Having an interpreter and compiler allows interesting workflows. E.g elisp users can try in the interpreter then compile when they're happy.
miniblog.
Related Posts
Some novel (to me) AI workflows from OpenAI in https://openai.com/index/open-source-codex-orchestration-symphony/
(1) Adding the ability for the LLM to create follow-up tasks in the issue tracker.
(2) Identifying weaknesses in the spec by implementing in several different languages.
Agentic programming workflows rather remind me of genetic programming. The agent has a validation step that looks like a fitness function, and both run iterative trials.
I certainly see the appeal of an LLM system with full context and tool use (OpenClaw), but the lethal trifecta puts me off deploying it.
I do like the idea of an agent with a heartbeat though. A bunch of nice cron-style workflows can be built on top.