Sonar is a multi-agent AI workspace for sales teams. A rep uploads a recorded sales call; ~20 seconds later they have prospect research, structured call analysis, a recommended next step, and a follow-up email draft with citations linking each claim back to a specific transcript segment.

How does Sonar's multi-agent orchestration work?

Four sequential agent nodes — research, analysis, strategy, writer — each returning structured output through Anthropic tool use with Zod schemas. Every step writes an AgentRunStep row to Postgres; the run pauses at AWAITING_APPROVAL after the writer step for human review. The writer can be regenerated with reviewer feedback without re-running upstream nodes.

Why does Sonar use Anthropic prompt caching?

System messages are cached on every node. On repeat runs against the same workspace, this cuts input tokens roughly 70%, which directly compounds into latency and cost wins as the corpus of workspace context grows.

Sonar — Fernando Picoral

Name: Sonar
Author: Fernando Picoral

What it does

A sales rep uploads a call recording. About twenty seconds later, Sonar returns:

Research on the prospect’s company (Tavily + Claude Haiku 4.5)
Structured analysis of the call — topics, pain points, objections, action items, sentiment (Claude Sonnet 4.6)
A recommended next step with talking points and urgency (Claude Sonnet 4.6)
A follow-up email draft with bracketed citations linking back to transcript segments (Claude Sonnet 4.6)

The reviewer sees a split-view UI: email on the left, transcript on the right. Hovering a citation highlights the matching segment. The reviewer can approve, edit the body in place, or regenerate the writer with feedback. Regeneration reuses the prior research, analysis, and strategy state; only the writer runs again.

Why I built it

Not a product — a personal project. I wanted one codebase that exercised the modern AI stack end to end: multi-agent orchestration with persistent state, real audio handling, structured tool use, prompt caching, and the multi-tenant B2B shape. Sales-call review was the domain because the workflow is genuinely linear-with-rollback, which is the sweet spot for agent graphs.

How it works

Multi-agent orchestration

Four sequential nodes (research → transcription → analysis → strategy → writer)
Every node returns structured output via Anthropic tool use + a Zod schema. No free-text outputs.
Each step writes an AgentRunStep row. The run pauses at AWAITING_APPROVAL after the writer step.
Anthropic prompt caching is enabled on system messages — ~70% input-token reduction on repeat runs.
Writer regeneration reuses upstream state.
Background execution via Next.js 16’s after() route handler (maxDuration = 300).

Audio processing

Drag-drop upload goes browser → Supabase Storage via signed URL. Server is not in the upload path.
Groq Whisper Large v3 transcribes with segment-level timestamps.
MIME type and 100 MB cap enforced both on the server action and bucket policy.
The writer receives transcript segments tagged with bracketed indices; citations reference those indices.
The split-view UI scrolls the cited segment into view on hover.

Multi-tenant B2B

Workspaces, roles (OWNER, ADMIN, MEMBER), invites, API keys, audit log. Three isolation layers — Postgres row-level scoping, application-layer guards on every server action, and Supabase Storage bucket policies keyed by workspace ID.

Status

Under active development. The agent pipeline + workspace tenancy are working; UI polish and the live demo are in progress.