Prompt Junky

AgentEvals

Online · Nationwide

AgentEvals

A companion LangChain package focused on scoring agent trajectories, comparing the sequence of tool calls an agent made against an expected path.

Image from the business's own website.

Services

  • Trajectory matching
  • Tool call evaluation
  • LLM-as-judge trajectories
  • LangSmith integration

Highlights

  • #python
  • #javascript
  • #agent-evals
  • #mit

Source: Official GitHub repository. Last checked 2026-11-11. Spot an error? Tell us.

Nearby and similar

More prompt tools

All prompt tools

Books

These links go to searches on Amazon. If you buy something after following one, this site may earn a commission at no extra cost to you. Nothing here is a paid placement, and no listing on this site pays to be included or ranked.As an Amazon Associate I earn from qualifying purchases.