AI CRM
A voice agent and assistant for a US auto-dealership group. Callers ask for repair status, parts-delivery ETAs, vehicle availability and part compatibility — and book service appointments. The hard part here is not the conversation, it is retrieval: pulling the exact answer out of the dealer’s live systems — inventory, parts catalog, service schedule — from whatever a caller says out loud, inside a live-call latency budget.
- 01 A call → the exact answer from the dealer’s live systems, by voice.
- 02 Two surfaces on one retrieval engine: chat and phone.
- 03 Answers arrive at the pace of a live conversation.
Pull the exact answer from a live database, by voice.
Callers ask where their car is in service, when a part arrives, whether a part exists and fits, and how to book service. The answer lives in the dealer’s DMS — inventory, parts catalog, service schedule — and changes by the hour.
The phrasing is live and ambiguous: people mix up models, name a part their own way, dictate addresses with errors. Exact-string search returns noise, and voice adds a hard latency budget on top.
- The answer must come from the dealer’s live database, not a static FAQ.
- Queries are ambiguous: model, part, address — all spoken and approximate.
- Voice does not forgive latency — the answer has to come back almost instantly.
Two surfaces over one retrieval engine.
One RAG engine over the dealer’s DMS serves two surfaces: async order and parts queries, and live voice over telephony. On top sits an agent that runs the dialog, calls tools, and writes back to the CRM.
- 01
Understand the query
A custom intent router and dialog state work out what the caller wants: status, availability, compatibility or a booking.
- 02
Retrieve the exact fact
Hybrid search, re-ranking and HyDE over inventory, parts and service slots. A deterministic pre-filter normalizes SKUs, matches the customer and resolves the address.
- 03
Answer in budget, by voice
Streaming STT, model routing with fallback to a cheaper model, and prompt caching on the static prefix — to stay inside the live-call latency budget.
- 04
Coach the rep
A real-time call-coach feeds suggestions to the sales rep mid-call.
- 05
Write back and prioritize
The agent writes the result back to the CRM, and a lead-ranking model prioritizes who to call first.
Retrieval that holds a live call.
Python/Django backend. Dialog on OpenAI, streaming STT on Deepgram, telephony on Twilio, speech synthesis under a tight latency budget. Model routing with fallback: when the top model is overkill, a cheaper one answers.
RAG over the dealer’s DMS: hybrid search with re-ranking and HyDE, an agentic loop with tool definitions and structured outputs, and a deterministic pre-filter — SKU normalization, customer matching, address resolution. Both surfaces are covered by eval sets, with prompt caching on the static prefix. Near the end we built our own lead review-and-scoring panel: an LLM council of several runs, a deterministic formula with per-factor reasons, and bulk rescoring across the base.
Hybrid search + re-ranking + HyDE over inventory, parts and service.
Deterministic pre-filter: SKU normalization, customer matching, address resolution.
Streaming STT (Deepgram) and telephony (Twilio) inside a latency budget.
Model routing with fallback and prompt caching on the static prefix.
Agentic loop: tool definitions, structured outputs, CRM write-back.
Eval sets on both surfaces — quality is measured, not promised.
What changed
Calls close without an operator
Around a hundred calls a day in production: repair status, availability, compatibility, service booking — the agent answers by voice on its own.
Answers from the live database, not a FAQ
Hybrid search and the pre-filter pull the exact fact from the DMS by live phrasing, not exact string match.
Quality under control
Eval sets on both surfaces catch regressions before release — the model and prompts can change without fear.
Need an agent that pulls the exact answer from your live database?
We help teams put retrieval and voice into production: hybrid search, ranking, an agentic flow, and evals that hold quality.