Better tools made Copilot code review worse. Here’s how we actually improved it.

Summary

When migrating GitHub Copilot code review from custom navigation tools to shared Unix-style CLI utilities—grep, glob, and view—benchmarks revealed higher review costs and fewer caught issues. Rather than an issue with the underlying tools, trace analysis showed the agent used general-purpose coding assistant instructions that triggered expansive repository browsing loops. In response, the team rewrote the tool guidance to enforce a review-specific workflow anchored to pull request diffs. The updated instructions direct the agent to narrow candidate call sites and files using batched discovery before reading minimal line ranges with view. This workflow tuning reduced average review costs by approximately 20% in production while maintaining review quality.

Context

Migrating Copilot code review to shared Copilot CLI code exploration tools caused higher token costs and fewer caught issues because general-purpose assistant prompts led the agent to browse repositories broadly instead of investigating diff evidence.

Approach / What changed

Rewriting the tool instructions to follow a review-specific workflow that anchors to the pull request diff, batches cheap discovery via grep and glob, reads minimal line ranges with view, and prevents guessing paths on search failures.

Takeaways

• Retaining broad tool output inside an LLM's working context inflates token usage and degrades focus across subsequent reasoning steps.
• Restructuring tool guidance to prioritize diff-anchored discovery before focused reads lowered average review costs by roughly 20% while maintaining review quality.
• Tool prompt optimizations tailored to pull request reviews failed to produce identical wins in the Copilot CLI, where broad interactive exploration remains necessary.

Related reading

• Github · Jul 8, 2026

  Automating cross-repo documentation with GitHub Agentic Workflows

  Maintaining documentation across separate repositories often leads to severe lag because technical writers must reverse-engineer shipped features weeks after release. To address this in the Aspire project, the team implemented an automated pipeline using GitHub Agentic Workflows to bridge the product and documentation repositories. When product pull requests merge, a bash step maps milestones to docs release branches before an LLM agent evaluates the diff, drafts documentation updates, and emits structured pull request intents. A dedicated safe-outputs handler materializes these drafts via a scoped GitHub App and assigns the original code reviewers to verify accuracy. Across 396 product pull requests, the system generated 82 documentation pull requests that all merged with a median turnaround time of 44.8 hours.

  David Pine

• Github · Aug 10, 2026

  Using the GitHub Copilot SDK for Java

  The GitHub Copilot SDK for Java offers a framework-agnostic client library to orchestrate AI agent sessions and tool execution directly from server-side Java code. Unlike framework-dependent alternatives, the SDK supports direct model providers such as OpenAI, Azure, and Anthropic through custom endpoint configurations without requiring a Copilot subscription. Developers can register tools declaratively using the experimental @CopilotTool annotation processor or dynamically through inline lambda definitions with ToolDefinition.from. When integrated into a Jakarta EE 11 application on Open Liberty, agent workflows run on container-managed virtual threads that propagate CDI and transaction contexts during blocking calls like sendAndWait. Real-time event subscriptions capture model execution steps and tool invocations to stream updates over WebSockets without exhausting platform threads.

  Edward Burns

• Github · Jul 17, 2026

  The cost of saying yes has changed

  Generating initial code patches has become significantly cheaper with AI agents, shifting the primary expense of small feature requests from writing code to debating scope in meetings. Teams can use agent-generated patches as diagnostic probes rather than final deliverables, turning abstract scope debates into concrete artifacts that reveal true system touchpoints and risks. However, low generation costs do not translate to low ownership costs, as changes touching areas like authorization, compliance, or public contracts still demand significant human review. Constrained attempts allow engineers to price uncertainty quickly and shift scope discipline from pre-implementation speculation to evidence-based code review.

  Dalia Abuadas

• Github · May 14, 2026

  From latency to instant: Modernizing GitHub Issues navigation performance

  GitHub Issues addressed navigation latency by shifting workloads to the client using a local-first, stale-while-revalidate architecture. To evaluate perceived delays, the team tracked user transitions through Highest Priority Content thresholds, aiming for instant rendering in under 200 milliseconds. The core implementation added a persistent client-side cache using IndexedDB, paired with a synchronous in-memory tier to serve hot issue payloads without asynchronous overhead. A selective preheating mechanism resolves missing cache entries for high-intent links without overburdening backend capacity with redundant requests. Following broad rollout, the proportion of instant React soft navigations increased from 4% to approximately 22%, yielding an overall cache-hit ratio of around 33%.

  Natalie Guevara