🚫 Workshop: Evals-Driven Developmen

Repo: https://github.com/Significant-Gravitas/AutoGPT


Forge Setup
./run setup
./run agent start forge

Benchmark Setup
cd benchmark
???

Agents — There are agents with side-effect or not.
Amongst the side-effect, there are some that may cause harm (e.g. sending an email, deleting a file) → For those agents, the reliability will need to be much higher than 99.9% (It has to work everytime.)


Followup
Look into Agent Protocol
Want to print your doc?
This is not the way.
Try clicking the ⋯ next to your doc name or using a keyboard shortcut (
CtrlP
) instead.