Open Source · Live Demo

An agent trace you can actually see

An infinite, Miro-style canvas that renders an AI agent's run as a node-edge graph — every model call, tool call and retrieval, each scored by an eval. The live demo below is a real run of the PubCrawl literature agent answering whether lecanemab slows cognitive decline in early Alzheimer's. Watch it draft an answer that overstates the clinical effect — and the eval catch it.

Real PubCrawl agent run Per-step eval scoring Live WebSocket replay

View on GitHub Open full screen

TypeScript · built on React, Konva & WebSockets · real data via PubCrawl over PubMed & ClinicalTrials.gov

01Live demo

Watch the agent think

Prompt

What is the evidence for lecanemab slowing cognitive decline in early Alzheimer's disease?

Drag to pan, scroll to zoom, click any step to inspect its input, output and eval. Press Replay live to stream the run over WebSocket. Tool inputs and outputs are real (PubCrawl over PubMed & ClinicalTrials.gov); latency and token figures are illustrative.