> ## Documentation Index
> Fetch the complete documentation index at: https://docs.trysquad.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# How We Review 50+ Agent-Generated PRs Per Week Without Losing Our Minds

> When agents save developer time but humans become the review bottleneck, you haven't solved anything—you've just moved the problem. Here's how we went from 47-minute reviews to 4.2 minutes with an 87% auto-merge rate.

<img src="https://mintcdn.com/trysquadai-f44a1db5/TlrUOcLfmY4w0wGA/images/blog/how-we-review-agent-prs.jpg?fit=max&auto=format&n=TlrUOcLfmY4w0wGA&q=85&s=b2546301417222db58a423dc5c63da40" alt="Reviewing Agent PRs at Scale" width="2752" height="1536" data-path="images/blog/how-we-review-agent-prs.jpg" />

**Author:** Danial Hasan, CTO @ Squad

## The Problem

**Week 1:** 3 agent PRs, 800 lines. Manageable.
**Week 4:** 12 PRs, 4,200 lines. Exhausting but doable.
**Week 8:** 47 PRs, 23,000 lines. **Impossible.**

The math doesn't work. If agents work in parallel (Agent A on checkout, Agent B on payments, Agent C on emails), I can't review each PR in isolation.

**Traditional code review assumes:**

* One human writes code
* Another human reviews it
* Both humans have full context

**Multi-agent reality:**

* 8 agents write code in parallel
* They share partial context
* Human can't hold all 8 contexts simultaneously

Here's what we built to actually ship agent code at scale.

***

## The Key Shift: Verify Proof, Not Code

We moved from "review the code" to "verify the proof."

**Old way (code review):**

* Agent writes 300 lines of checkout flow
* I read 300 lines
* I guess if it's correct
* Takes 45 minutes

**New way (receipt verification):**

* Agent writes 300 lines + generates receipt
* Receipt says: Tests passed (98%), API matches contract, DB migration succeeded, 0 security issues
* I verify the **proof**, not the code
* Takes 3 minutes

***

## The Tools We Use

**Our review stack:**

1. **Receipt System** - Every agent action produces verifiable proof
2. **Acceptance Gates** - Frozen contracts prevent chaos before execution
3. **Director Agent** - Meta-reviewer that checks inter-agent coordination
4. **LLM-as-Judge (Claude Opus)** - Reviews subjective quality
5. **GitHub + Linear Integration** - Automated PR linking with receipt metadata

***

## Actual Stats from Last 30 Days

* **187 agent PRs generated**
* **163 auto-merged (87%)**
* **24 manual reviews (13%)**
* **Average review time:** 4.2 minutes (down from 47 minutes)
* **Rollbacks:** 2 (both caught in staging, 0 in production)

**Compare to our pre-agent baseline:**

* 187 human PRs
* 187 manual reviews (100%)
* Average review time: 47 minutes
* Rollbacks: 7 (3 reached production)

**Agents + receipts are more reliable than humans.**

***

<Note>
  This is a scaffold post. Full content will include:

  * Step-by-step workflow with code examples
  * Frozen contracts YAML format
  * Director Agent pre-review output
  * LLM-as-Judge prompts and responses
  * Auto-merge decision tree
  * Real failure modes and how we fixed them
</Note>

***

## Try It: The Receipt Challenge

**Next AI-generated PR, don't review the code first.**

Instead, check:

1. ✅ Did tests pass?
2. ✅ Did it match the spec?
3. ✅ Did anything unexpected happen?

If all three are ✅, **merge it without reading the code.**

Scary at first. Liberating after the 5th time.

***

**Related Reading:**

* [Receipts-First Governance](/blog/receipts-first-governance)
* [Meta AI Engineer Validation](/blog/meta-ai-engineer-validation)
* [Agent Orchestration Workloads](/blog/agent-orchestration-workloads)