Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.
Title
Cloudflare builds an internal agentic AI engineering stack on its own platform, reaching 93% R&D adoption
…esh Bhatia 18 minute read COPY URL This post is also available in 日本語 and 한국어 . In the last 30 days, 93% of Cloudflare’s R&D organization used AI coding tools powered by infrastructure we built on our own platform. Eleven months ago, we undertook a major project: to truly integrate AI into our…
Description
Cloudflare describes an eleven-month internal rollout of AI coding tools routed through AI Gateway behind Cloudflare Access, with Workers AI inference, an MCP server portal of 13 servers exposing 182+ tools, AGENTS.md files generated for roughly 3,900 repositories, and an AI Code Reviewer covering all repos on its standard CI pipeline. The source reports 3,683 active users (60% of the company, 93% of R&D), 47.95 million AI requests, and a rise in weekly merge requests from about 5,600 to over 8,700 on a four-week average.
…on used AI coding tools powered by infrastructure we built on our own platform. Eleven months ago, we undertook a major project: to truly integrate AI into our engineering stack. We needed to build the internal MCP servers, access layer, and AI tooling neces…
…, and Code Mode together. Here's the short version of what we built internally. Our internal portal aggregates 13 production MCP servers exposing 182+ tools across Backstage, GitLab, Jira, Sentry, Elasticsearch, Prometheus, Google Works…
…d the system opens a merge request so the owning team can review and refine it. We've processed roughly 3,900 repositories this way. The first pass wasn't always perfect, especially for polyglot repos or unusual…
…complex reviews where reasoning capability matters most. Over the last 30 days: 100% AI code reviewer coverage across all repos on our standard CI pipeline. 5.47M AI Gateway requests 24.77B tokens processed We're releasing a detailed te…
…ere are some numbers that capture our own agentic AI use over the last 30 days: 3,683 internal users actively using AI coding tools (60% company-wide, 93% across R&D), out of approximately 6,100 total employees 47.95 million AI requests 295 teams…
…(60% company-wide, 93% across R&D), out of approximately 6,100 total employees 47.95 million AI requests 295 teams are currently utilizing agentic AI tools and coding assistants. 20.18…
…e’ve never seen a quarter-to-quarter increase in merge requests to this degree. As AI tooling adoption has grown the 4-week rolling average has climbed from ~5,600/week to over 8,700. The week of March 23 hit 10,952, nearly double the Q4 baseline. MCP servers wer…
Company
Cloudflare
The AI engineering stack we built internally — on the platform we ship | Cloudflare Blog Skip to content All Categories AI Developers Radar Product News Security Policy…
Industry
Technology & Software
…y knowledge graph Backstage (OSS) None of this is internal-only infrastructure. Everything (besides Backstage) listed above is a shipping product, and many of them got substantial updates during Agents Week. We’ll walk throug…
Problem
Cloudflare needed to integrate AI into its engineering stack, building the internal MCP servers, access layer, and AI tooling necessary for agents to be useful, and to rethink how standards are codified, how code gets reviewed, how engineers onboard and how changes propagate across thousands of repos.
…we undertook a major project: to truly integrate AI into our engineering stack. We needed to build the internal MCP servers, access layer, and AI tooling necessary for agents to be useful at Cloudflare. We pulled together engineers from across the company to form a tiger team calle…
…were the starting point, but the team quickly realized we needed to go further: rethink how standards are codified, how code gets reviewed, how engineers onboard, and how changes propagate across thousands of repos. This post dives deep into what that looked like over the past eleven months an…
Solution
An internal tiger team called iMARS built the stack on Cloudflare's own products: Cloudflare Access for authentication, AI Gateway for LLM routing, cost tracking and data retention controls, Workers AI for on-platform inference, and an MCP Server Portal aggregating 13 production MCP servers exposing 182+ tools. AGENTS.md files were generated for roughly 3,900 repositories, and an AI Code Reviewer runs on every merge request in the standard CI pipeline.
…, access layer, and AI tooling necessary for agents to be useful at Cloudflare. We pulled together engineers from across the company to form a tiger team called iMARS (Internal MCP Agent/Server Rollout Squad). The sustained work landed with the Dev Productivity team, who also own much of…
…d to solve for access and visibility across many clients, use cases, and roles. Everything starts with Cloudflare Access , which handles all authentication and zero-trust policy enforcement. Once auth…
…enforcement. Once authenticated, every LLM request routes through AI Gateway . This gives us a single place to manage provider keys, cost tracking, and data retention policies. The OpenCode AI Gateway overview: 688.46k requests per day, 10.57B tokens per d…
…AGENTS.md should be updated. Act 3: The enforcement layer The AI Code Reviewer Every merge request at Cloudflare gets an AI code review. Integration is straightforward: teams add a single CI component to their pipeli…
Business value
Cloudflare reports that in the last 30 days 3,683 internal users (60% company-wide, 93% across R&D) used AI coding tools, with 47.95 million AI requests. It also reports that the 4-week rolling average of merge requests climbed from ~5,600/week to over 8,700 as AI tooling adoption grew. These are company-reported figures.
…ere are some numbers that capture our own agentic AI use over the last 30 days: 3,683 internal users actively using AI coding tools (60% company-wide, 93% across R&D), out of approximately 6,100 total employees 47.95 million AI requests 295 teams…
…(60% company-wide, 93% across R&D), out of approximately 6,100 total employees 47.95 million AI requests 295 teams are currently utilizing agentic AI tools and coding assistants. 20.18…
…e’ve never seen a quarter-to-quarter increase in merge requests to this degree. As AI tooling adoption has grown the 4-week rolling average has climbed from ~5,600/week to over 8,700. The week of March 23 hit 10,952, nearly double the Q4 baseline. MCP servers wer…
AI capabilities
Agentic AI, Generative AI
…wn much of our internal tooling including CI/CD, build systems, and automation. Here are some numbers that capture our own agentic AI use over the last 30 days: 3,683 internal users actively using AI coding tools (60% company-wide, 93% acr…
Headline outcome
…esh Bhatia 18 minute read COPY URL This post is also available in 日本語 and 한국어 . In the last 30 days, 93% of Cloudflare’s R&D organization used AI coding tools powered by infrastructure we built on our own platform. Eleven months ago, we undertook a major project: to truly integrate AI into our…
Use case type
Software engineering assistance
…e products we’re shipping and enhancing this week. The architecture at a glance The engineer-facing tools layer ( OpenCode , Windsurf, and other MCP-compatible clients) include both open-source and third-party coding assistant tools. Each layer maps to a Cloudflare product or tool we use: What we built Built wit…
