roadmap: add no-score + no-measurement guardrails (agent panel 08-16)
This commit is contained in:
@@ -63,7 +63,9 @@ per-client margin.
|
|||||||
source. Any proposed artifact answers yes/no: does it render verified truth,
|
source. Any proposed artifact answers yes/no: does it render verified truth,
|
||||||
or create a second truth?
|
or create a second truth?
|
||||||
3. **No second source, no new surface without a client who asked for it.**
|
3. **No second source, no new surface without a client who asked for it.**
|
||||||
4. DR-001 (website scope) and DR-002 (cadence) stand unchanged unless explicitly superseded.
|
4. **No GEO score, no GEO promise.** We sell the *outcome* — facts accurate and consistent everywhere the systems that recommend a business read them. We never promise an "AI visibility score", a ranking movement, or a recommendation share; a score we cannot compute or control is a liability, not a feature.
|
||||||
|
5. **No GEO measurement build.** No AI-answer scraping, prompt-test harnesses, or visibility dashboards until a phase gate fires — and then only against a real, sent trust receipt.
|
||||||
|
6. DR-001 (website scope) and DR-002 (cadence) stand unchanged unless explicitly superseded.
|
||||||
|
|
||||||
## Non-goals (until Phase 1 trigger fires)
|
## Non-goals (until Phase 1 trigger fires)
|
||||||
- No llms.txt or website deliverable beyond the DR-001 one-time Lovable fix.
|
- No llms.txt or website deliverable beyond the DR-001 one-time Lovable fix.
|
||||||
|
|||||||
Reference in New Issue
Block a user