Diego Garcia

VELOXCRMAI-POWERED INTELLIGENCE
COMPLETED

End-to-end sales automation for car retailers. Lead capture to qualified conversation, zero manual intervention.

200 → 4

leads per day

7–15 min

response delay

24 / 7

no supervision

SCROLL

THE PROBLEM

The funnel breaks at scale

Car dealerships running Meta ad campaigns receive hundreds of leads daily. Most are not ready to buy. Sales managers were spending the majority of their time chasing cold prospects instead of closing warm ones, and real buyers were waiting days for a first response. The economics only get worse as ad spend grows.

200+

Daily leads from Meta campaigns

Most unqualified, all requiring manual triage

Hours

Wasted per manager per day

Cold calling prospects with no buying intent

Days

Average first response time

Buyers engage the first dealership that responds

SYSTEM ARCHITECTURE

Four stages. Zero gaps.

Every component is purpose-built for throughput. The pipeline runs continuously, handles concurrency without degradation, and surfaces only what managers need to act on.

END TO END PIPELINE · ZERO MANUAL INTERVENTIONCAPTUREMeta Ads APIWebhookPostgreSQLENGAGEWhatsApp APIGemini 2.57–15 min delayQUALIFY · RAGQuerypgvectorGrounded responseRedis cache layerFLAGPriority scoreManager dashboard200 → 4–5 leads
01

STAGE 01

Capture

Facebook Lead Ads webhook fires on form submission. Lead data streams directly into PostgreSQL; name, contact, vehicle interest with zero latency and zero manual input.

02

STAGE 02

Engage

Gemini 2.5 initiates a WhatsApp conversation 7 to 15 minutes after capture, randomized to avoid bot detection. Natural dialogue extracts intent, timeline, and budget.

03

STAGE 03

Qualify

Custom RAG pipeline, no framework overhead, queries 768-dimensional pgvector embeddings over company inventory, pricing, and regulations. Every response grounded. Zero hallucinations.

04

STAGE 04

Flag

Qualified leads scored and routed to the manager dashboard. From 200 daily inputs, managers see 4 to 5 prospects ready to close. Cold calling eliminated entirely.

TECHNICAL STACK

Each component earns its place

No unnecessary abstractions. Every library chosen for a specific reason, every integration justified by throughput or precision.

Conversational AI

Gemini 2.5

Drives all WhatsApp conversations. Context-aware, grounded through RAG, never hallucinates.

Vector store

PostgreSQL + pgvector

768-dimensional embeddings over company knowledge. Semantic search in milliseconds.

Caching layer

Redis

Conversation state and hot queries cached. Sub-second response times under any load.

Delivery channel

WhatsApp Business API

Native WhatsApp integration with randomized 7 to 15 minute delays for human-paced behavior.

Capture

Meta Leads API

Webhook-driven real-time lead ingestion from Facebook and Instagram ad campaigns.

Nurture sequences

Resend

Drip email campaigns for leads not ready to convert. Keeps prospects warm until buying intent peaks.

WHAT IT TAUGHT ME

Building the RAG pipeline without a framework forced a deeper understanding of how retrieval actually works, what the embeddings represent, where semantic search breaks down, and why chunking strategy matters more than model choice.

The 7 to 15 minute delay was not a technical decision. It was the most important product decision in the whole system. A response in seconds gets ignored. A response that feels human gets a conversation.