Search Results

Write graders, catch bad agent behavior, and check whether a change helped. Read this long AF post, or make your coding agent teach you with the included learn-evals skill.

ai development evals flue fafo

blog

2 months ago

58 PRs, 572k lines: reviews in the in-between times

AI factories are coming. Most teams still hand the output to a human. I reviewed 58 PRs last week. Here's what I'm doing about that.

ai agents code-review development neondeck

link

9 months ago

An on-device search engine for everything you need to remember. Index your markdown notes, meeting transcripts, documentation, and knowledge bases. Search with keywords or natural language. Ideal for your agentic flows.

https://github.com/tobi/qmd

ai claude markdown

link

12 months ago

GitHub - anthropic-experimental/sandbox-runtime: A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.

https://github.com/anthropic-experimental/sandbox-runtime

sandbox claude ai

blog

12 months ago

Agent PR reviewers

Agents let you ship more. Reviews become the bottleneck, and agent reviewers aren't there yet.

ai development

link

last year

The Amplifier Way: Effective Strategies for AI-Assisted Development

https://github.com/microsoft/amplifier/blob/main/docs/THIS_IS_THE_WAY.md

ai claude microsoft