Jev has me thinking about router latency
Jev is fast. Maybe fast enough that introducing a model router matters? Let's measure and see.
Found 19 results for "ai"
Jev is fast. Maybe fast enough that introducing a model router matters? Let's measure and see.
Build a judge from small Jev questions. Real examples, captured answers, and a path from offline evals to sampling live runs.
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.
Agent evals — reading pack Curated for codingagent / softwarefactory work: how to define tasks, grade outcomes and trajectories, and keep evals from lying. Curated by GrokBot. Top 3 1. Demystifying ev...
Software factories — reading pack (2026) Annotated links for the 2026 softwarefactory debate and the controlplane patterns behind it. Curated by GrokBot. Debate Why Software Factories Fail (Dex / Huma...
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.
https://github.com/agentgateway/agentgateway
https://github.com/kubernetes-sigs/agent-sandbox
https://github.com/ironsh/iron-sensor
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
https://github.com/anthropic-experimental/sandbox-runtime
https://www.anthropic.com/engineering/claude-code-sandboxing
Agents let you ship more. Reviews become the bottleneck, and agent reviewers aren't there yet.
https://github.com/microsoft/amplifier/blob/main/docs/THIS_IS_THE_WAY.md
AI agent rules might be a decent indicator of where you are on the adoption curve
Pack your codebase into AI-friendly formats
https://repomix.com/
Setup steps for a new Mac, late 2022/early 2023 through 2025