Back
VercelEngineering PostOfficial SourceagentNew
Building a software factory for AI SDK
Give each agent one reviewable task with isolated context and evidence, while keeping human scrutiny proportional to change risk.
VercelAug 12, 20262 min
Source Summary
Vercel’s AI SDK factory shows a practical scaling pattern: narrow agents produce evidence inside sandboxes while humans retain merge authority and review effort follows risk.
Practical Implication
The reusable pattern is one agent per reviewable task, each with its own prompt, context, and evals. Start locally, pass evidence between classification, analysis, reproduction, implementation, and review stages, then vary human scrutiny by change risk rather than treating every agent output equally.
Agent-Ready Context
AI SDK had accumulated **over 1,000 issues and almost 800 pull requests** by late June. Four weeks after introducing its factory, Vercel says agents authored **25–35% of merged PRs** and closed **70–80% of issues**, while humans approved every merge. The reusable pattern is one agent per reviewable task, each with its own prompt, context, and evals. Start locally, pass evidence between classification, analysis, reproduction, implementation, and review stages, then vary human scrutiny by change risk rather than treating every agent output equally. These are early results from one large open-source project, not a controlled comparison. The factory also depends on isolated sandboxes, restricted secrets and networking, queues, monitoring, and sustained human review, so the headline automation rates omit substantial operating machinery.
Context Map
agentcodingsecurity#multi-agent#harness-engineering#sandboxingGeneric AgentPrepare Coding Session
Rate This Item
Personal Note
No note yet. Notes are included in exported bundles.
Related — Every Edge Explained
No approved edges yet for this post.