Key Points

Generative AI as an agentic research tool

  • An agentic assistant runs tools and reads their output; a chat model only returns text.
  • Treat every result as a hypothesis and check it against clear criteria before you accept it.

The measurement: Λ⁰ → p π⁻

  • The Λ⁰ shows up as a peak at 1.1157 GeV in the proton–pion invariant mass.
  • The peak width comes from detector resolution.

Tool servers and the Model Context Protocol (MCP)

  • MCP servers give an assistant tools; any MCP assistant can use them.
  • eic-mcp up starts the servers in eic-shell and eic-mcp config opencode connects opencode.

Persisting instructions: AGENTS.md and SKILL.md

  • AGENTS.md holds project context; a SKILL.md holds a procedure the assistant loads when needed.
  • Put success criteria in the skill so you can check the result.

An end-to-end, reproducible Λ⁰ analysis

  • One prompt runs the whole Λ⁰ analysis, from one file up to the full dataset.
  • Check the fit against the audit checklist before you trust it.

Catalog: MCP servers and AI infrastructure in the EIC ecosystem

  • EIC provides more MCP servers than the three used here.
  • The DISpatcher bot in Mattermost gives you these tools without any setup.