Warp bets on GPT-5.5 for open-source agent workflows
Curated by the Inblix editorial team
Warp, the modern terminal beloved by developers, is doubling down on open-source development with AI agents powered by GPT-5.5. The company’s Open Agentic Development model lets humans define goals and review outputs while agents handle planning, coding, testing, and pull requests. GPT-5.5 uses 30% fewer tokens per task than its predecessor, making long-running agent workflows more efficient at scale. With nearly 1 million developers and 56% of Fortune 500 companies using Warp, agents now co-create about 90% of internal pull requests. Warp also built Oz, a cloud orchestration platform, to manage agents across local and cloud environments. Why it matters: This signals a shift where open-source contributions become less about writing code and more about providing human judgment and vision, with AI handling the implementation grunt work.
💡 Key Takeaways
- Warp's Open Agentic Development model uses GPT-5.5 for agents that plan, code, and test while humans supervise outcomes.
- GPT-5.5 uses 30% fewer tokens per agentic coding task than GPT-5.4, improving efficiency for long-running workflows.
- Agents now co-create roughly 90% of Warp's internal pull requests, highlighting the scalability of AI-assisted development.
Keep reading: See related articles below for more coverage on this topic.
Get smarter about AI
The sharpest AI news, curated daily. Delivered free to your inbox.