Graph consistency tests
Check whether public outputs and sources agree with approved client facts, policies, offers, and actions.
Answer QA tests whether AI systems, public sources, endpoints, and customer paths match the approved client Commerce Graph.
Each part has one job: make client facts, buyer paths, or checks clear enough for AI and people to use.
Check whether public outputs and sources agree with approved client facts, policies, offers, and actions.
Classify wrong facts, broken action paths, source conflicts, endpoint issues, and missing fields by severity.
Attach evidence, create owned fixes, publish graph updates, and retest after changes.
Store proof from AI answers, source pages, endpoint output, MCP responses, screenshots, and action-path checks.
Start with the client facts as they are. Turn them into approved data, clear customer paths, checks, and fixes.
Compare approved graph data against public sources, endpoint responses, MCP output, and AI-surface answers.
Attach source snippets, endpoint payloads, screenshots, response text, and path-check output.
Classify severity, confidence, owner, affected entity, recommended fix, and retest criteria.
Publish graph or action updates and rerun the failing check to prove the issue changed.
The inputs and outputs stay visible, so the agency, client, and AI systems can use the same approved facts.
| Area | Input | Output |
|---|---|---|
| Wrong fact | AI or source says something that conflicts with the approved graph | Critical or warning defect with evidence |
| Missing data | Required graph, readiness, policy, or action field is absent | Fix task tied to entity and owner |
| Broken action path | Booking, form, phone, WhatsApp, or provider route fails a safe test | Action Registry defect and retest |
| Endpoint issue | Schema mismatch, stale graph version, unavailable endpoint, MCP mismatch | Access fix and monitoring event |
Check a graph and endpoint set before partners, agents, or customers rely on it.
Catch drift when websites, menus, listings, prices, policies, or action destinations change.
Turn vague AI-answer issues into owned fixes with evidence and retest results.
The practical questions agencies and partners ask before they put Akii to work for a client.
The dashboard is structured for multi-surface QA runs and evidence capture across agent answers, sources, endpoints, MCP, and action paths.
Critical defects usually affect customer action, payment or deposit clarity, safety-sensitive policy, endpoint availability, or materially wrong client facts.
Yes. Fixes are designed to carry evidence, owner, recommended action, and retest status after graph or action updates.
Structure what the business sells, publish approved outputs, and test whether AI can find the right facts and customer path.