---
title: "Project Acme — Architecture"
url: https://mdfy.app/ycd140D0
updated: 2026-05-10T15:36:24.394Z
source: "mdfy.app"
---
# Project Acme — Architecture

> _Recreated outline. Original was lost to the SAMPLE_WELCOME race._

## Overview

Acme is a post-call sales intelligence layer. Components (high level):

```
audio in → transcription → extraction → CRM write
            (Whisper)       (Claude)     (Salesforce / HubSpot)
```

## Components

### Ingestion
- Cloud upload endpoint (POST /v1/calls)
- Webhook from Zoom / Gong / Chorus
- File-store: object storage (raw audio, retained 30d)

### Transcription
- Provider: Whisper (self-hosted) or Deepgram (managed)
- Output: speaker-diarised transcript JSON

### Extraction
- LLM: Claude with structured output (JSON schema)
- Inputs: transcript, account context, recent CRM state
- Outputs: follow_ups[], decisions[], next_steps[]

### CRM bridge
- OAuth tokens per tenant (Salesforce, HubSpot)
- Idempotent write with external ID = call_id
- Approval queue: nothing writes without human OK in v1

## Data model

- `calls(id, tenant_id, audio_url, status, transcript_id, ...)`
- `extractions(id, call_id, kind, payload, status, approver_id)`
- `integrations(tenant_id, provider, refresh_token, ...)`

## Open questions

- Streaming vs batch transcription
- Multi-tenant inference vs per-tenant model pinning
- Retention: raw audio vs transcript vs extracted-only