In development · live demoAI Apps2026
An embeddable AI support agent that answers from your help-center docs, escalates to humans, and writes ticket summaries.
Overview
The brief.
An embeddable AI support agent that answers from your help-center docs, escalates to humans, and writes ticket summaries.
Receipts
- What works today
- Embeddable widget that answers from the connected help-centre content, with citations.
- Low-confidence or high-risk drafts go to a human approval queue instead of the customer.
- Golden-question evals that store pass/fail evidence per run; audit log on every AI decision.
- What I owned
- product, RAG pipeline, approval workflow, eval runner, widget.
- Evidence
- SourceTry it in the AI Lab
- Known limits
- No live customer traffic yet, so there are no deflection or satisfaction numbers to report.
- Multi-user RLS is tested locally; live multi-tenant proof still needs a clean project.
- Production boundary
Architecture
User question
in-app chat
Retrieval
help-center docs
Grounded answer
with confidence
Escalate
human handoff if unsure
