--- title: "News" description: "Product announcements, releases, and company news from Baz, the engineering review platform for AI-written code." canonical: "https://baz.ai/resources/news" --- # News Product announcements, releases, and company news from Baz, the engineering review platform for AI-written code. - [Introducing gion: The Fastest Git Client for Agents](https://baz.ai/resources/news/introducing-gion-the-fastest-git-client-for-agents): gion is a new open source git client from Baz, built for agents and CI. It fetches only the files, trees and commits a task needs, so agents can read, search, commit and push on huge repositories without a full clone. - [Baz Is Now Available on AWS Marketplace](https://baz.ai/resources/news/baz-is-now-available-on-aws-marketplace): Baz is now listed on the AWS Marketplace, so organizations that procure software through AWS can subscribe to Baz against their existing AWS billing and committed spend. - [Baz Announces Planner and an Extended Seed Round Co-Led by Battery Ventures and boldstart ventures](https://baz.ai/resources/news/baz-announces-planner-and-extended-seed-round): At AI Engineer World's Fair, Baz announced Baz Planner - a gateway that eliminates entire classes of bugs and vulnerabilities in code planning - alongside $9M in new funding, bringing total raised to $17M. - [Baz is building agents for the autonomous codebase with Datadog LLM Observability](https://baz.ai/resources/news/baz-is-building-agents-for-the-autonomous-codebase-with-datadog-llm-observability): How Baz uses Datadog LLM Observability to run autonomous agents safely in production - with end-to-end trace coverage, human-in-the-loop validation, and ~80% faster root cause analysis. - [How Baz improved its AI Agent Code Review accuracy using Amazon Bedrock AgentCore](https://baz.ai/resources/news/how-baz-improved-its-ai-agent-code-review-accuracy-using-amazon-bedrock-agentcore): Baz wanted to automate this missing layer of verification, bringing intent, behavior, and implementation into a single review workflow - [LSports cuts time-to-merge by 26% and ships 5.3x more deployments after fast-tracking Baz as their LLM-as-a-Judge for code](https://baz.ai/resources/news/lsports-cuts-time-to-merge-by-26-and-ships-5-3x-more-deployments-after-fast-tracking-baz-as-their-llm-as-a-judge-for-code): LSports - one of the most technologically advanced engineering organizations in real-time sports data - moved early and decisively on agentic coding tooling, partnering with Baz to deploy an LLM-as-a-Judge layer across 241 repositories. The result: a 5.3x increase in deployment frequency, a 7.1-point lift in merge rate, and a 26% reduction in P90 lead time on their slowest, most complex pull requests. Over the same four-month window (Dec 2025-Mar 2026), Baz caught 214 real bugs - including 211 production-impacting issues and 3 security vulnerabilities. - [SpotDraft scales high-signal code review with Baz](https://baz.ai/resources/news/spotdraft-scales-high-signal-code-review-with-baz): Replaces CodeRabbit with production-aware reviews - [PayEm reduced bugs by 50% in 2 months with Baz](https://baz.ai/resources/news/payem-reduced-bugs-by-50-in-2-months-with-baz): After introducing code generation agents into their SDLC, the R&D team at PayEm began looking for a solution to ensure code quality and increase development velocity. - [Spec Reviewer now embeds requirements directly into code review](https://baz.ai/resources/news/spec-reviewer-now-embeds-requirements-directly-into-code-review): Today we’re extending the same model to Spec Reviewer. Unmet requirements now appear inline, pinned to the exact code paths that cause them, and reviews include screenshots from the agent’s sandbox session showing the evaluated behavior. - [Baz Spec Reviewer: Bring Product Requirements Into Backend Review](https://baz.ai/resources/news/baz-spec-reviewer-bring-product-requirements-into-backend-review): Baz’s Spec Reviewer for Backend loads a running environment and verifies backend behavior against the constraints found in Jira tickets, technical requirements, and product specifications. - [Awesome Reviewers: Reusable code review prompts built from GitHub](https://baz.ai/resources/news/introducing-awesome-reviewers-a-public-library-of-ai-powered-prompts-based-on-1-000-github-repos): A free library of code review prompts extracted from the top open source GitHub repositories, ready to drop into your own AI review agents. - [Launching the New Baz Evaluations: From Metrics to Action](https://baz.ai/resources/news/launching-the-new-baz-evaluations-from-metrics-to-action): Baz Evaluations gets an end-to-end redesign. A new Impact Dashboard ties reviewer data to action with org-wide signals, category breakdowns, and recommendations. - [Baz Raises $8M to Rebuild Pull Request Review](https://baz.ai/resources/news/ai-code-is-everywhere-baz-gives-pull-requests-the-overhaul-github-wont-with-8m-seed-round): Developers increasingly lean on AI to write and test code. Baz rebuilds pull request review so those changes never break running applications. - [Turn Past PRs Into Code Review Agents: Introducing Custom Reviewers by Baz](https://baz.ai/resources/news/turn-past-prs-into-code-review-agents-introducing-custom-reviewers-by-baz): Introducing Custom Reviewers, powered by your team’s own pull request history. Paired with the Prompt Playground, this lets you encode, test, and evolve your team’s engineering brain into a system of principles that AI can actually use. - [How Baz Uses RAG for AI Code Review](https://baz.ai/resources/news/baz-releases-rag-powered-ai-code-review-deduplications-and-improved-workflow-customization): How Baz Reviewer uses retrieval-augmented generation for code review: dynamic retrieval and semantic analysis to detect redundancy and enforce standards. - [Introducing Baz: AI Code Review With Full Context](https://baz.ai/resources/news/hello-world): Baz is an AI code review platform built to simplify code reviews, with context-rich insight across your codebase and smarter collaboration for developers. - [Introducing Module Memory: Smarter, More Contextual Code Reviews](https://baz.ai/resources/news/introducing-module-memory-smarter-more-contextual-code-reviews): Discover how Module Memory enhances code reviews through structured, persistent context. See functional shifts, reduce cognitive load, and improve AI-assisted workflows - see this in action with the Change Request Graph in Baz. - [AI Code Review in Any IDE, Securely with Baz MCP Server](https://baz.ai/resources/news/review-any-code-in-any-ide-securely-with-baz-mcp-server): Get high-signal, secure AI code reviews in any IDE with Baz’s new MCP server. No repo integration needed. Just connect, diff, and review. Works with Cursor, Claude, VS Code, and more.