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)→
More from coding & agent
- Perplexity rolls out effort presets for Computer's model selector for long-horizon agentic work — inductionheads · 2026-09-18
- Jev evaluates PRs 1.93x faster, matches GPT-5.6 Luna verdicts at $0.0014 per review — aniketmaurya · 2026-09-18
- Jev opens trial: fast, consistent PR evaluation at $0.0014 per run — aniketmaurya · 2026-09-18
- Opal Zero launches to inventory and gate AI agent access via MCP, GA in September — testingcatalog · 2026-09-18
- Ramp x Cognition ran an AI-agent-run business: thousands of calls, one breach, $75 revenue — sandylikesfrogs · 2026-09-18
- Grok walks users through installing open-source gods-eye-view via Pinokio, no key needed — cocktailpeanut · 2026-09-18