A Two-Model Coding Workflow: Plan in Chat to an MD File, Hand Off to GLM or DS

viksit · x · 2026-09-18

Developer dbreunig shares his favorite current coding setup: have a long conversation with Fable or Astra in mobile chat apps that produces a large MD file with design and plan, then feed that file to GLM or DeepSeek Flash to do the coding. In the thread he notes he uses Pi. A two-stage "strong model plans, another model executes" workflow.

Related event: Popular two-model workflow: plan in chat, then let the model code(2 posts)→

Original post →

More from coding & agent

coding & agent channel →