AI anteroom for WhatsApp
WhatsApp that knows when to answer, and when to hand off.
Antesala reads every inbound message, replies only from your approved knowledge base, and escalates to a person, with the full thread, the moment no source supports an answer. Each decision is numbered, dated, and traceable.
Built for small and mid-size teams. Bilingual, Spanish and English.
What makes it trustworthy
Four guarantees, enforced by the architecture, not by a clever prompt.
- F.01
Grounded answers only
Every reply cites a document from your knowledge base. If no source supports the answer, the message escalates. It does not guess.
- F.02
Immutable escalation register
Every conversation that reaches a human is numbered, dated, and stored permanently per tenant. Nothing is overwritten.
- F.03
Zero hallucination by design
The model can only answer from the passages you ingest. No ingested source, no answer: by construction, not by prompt.
- F.04
Multi-tenant from day one
Each client gets a separate knowledge base, prompt set, WhatsApp number, and escalation queue. Isolated end to end.
The escalation register
Every hand-off becomes a permanent, numbered record. Auditable per tenant, never overwritten.
| Ref | Date | Tenant | Status | Note |
|---|---|---|---|---|
| R.0001 | 2026-02-04 | ferreteria-cr | escalated | Bulk discount, no source |
| R.0002 | 2026-02-04 | clinica-este | answered | Hours · hours.pdf p.2 |
| R.0003 | 2026-02-05 | ferreteria-cr | answered | Returns · policy.pdf p.1 |
| R.0004 | 2026-02-05 | estudio-legal | escalated | Case status, needs human |
Solid work behind the chat
Retrieval, orchestration, and hand-off are wired from proven parts, no black boxes.
- WhatsApp Cloud API
- Anthropic Claude
- Voyage AI
- pgvector
- Chatwoot
- n8n
- Next.js
- FastAPI
Put Antesala in front of your WhatsApp inbox.
Ingest your documents, connect a number, and let it answer what it can prove, escalate the rest.