Simplified agent with single bash tool, improved performance
Vercel redesigned their internal AI agent (d0) by removing specialized tools and complex prompt engineering, replacing them with a single bash command execution tool. The simplified approach improved success rate from 80% to 100% while reducing latency and token usage.
It got better.
We spent months building a sophisticated internal text-to-SQL agent, d0, with specialized tools, heavy prompt engineering, and careful context management. It worked… kind of. But it was fragile, slow, and required constant maintenance.
So we tried something different. We deleted most of it and stripped the agent down to a single tool: execute arbitrary bash commands. We call this a file system agent. Claude gets direct access to your files and figures things out using , , and . grepcatls
The agent got simpler and better at the same time. 100% success rate instead of 80%. Fewer steps, fewer tokens, faster responses. All by doing less.
Source: original entry ↗
More from Vercel
Follow Vercel to get its new changes in your feed and email digest.
OpenAI Decisions API now available on AI Gateway
OpenAI's Decisions API is now accessible through Vercel's AI Gateway with an OpenAI-compatible endpoint, enabling decision models to answer typed questions and return probabilities, choices, and scores for routing, triage, and guardrails use cases. Support is available across the OpenAI SDK, AI SDK, HTTP API, and CLI with the latest versions.
Timestamp attributes now supported in Vercel Flags
Vercel Flags now supports timestamp attributes for entities, allowing you to create time-based targeting rules. Use this feature to run limited-time campaigns, show content between specific dates, or target users based on registration date.
Glyph Cluster now available in stealth on AI Gateway
Glyph Cluster, a reasoning model for coding and long-context analysis, is now available as a stealth model on Vercel's AI Gateway for Pro and Enterprise plan teams with purchased AI Gateway credits at no cost during the stealth period. The model supports function calling, streams responses, and can be accessed via AI SDK, OpenAI-compatible APIs, and coding agents.