diff --git a/docs/agents/audit-playbook-v1.md b/docs/agents/audit-playbook-v1.md index bef7840..19c9134 100644 --- a/docs/agents/audit-playbook-v1.md +++ b/docs/agents/audit-playbook-v1.md @@ -9,6 +9,11 @@ - `docs/architecture/path-to-poc-sequencing.md` - Templates in `docs/templates/` +**GBP-specific tooling:** +- Intake template: `docs/templates/gbp-snapshot-intake.md` +- Leonard execution card (minimal reasoning): `docs/agents/leonard-gbp-execution-card.md` +- HTML form (fill → copy/paste to Leonard): `tools/gbp-snapshot-form.html` + --- ## Non-Negotiables @@ -28,7 +33,7 @@ **Goal:** Record what exists, where it lives, and verification status. Nothing else. ### Required sources (minimum) -- Google Business Profile (or clear statement that it is missing/unclear) +- Google Business Profile / GBP (or clear statement that it is missing/unclear) - Website - Primary social channel(s) - Booking / scheduling system (or explicit “not visible”) @@ -47,6 +52,7 @@ - Do not claim “owner access” unless it is confirmed in the current process. - Missing sources are documented as gaps, not ignored. - Technical findings (404s, schema, NAP conflicts, etc.) require a dated snapshot. Old findings must be marked for re-verification. +- **GBP without owner access:** use human snapshot via `tools/gbp-snapshot-form.html` (or markdown intake). Leonard maps via the execution card only — no free-form GBP reasoning. ### Exit criteria (human must confirm) - [ ] All accessible sources recorded @@ -79,6 +85,7 @@ - Competitor comparisons are secondary context only, never the primary claim. - If data is stale, say so in Data Recency or Notes. - No recommendations, fixes, or next actions. +- **GBP-related threats:** only create/update via execution-card trigger rules R1–R3 when ingesting a GBP snapshot. ### Severity guidance (use conservatively) - **Critical:** Directly blocks or severely impairs local discovery / conversion and evidence is clear. @@ -105,6 +112,12 @@ When unsure, choose the lower severity. 5. Surface blockers and stale data explicitly. 6. Stop at the human review gate. Do not self-lock. +### GBP cold-audit pattern +1. Human fills `tools/gbp-snapshot-form.html` (or markdown intake). +2. Human pastes output to Leonard with: follow `docs/agents/leonard-gbp-execution-card.md` exactly. +3. Leonard maps fields and fires only R1–R3. +4. Human reviews; Director may score against the rubric below. + --- ## Training / Evaluation Rubric (simple) @@ -128,7 +141,7 @@ Score a Leonard (or any agent) run 0–2 on each: - Client: Overcome Fitness - Files: `docs/clients/overcome-fitness/data-inventory-v1.md` and `threat-register-v1.md` -- Status: Draft (Benchmark) — not yet Locked; freshness gaps remain +- Status: Draft (Benchmark) — not yet Locked; GBP completeness still open Future Leonard runs should be compared against this package and scored with the rubric above.