I've been using Codemode with the new Dot so that Dot can coordinate my agents with:
1. Launching workflows, so it avoids some large configuration
2. Reviewing work, with reviewers restricted to read-only tools or specific tools. Or some tools for reviewers to check hashes, correctness, etc.
3. I'm using the widely used pi-extensible-workflows. So say you want to stop a workflow, you gonna call workflow_stop. Or check the status with workflow_status. Without Codemode, Pi exposes an API, that the agent can use. So yes, you can call workflow_status. Or call workflow_stop. With Codemode, the agent can do something more complex like a for loop over all the list of workflow ids and get a status and stop them all (again, it's just an example).
So basically, Codemode allows to build a sort of framework for more correctness like using a typed language vs. JavaScript without a linter. It gives boundaries essentially. And also Codemode allows an agent to do things more easily like using internal Pi extensions.
1. Launching workflows, so it avoids some large configuration
2. Reviewing work, with reviewers restricted to read-only tools or specific tools. Or some tools for reviewers to check hashes, correctness, etc.
3. I'm using the widely used pi-extensible-workflows. So say you want to stop a workflow, you gonna call workflow_stop. Or check the status with workflow_status. Without Codemode, Pi exposes an API, that the agent can use. So yes, you can call workflow_status. Or call workflow_stop. With Codemode, the agent can do something more complex like a for loop over all the list of workflow ids and get a status and stop them all (again, it's just an example).
So basically, Codemode allows to build a sort of framework for more correctness like using a typed language vs. JavaScript without a linter. It gives boundaries essentially. And also Codemode allows an agent to do things more easily like using internal Pi extensions.