Build a coding agent with GPT 5.1

kept by eddie nov 19, 25

OpenAI demonstrates building a GPT-5.1 coding agent that scaffolds NextJS/shadcn apps using shell, web search, apply_patch, and Context7 MCP tools via the Agents SDK and Responses API.

The Anatomy of an Agent Harness
An agent's usefulness comes from its 'harness'—the code, tools, and orchestration around the model—which must be engineered for tasks like durable storage, code execution, and context management.
also on Context7, #ai-coding, #developer-tools
Context7 - Up-to-date documentation for LLMs and AI code editors
Context7 generates up-to-date documentation context for LLMs and AI code editors.
also on Context7, #ai-coding, #developer-tools
Where the goblins came from
OpenAI traced GPT-5.1's goblin metaphor habit to reinforcement learning rewards that favored creature metaphors in Nerdy personality training.
also on GPT-5.1, #generative-ai, OpenAI
Unrolling the Codex agent loop
OpenAI explains the architecture of Codex CLI's agent loop, detailing how it orchestrates model inference, tool calls, and context management using the Responses API.
also on Responses API, OpenAI, #open-source, #ai-coding, #developer-tools
GPT-5.1-Codex-Max Prompting Guide
OpenAI recommends migrating to the Codex-Max agentic model using the codex-cli prompt, compacted context, and specific tools for best performance on complex coding tasks.
also on Responses API, OpenAI, #open-source, #ai-coding, #developer-tools