Carl Yeh

But so essentially it's not actually that difficult of a concept to

But whenever... And I'm trying to think about how I'll tie this into the new team's agents that was yesterday.

But what happened here... So in this example, we have... I have six or seven agents doing specific work on PDFs for a client.

But what we did instead is each agent has a skill attached to it.

And so...

When you built, like, you don't have to have agents to do this.

But in this case, I did.

So each agent has a skill and a learnings MD file.

So what you're doing is every single time you complete a task, in this case, this tab, there's a task that they do and they review 30, 40, 50 PDFs at a time, extract information and rename, do a rename and then move into a different folder.

Every single time it does that task, I have in here a slash command called retrospective.

And so when you hit retrospective,

It does three things.

One is it reviews your entire session, like your conversation for that session.

Then it takes the learnings and failures.

And then it updates the learning and the skill for each agent, subagent here.

So every single time we complete a task, I just hit retrospective.

So everything that we learn from that task, any edge cases, is automatically populated into the learnings and skill.

And every single time the agent executes, it goes into its learnings and its skill.

So hence, continuous learning every single time it's used.

So that's pretty much it.