Cloudflare Launches Agent Lee to Manage Infrastructure via Natural Language Prompts

Cloudflare

Apr 16, 2026 · Updated Apr 25, 2026

Cloudflare introduced Agent Lee, an in-dashboard AI agent that allows users to troubleshoot and manage their entire stack through a single conversational interface. By shifting from manual tab-switching to a grounded technical collaborator, the agent simplifies complex DevOps tasks like debugging errors and deploying resources.

Cloudflare, a network and security company, launched Agent Lee in beta, an AI agent integrated into the dashboard as a technical collaborator. It understands account-specific context—including Workers and DNS—to answer questions and execute changes. The agent uses Codemode to generate TypeScript code for multi-step tasks, improving accuracy over standard tool-calling (invoking functions via structured requests).

Managing cloud infrastructure often requires cross-referencing logs across dozens of tabs. Agent Lee collapses this complexity into a single prompt, using a sandboxed environment to interact with account data. A mandatory human-in-the-loop approval step ensures no configuration changes occur without explicit user consent.

You can now use the agent to visualize traffic trends or deploy resources without manual navigation. Agent Lee is available to Free plan users via the dashboard. The system is built on the same Agents SDK and MCP infrastructure available to all Cloudflare developers.

View the full update on blog.cloudflare.com

Cloudflare

@CloudflareApr 15

Agent Lee is an in-dashboard agent that shifts Cloudflare’s interface from manual tab-switching to a single prompt. Using sandboxed TypeScript, it helps you troubleshoot and manage your stack as a grounded technical collaborator. https://t.co/bVqer0inVp

953

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

See all AI news & updates from Cloudflare →

Keep reading

Cloudflare Launches Agent Memory to Give AI Agents Persistent Long Term State

Cloudflare introduced Agent Memory, a managed service that extracts and stores key information from agent conversations to prevent context rot. By moving state management to a dedicated pipeline, agents can recall past decisions and facts across sessions without exhausting their context windows.

Cloudflare adds MiniMax M3 with 1M context for agentic coding

MiniMaxJun 2

Cloudflare adds MiniMax M3 with 1M context for agentic coding

Cloudflare has integrated the MiniMax M3 foundation model into its AI Gateway platform. The update provides developers with a high-context, multimodal model specialized for autonomous coding tasks directly within their existing infrastructure.