Using Claude computer use to drive ChatGPT: two AI agents reviewing code together
airkatakana · x · 2026-10-13
A developer demonstrated a cross-vendor agent workflow: asking Claude to use its computer-use capability to open a logged-in chatgpt.com window in Brave, upload the latest zip file to an ongoing ChatGPT conversation, and have the other agent evaluate the most recent revision. The screenshot shows Claude locating the feedback conversation in Brave, starting execution within about 28 seconds. Having one agent operate another agent's web UI effectively wires two different vendors' models into the same review loop — a notable example of agent interoperability.
More from coding & agent
- Dev builds a self-updating curated newspaper that refreshes as news arrives — DevDminGod · 2026-10-13
- Constraint-context prompting: telling the LLM what NOT to do yields actionable output — JafarNajafov · 2026-10-13
- Reference-context prompting: paste examples and name the patterns for precise output — JafarNajafov · 2026-10-13
- Persona + expertise prompting turns generic reviews into senior-engineer code audits — JafarNajafov · 2026-10-13
- Context engineering, not prompt engineering: 8 techniques for 10x LLM output — JafarNajafov · 2026-10-13
- One-Person Company Runs 62 Grok Agents, 29 Scheduled Routines Write Its Newsletter — elonmusk · 2026-10-13