eval-engineering
langchain-ai4.2k installs
Build agent benchmarks backed by real runs.
What it does
Builds reviewed agent evaluation tasks with audited runs and reusable project knowledge.
When to use it
Use for designing agent evaluations, constructing controlled test environments, auditing runs, and maintaining benchmarks.
How to use it
Give it an agent repository and evaluation priorities; it works with you to review a task specification, implement the task, and audit a real run.
What you provide
- An existing project
Good to know
- starts one helper agent per item, so the count depends on the work
Latest review
What you need · 2
Requires the project's pinned or supported Harbor CLI, using its installed help to determine valid commands and flags.
Uses Docker for the default local evaluation environment unless the task requires another supported environment.
Access · 0
No additional actions listed.