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

说明与用途

构建了一个只凭证据回答的代理：每个答案都附带官方来源URL、确切引用和新鲜度时间戳，冲突以时间线卡片形式展示。

问题

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

结果

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.

工作流

• 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.

证据

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.

来源

The part I'm proudest of: contradiction cards

来源