Popular two-model workflow: plan in chat, then let the model code

Developer dbreunig shares a favorite workflow: long chat sessions with Fable or Astra produce a detailed Markdown plan, which is then handed to GLM or DeepSeek to write the code.

2026-09-17 ~ 2026-09-18 · 2 related posts

• Dev's workflow: plan via mobile AI chat, hand MD spec to GLM to code — dbreunig · 2026-09-17
• A Two-Model Coding Workflow: Plan in Chat to an MD File, Hand Off to GLM or DS — viksit · 2026-09-18