--- title: "High-Signal AI Code Review That Adapts to Your Codebase at Scale" url: https://daily.dev/posts/high-signal-ai-code-review-that-adapts-to-your-codebase-at-scale-qemkduhog source_url: https://www.linkedin.com/blog/engineering/ai/high-signal-ai-code-review-that-adapts-to-your-codebase-at-scale type: article source: "LinkedIn Engineering" published: 2026-08-13T13:29:51.939Z updated: 2026-08-15T05:18:36.515Z tags: ["llm", "ai-agents", "code-review", "linkedin"] reading_time: 13 upvotes: 1 comments: 1 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # High-Signal AI Code Review That Adapts to Your Codebase at Scale **[LinkedIn Engineering](https://daily.dev/sources/linkedin)** · 13 min read · 1 upvotes · 1 comments ## Summary LinkedIn describes a multi-agent AI code review system deployed across roughly 10,000 repositories, handling 79,000+ weekly review comments with a 63.9% acceptance rate. The architecture runs multiple model-and-harness subagents in parallel per PR, cross-validates and deduplicates their findings (treating overlap as a confidence signal), and layers a three-tier customization framework encoding org- and repo-specific conventions. Reviews typically post before human reviewers even open the PR, with a speed SLA targeting under 10 minutes end-to-end. Acceptance is measured post-merge by checking whether suggestions were actually incorporated into merged code, with correctness-related suggestions (bug fixes, logic errors, concurrency bugs) seeing far higher acceptance than refactoring or security suggestions. Future work includes a visual risk-heatmap review surface and pipelines that turn production incident postmortems into new review rules. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does LinkedIn measure whether AI code review suggestions are actually useful, not just upvoted? LinkedIn built a post-merge acceptance-rate pipeline that compares AI reviewer suggestions against the final merged codebase rather than relying on thumbs-up reactions. Across 1,727 PRs and 5,230 sampled comments over a 7-day window, an LLM-based evaluator classified each suggestion as accepted, partially accepted, not accepted, or not actionable, with 90.1% of judgments rated high-confidence, yielding an overall 63.9% acceptance rate. _daily.dev surfaces engineering writeups like this for teams weighing how to measure AI code review impact._ ### Why did LinkedIn build its own multi-agent AI code reviewer instead of using an off-the-shelf vendor tool? Single-model reviewers carry fixed training biases that cause consistent blind spots, their rule-file context injection can't compose organization-wide and repo-specific policies across thousands of repositories, and they are consumed as products rather than operated as infrastructure, preventing canarying, failover, or fleet-wide observability. LinkedIn's multi-agent system runs several independent model-and-harness subagents per PR and cross-validates their output to close these gaps. _developers evaluating build-vs-buy for AI code review can compare architectures like this on daily.dev._ ### Which types of AI code review suggestions get accepted most often by developers? Correctness-oriented suggestions see the highest acceptance: concurrency bug flags reach 100% acceptance, logic error suggestions reach 80%, and bug fixes overall sit at 58.1%, the highest-volume category. Refactoring suggestions land at 43.5% and security suggestions at 40.6%, reflecting that these categories are more subjective and context-dependent rather than indicating lower suggestion quality. _teams tuning AI reviewer prompts can track category-level acceptance benchmarks like these on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@agustinbarrientos** · 0 upvotes > The evaluator should publish disagreement rates by category, especially where acceptance depends on an LLM reading the merged diff. A 63.9% headline needs a calibration trail. ## Similar posts on daily.dev - [AI Code Review at Scale: LinkedIn's Multi-Agent Approach](https://daily.dev/posts/ai-code-review-at-scale-linkedin-s-multi-agent-approach-7lpkuhkzi) · InfoQ · 0 upvotes · 0 comments - [Orchestrating AI Code Review at scale](https://daily.dev/posts/orchestrating-ai-code-review-at-scale-re4wh2np4) · Cloudflare · 0 upvotes · 0 comments - [AI Code Review Bottleneck 2026: Why PRs Are Stuck in Review](https://daily.dev/posts/ai-code-review-bottleneck-2026-why-prs-are-stuck-in-review-o7qcycgq0) · Alex CloudStar · 1 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#code-review](https://daily.dev/tags/code-review), [#linkedin](https://daily.dev/tags/linkedin) [View this post on daily.dev](https://daily.dev/posts/high-signal-ai-code-review-that-adapts-to-your-codebase-at-scale-qemkduhog)