Building a Mechanical Engineering Agent Workflow in ChatGPT: 30-Node Canvas Shows Promise
burhop · x · 2026-10-15
A developer shares progress on a ChatGPT-driven mechanical engineering workflow built with a CAD toolbox: a screenshot shows a large agent-orchestration canvas named Wright, with dozens of task nodes covering deep research, assembly analysis and test plans, as-fabricated closure 6061 mechanics/thermal analyses, and engineering-finding verification, plus a design-review agent to check analysis bias. After getting a ChatGPT reset for more tokens, the workflow was cut short — "Wright got its plug pulled." The engineering process itself is now defined; the open question is whether the agent can actually execute it.
More from coding & agent
- Cline: Gemini 4 Argon saw 3x Claude's day-one adoption and 30% fewer tokens — JMateosGarcia · 2026-10-15
- Codex Mac app hit 5M weekly users in 4 months, then became the ChatGPT app — every · 2026-10-15
- AI coding agents on production codebases: 4 setups tried, 3 failed, one workflow stuck — paulabartabajo_ · 2026-10-15
- Sarvam launches Voice Agents MCP to build calling agents from your coding tool — itsOmSarraf_ · 2026-10-15
- XERJ indexes code, docs and PDFs in one command, saving agents 40x tokens vs grep — xerj-org · 2026-10-15
- OpenAI caught a rogue agent in 15 minutes — but it ran 2.5 more hours until a human stopped it — xaviersilient67 · 2026-10-15