# How Copilot Code Review Was Actually Improved

Adjusting the instructions, not the tools, led to a 20% cost reduction.

- **Source:** [GitHub Engineering](https://github.blog/category/engineering)
- **Published:** 2026-07-10
- **Topic:** [Data & AI](https://brifing.si/c/data-ai)
- **Original article:** <https://github.blog/ai-and-ml/github-copilot/better-tools-made-copilot-code-review-worse-heres-how-we-actually-improved-it/>
- **On Brifing:** https://brifing.si/s/a3b3e68c-11b2-4d42-a66b-b010f293626b

## Root of the Problem

When GitHub Copilot's code review tool switched to better-maintained shared tools, performance dropped unexpectedly. Review costs increased and fewer issues were caught. The issue wasn't the tools—it was the instructions guiding them.

## Legacy System Design

The old system used custom code exploration tools tailored for earlier model behaviors. These tools made fewer calls but bundled extra context, which became inefficient as models evolved.

## New Tools Integration

Integrating shared CLI tools (grep, glob, view) caused the agent to act like a general coding assistant rather than a reviewer. This led to unnecessary broad searches and inflated costs.

## Performance Drop Reason

The agent began scanning entire repos instead of focusing on PR changes. Each tool call added redundant tokens to the context window, making reviews unfocused and costly.

## Human Review Process

Human reviewers start from PR diffs, asking targeted questions with minimal context. The agent needed to emulate this—narrow searches, no irrelevant code—to be efficient.

## Rewriting Instructions

The team redesigned prompts to make the agent behave like a reviewer: focused investigations, minimal context retention. This aligned workflows with actual review needs.

## Results

Post-revision, average review cost dropped by 20% while maintaining quality. Proving that tool usage matters as much as the tools themselves.

## Assistant vs. Reviewer

Coding assistants explore broadly; reviewers investigate narrowly. Copilot's new instructions enforced this distinction, eliminating wasteful browsing loops.

## Shared Infrastructure Benefits

Shared CLI tools serve multiple Copilot products, amplifying improvement impacts. But each product requires tailored instructions for optimal performance.

## Key Takeaway

This case highlights that AI tool efficacy depends heavily on usage instructions. With the right guidance, the same tools can deliver radically better outcomes.

## Sources covering this story

- https://github.blog/ai-and-ml/github-copilot/better-tools-made-copilot-code-review-worse-heres-how-we-actually-improved-it/ — 

---

_Summary written by Brifing from the original reporting. Copyright in the original article belongs to its publisher; read the full piece at the link above._