[psadri]

You could instruct the LLM to formulate a “lesson” based on the error and add this to the tool instructions for future runs.

[ch4s3]

This isn’t practical at scale. You’ll run into too many novel lessons and burn through too many tokens setting up context.

[psadri]

At scale you need to use more tricks. For example, only inject examples if the tool is going to be needed. Or amass lessons, then ask the LLM to summarize them to prune redundant information before it is used in the context.