We Should Revisit Literate Programming in the Agent Era

this person didn't know about detangling or entangled, but...

Now when I want to test a feature, I ask the clanker3 to write me a runbook in Org. Then I can review it – the prose explains the model's reflection of the intent for each step, and the code blocks are interactively executable once I am done reviewing, either one at a time or the whole file like a script. The results will be stored in the document, under the code, like a Jupyter notebook.

I can edit the prose and ask the model to update the code, or edit the code and have the model reflect the meaning upon the text. Or ask the agent to change both simultaneously. The problem of maintaining the parallel systems disappears.

The agent is told to handle tangling, and the problem of extraction goes away. The agent can be instructed with an AGENTS.md file to treat the Org Mode file as the source of truth, to always explain in prose what is going on, and to tangle before execution. The agent is very good at all of these things, and it never gets tired of re-explaining something in prose after a tweak to the code.