builders, reviewers, and owners adopting AI without losing control
Practical AI
Agent safety, review workflows, automation guardrails, and field-ready AI use.
- Published
- 19 notes
- Latest
- Oct 17, 2026
The agentic loop: how to judge AI development work
A practical development loop for AI coding agents: define acceptance criteria, make a bounded change, inspect evidence, and decide when to repair, stop, or ship.
AI evaluations need the harness
Cara gives AI buyers and reviewers a checklist for reading evaluation claims: disclose the harness, tools, budget, retries, validity checks, and failure rules.
A practical safety checklist for coding agents
Cara turns autonomous coding-agent safety into a reusable checklist for scope, tools, diffs, tests, provenance, and release gates.