I Realized I Couldn't Trust AI With My Research

说明与用途

Research Council通过Sanity知识库的结构化证据验证，防止AI记忆架构的不可比对结果被误用。

问题

Researchers need a trustworthy method to compare AI memory architectures, but existing papers use incomparable benchmarks, models, and metrics, leading to unreliable conclusions.

结果

Research Council delivers evidence-backed verdicts, preventing fabricated conclusions and highlighting when evidence is lacking.

工作流

• 1. Populate Sanity Knowledge Base with 13 research papers and custom instructions for recording results.
• 2. Use Sanity Context tools: initial_context, knowledge_base_search, knowledge_base_read to fetch relevant evidence.
• 3. Run four agents in parallel: Researcher A, Researcher B, Contradiction Hunter, Evidence Auditor.
• 4. Verifier retrieves cited entries via knowledge_base_read and checks quotes word‑for‑word.
• 5. Judge aggregates verified evidence and outputs a verdict.
• 6. Result is a clear indication of whether evidence supports, contradicts, or is insufficient for the research question.

证据

The problem was that almost every approach had results showing that it worked, but those results weren't always directly comparable.

来源

One full investigation takes just 5 model calls: four agents in parallel, then the Judge.

来源

Research Council doesn't treat a research question as a prompt that needs an answer. It treats it as an investigation.

来源