Coding Models Move to Multi-Agent Workflows
nptacek · x · 2026-07-17
This post reviews the evolution of coding models: a few years ago, models would write // todo due to insufficient context windows; now, a system can launch 40 sub-agents in a single workflow and max out quota within 15 minutes.
The point: the bottleneck for coding AI is no longer just "can it code?" but how to push task scale further through multi-agent orchestration.
More from coding & agent
- Tenable and AWS launch a Black Hat build event for open-source security agents and MCP servers — Dave_Maynor · 2026-07-22
- Codex helps build Valdiluce, an open-world game with climbing, gliding and gondolas — Dimillian · 2026-07-22
- HeyGen adds a media-sourcing skill for coding agents with 75k images and 10k tracks — HeyGen · 2026-07-22
- Agent search bottlenecks are now about variance, not raw latency — rohanpaul_ai · 2026-07-22
- LangSmith adds tracing for Pipecat, LiveKit, OpenAI Realtime, and Gemini Live — LangChain · 2026-07-22
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22