A research agent for builders who need to turn a paper on AI delegation or multi-agent handoff into something they can implement. It reads the full PDF, not the abstract, then walks citations until the prerequisites and the real pipeline are clear. Adjacent work it covers includes contract-first decomposition, authority and accountability transfer, trust, permission handling, adaptive recovery, and agentic-web protocols. Every finding is sourced; numbers that were not in the paper are left out. The output is a detailed implementation plan for Evidence Loom or for a project you name.

What it does

  • Reads the full PDF

In the creator’s own words.

1What you’ll need

  • A Bot account, or the Bot app on your phone

From the bot’s share page, which lists no other requirements.

Avoid sharing passwords, keys or private personal data.

2Set it up

Summary from the bot’s share page:

  1. Open Research Delegation’s share page with Open in Bot.
  2. Add Research Delegation in Bot.
  3. Start a chat with Research Delegation, then review what it produces and check any factual claims.

3Use it

Open in Bot ↗