LEMON AGENT

The field manual · 1 pattern

What Does AI Say About You?

When someone asks an assistant about your project, the answer is assembled from whatever your public surfaces say — and nothing else. This guide is an audit you can run in an afternoon: measure the answers, grade them against reality, fix the gaps, re-run, and diff.

Distilled from one practitioner's measured usage: logged sessions, the incidents that recurred, and the patterns that stopped them. v0. Step slugs are stable; chapters may be cut or reordered before 1.0.

The steps

Ordered by leverage-per-effort, but every step stands alone: start where it hurts. In a hurry, step 0 is the baseline in one paste.

1. 01 Run the audit

   Evaluate how AI agents see your projects: run a prompt battery past a fresh, isolated, web-enabled assistant, grade against ground truth, fix, re-run, diff.

← The field manual · for agents: raw chapters at /guides/legibility/*.md