12 Factor Agent Design Review

Design and evidence-review LLM systems with HumanLayer's 12-Factor Agents. Use whenever planning or auditing an LLM workflow, agent loop, tool-calling app, framework migration, human approval, or unreliable agent—even without naming the method. Covers LLM/code boundaries, prompts/context, typed tools, durable state, control flow, pause/resume, retries, and replay. Not for Twelve-Factor App deployment, prompt-only edits, model comparisons, generic code review, security-only work, or scaffolding.

daviddwlee84 Updated 1 repo stars

File contents

daviddwlee84/agent-skills commit 9cb5e27f41

Frequently asked questions

npx get-skill add daviddwlee84/12-factor-agent-design-review