I built an evidence agent that refuses to answer without receipts (my first hackathon entry)

Description and use

Built an evidence agent that answers only with receipts: each answer includes an official source URL, exact quote, and freshness timestamp, with contradictions shown as timeline cards.

Problem

Frontier model specifications (context windows, prices, capabilities) change monthly, causing LLM answers to become stale quickly.

Outcome

The agent provides grounded answers with receipts, flags stale claims, and resolves contradictions via timeline cards, demonstrating a proof‑of‑concept for evidence‑based model fact retrieval.

Workflow

• 1. Collect official provider pages for model specs.
• 2. Create evidenceClaim documents in a Sanity dataset with source URL, quote, and observed date.
• 3. Use Sanity’s hosted Context MCP endpoint to query the knowledge base.
• 4. Build a Next.js UI on Netlify to display answers and contradiction cards.
• 5. Deploy the agent, keeping environment secrets in a vault.
• 6. Test the agent by asking constraint questions and reviewing contradiction cards.

Evidence

Ask it the constraint question today and it answers: one model satisfies every constraint - Claude Haiku 4.5, 200,000-token context (official Anthropic models page), $1 per million input tokens (official Anthropic pricing page), both observed today, 0 stale claims, 0 active conflicts.

Source

The part I'm proudest of: contradiction cards

Source