# Building a software factory for AI SDK

Source: [Vercel](https://vercel.com/blog/building-a-software-factory-for-ai-sdk)  
Feed7 permalink: https://feed7.dev/p/building-a-software-factory-for-ai-sdk-73fc37ffd6  
Published: 2026-08-12T00:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

Give each agent one reviewable task with isolated context and evidence, while keeping human scrutiny proportional to change risk.

## 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

- Layer: agent
- Domains: coding, security
- Topics: multi-agent, harness-engineering, sandboxing

## Uncertainty

- None recorded.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.