Launch evidence
Proof before expansion
Dchat packages launch review around manual evidence: regression scenarios, handoff transcripts, channel continuity checks, rollback references, and owner approval before automation widens.
Manual regression packet
Review stale knowledge, sensitive actions, identity continuity, failed tool runs, and replay candidates before changing prompts, models, or channels.
- Scenario matrix
- Replay candidates
- Reviewer notes
Handoff readiness
Show that visitor transcript, AI reply, handoff summary, and first human response are visible before citing fallback readiness.
- Transcript
- Handoff summary
- Human response
Expansion boundaries
Separate website chat and configured intake evidence from unshipped ChatGPT, Gemini, voice, mobile, and universal messaging surfaces.
- Current surface
- Planned surface
- Missing proof
Expansion waits for evidence, rollback, and owner approval.
| Capability | Status | Detail |
|---|---|---|
| AI distribution readiness | Available | Use launch packets to collect prompt, model, knowledge, tool, channel, routing, and audit-event references. |
| Manual regression run packet | Available | Package scenario count, replay transcript ids, failed scenario count, reviewer notes, and rollback reference. |
| Human handoff readiness | Available | Review handoff transcripts, stale queue rows, and first-human-response evidence before widening AI fallback. |
| Channel continuity review | Configured | Tie planned assistant, voice, messaging, and mobile surfaces to continuity checks before citing cross-surface readiness. |
| Automated eval harness | Available | Save real customer questions and re-run them through the live grounded answer path after knowledge or prompt changes; pass/fail results persist per question. Not automated prompt rollback, provider-certified QA, or guaranteed outcomes. |
| External agent coverage | Not claimed | Do not claim live ChatGPT, Gemini, voice, mobile, marketplace, or universal messaging coverage from planning packets alone. |
This is the evidence layer broader AI-agent suites often blur: Dchat should expand only after review artifacts and rollback ownership are visible.