Speeding up agentic workflows with WebSockets in the Responses API
What changed
A deep dive into the Codex agent loop, showing how WebSockets and connection-scoped caching reduced API overhead and improved model latency.
Why it matters
A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.
How it compares
Related prior coverage to compare against:
- Unrolling the Codex agent loop
- New tools and features in the Responses API
- Open LLM Leaderboard: DROP deep dive
Sources
- Speeding up agentic workflows with WebSockets in the Responses API (openai-blog)primary