Get early access
Back to episodes
#4010 months ago

Applying 12-Factor Principles to Coding Agent SDKs

We've done a lot of talking in the last few months about prompting coding agents and context engineering w/ markdown files, but today we'll talk about how to squeeze even more out of agents by using agent loops as smaller elements of a deterministic workflow. In this session we'll cover: - using the claude agent sdk to stitch together microagent workflows - accumulating user rules across context windows - json state and structured outputs with zod - session continuation and forking vs. direct compaction

Project details

Open in GitHub

ai that works: Applying 12-Factor Principles to Coding Agent SDKs

We've done a lot of talking in the last few months about prompting coding agents and context engineering w/ markdown files, but today we'll talk about how to squeeze even more out of agents by using agent loops as smaller elements of a deterministic workflow.

Video

Topics Covered

  • Using the Claude Agent SDK to stitch together microagent workflows
  • Accumulating user rules across context windows
  • JSON state and structured outputs with Zod
  • Session continuation and forking vs. direct compaction

Links

<!-- Add relevant links here -->

Resources

Whiteboards

image

image

image

image

image

image

image

All episodes