My workflow is also highly inspired by Matt's skills, but I'm leveraging Linear instead of Github.

/grill-me (back-and-forth alignment with the LLM) --> /write-a-prd (creates project under an initative in Linear) --> /prd-to-issues (creates issues at the project level). I'm making use of the blockedBy utility when registering the issues. They land in the 'Ready for Agent' status.

A scheduled project-orchestrator is then picking up issues with this status leveraging subagents. A HITL (Human in the loop) status is set on the ticket when anything needs my attention. I consider the code as the 'what', so I let the agent(s) update the issues with the HOW and WHY. All using Claude Code Max subscription.

Some notes:

- write-a-prd is knowledge compression and thus some important details occasionally get lost

- The UX for the orchestrator flow is suboptimal. Waiting for this actually: https://github.com/mattpocock/sandcastle/issues/191#issuecom...

- I might have to implement a simplify + review + security audit, call it a 'check', to fire at the end of the project. Could be in the form of an issue.

▲

hansmayer 3 days ago | parent [-]

Phew, that's a very elaborate process indeed. It seems like folks like you are now working even more than without LLMs. What did you actually build and release with it?

▲

Bossie 3 days ago | parent [-]

Building a multi-app monorepo for apps which integrate with a Dutch ERP vendor. I'd say the size of those apps is fairly small.

Also building out an MCP server.

	▲	hansmayer 3 days ago \| parent [-]
		Oh. Honestly for those relatively limited use-cases, you'd probably be better off just retaining the LLMs as a verbose search engine, rather than going through all that pain, just to build a monorepo.