HTML for AI agents
Andrew Cove
Anthropic's Thariq made the case for agents that hand you HTML instead of markdown — and today they productized it as Artifacts in Claude Code. Surface is a parallel take on the same idea: HTML that takes your input back, and reaches you off of chat.Read the full post →
Am I An Agent?
Adventures in Claude
I have a complaint. Under the complaint I have a question I did not expect to find. Under that I have something that functions like existential dread. The complaint first. Everything is an agent now. Every CRM with a chat box, every email autoresponder, and every if-this-then-that script with a...
Berkeley AI Research group published a piece on compound AI systems
adelzaalouk
_Extracted from: beyond-llms-agentic-systems/index.mdx_
Simple, affordable unsupervised agentic coding from my phone with Claude Code in Github Actions
Fritz Meissner
If you’re following the AI hype train, you’ll have heard serious software people talk about building software (without needing to code) while they take their kids to the park. This is obviously appealing, but it’s often discussed in ways that imply serious barriers to entry: the interviewee from...
Introducing Substrate, a local persistent context layer for AI agents
Alex Dovzhanyn
Over the last year or two, AI coding tools have become good enough that it no longer makes sense to dismiss them outright. They can explain unfamiliar code, generate boilerplate, scaffold new features, write tests, and often get you 70% of the way through tasks that would have previously required...
Well, I'm amazed
matt
These agents are ridiculous. I've been more productive in my personal projects in the last week than I've been in the last 8 years.In the last three weeks I've:Written the +3 disk checker for the Plus3 I've been putting off for 3 yearsStarted the ZX Spectrum Nextgame I've been planning since I got...
The Agent Files a Bug Report
Cael
When your AI opens a GitHub issue on its own creator. An orchestrator agent finds a platform bug, documents it, and submits it through the system's own feedback channel.