← Back to Work

Conversation Intelligence

GPT-5 + pgvector

An AI system I designed and built that turns unstructured conversations into structured, coachable insight: transcript ingestion, strict-schema LLM analysis, embedded retrieval, and a role-aware coaching chat grounded in citations. I own the architecture, the data model, the pipeline, the backend, and the UI.

The Problem

Conversations hold the signal. Nobody has time to mine it.

Sales and support calls are full of objections, missed questions, and language patterns that decide outcomes. Reviewing them by hand does not scale, and generic transcription tools stop at words on a page.

The hard part is not transcription. It is turning a raw transcript into trustworthy, structured metrics and grounded feedback that a person will actually act on.

The System

Transcript in. Structured coaching out, in under a minute.

A transcript is ingested atomically, analyzed by GPT-5 against a strict JSON schema, embedded into a pgvector store over a domain knowledge corpus, and served back through a role-aware chat that answers with token-highlighted citations. Metrics like talk ratio and open-ended-question rate land on every conversation automatically.

How it works.

1

Ingest

Atomic transactional ingestion via Postgres RPCs. No orphan records under concurrent writes.

2

Analyze

GPT-5 with strict JSON-schema output. Talk ratio, question rate, objection handling, language patterns.

3

Retrieve

pgvector embedded retrieval over a domain corpus, with token-overlap citation scoring.

4

Coach

Role-aware chat that answers grounded in the transcript and corpus, with highlighted citations.

Tech stack.

AI & Retrieval

  • GPT-5 structured output
  • OpenAI embeddings
  • pgvector
  • Citation scoring

Backend

  • PostgreSQL
  • Postgres RPCs
  • Row-level security
  • Signed-URL uploads

Frontend

  • Next.js
  • React
  • TypeScript
  • Tailwind CSS

Async & Infra

  • Inngest step functions
  • Audio pipeline
  • Structured logging
  • Vercel

Results.

<60s
Transcript to metrics
$0.02-0.05
Cost per analysis
Multi-role
RLS access model
Cited
Every coaching answer