Catching rogue AI behavior with identity-aware analytics

When you look at your AI bill, it can be hard to tell if anything is amiss. You first need a baseline so you can see what has changed, whether it’s an agent that’s gone wild or an employee whose usage has spiked 10x. Being able to spot those shifts lets you start investigating, and so far, it’s been hard to see them.

Knowing who is doing what with AI is one of the key challenges organizations are confronting right now. One report from Stanford University found that 59% of organizations said knowledge gaps were their biggest obstacle to responsible AI governance. 

This is a security problem as much as a financial one. Solving these issues takes two things: a verified identity on every request (so a spike has a name behind it), and a picture of what normal looks like for that identity. Today we're announcing both.

Identity-aware AI Gateway with Cloudflare Access is now in open beta, and User Insights is generally available to every AI Gateway customer at no additional cost. Together they turn the traffic already flowing through AI Gateway into a behavioral baseline for every person and agent using it, and identify the ones Continue reading

Minisforum MS-A2 Review for Network Labs/Homelab

Minisforum MS-A2 Review for Network Labs/Homelab

In my previous blog post, I covered setting up network labs on a budget using used mini PCs, and I saw good interest in that post. So, I thought I would write another one sharing my experience using the Minisforum MS-A2 for network labs. As of writing this post, the MS-A2 costs £1160 with an AMD Ryzen 9 9955HX, 32GB of DDR5 RAM, and 1TB of storage. You can buy the barebone version (without RAM and storage) for £727 on Amazon. I bought the 32GB version + 1TB of RAM.

I would have bought the 64GB RAM version (I'd recommend 64GB for anyone buying) if that was available on Amazon, but that option was only available on the Minisforum website, and it ships from their HK warehouse and takes a few days. So I went with Amazon, which came with a single 32GB stick, and then added another 32GB stick myself (RAM costs a fortune as of writing this post 😢)

  • CPU options - AMD Ryzen 9 9955HX / 9 7945HX / 7 7745HX. I went with the 9955HX (16c/32t) for extra headroom running multiple labs at once.
  • RAM - Dual channel DDR5-5600MHz, up to 96GB. Plenty for running Continue reading

PP120: News Roundup—AI Giants Praise Open Weight Models, Attackers Capture Captive Portals, a Tricky Mac Attack, and More

Packet Protector uncorks another News Roundup! We talk about attackers capturing hotels’ captive portals to steal Microsoft credentials, and the OpenAI-attacking-Hugging Face story and how it ties into a broader industry effort to keep the US government from blocking access to open weight AI models from China. Nvidia and the Linux Foundation launch separate AI... Read more »

HS139: When “One Cloud to Rule Them All” is NOT the Answer: Regionalization

IT folks spent a lot of time in the last 20 years creating globe-spanning infrastructures that maximize performance while minimizing the number of data centers or cloud instances they operate. More recently, the steady rise of regionalized data sovereignty requirements has created counter-pressure. AI regulations are now adding to that pressure to ditch a single... Read more »

The Agent Development Lifecycle has arrived on Cloudflare

Engineering managers spent the past few decades figuring out ways for many programmers to work together on a shared codebase. This work dates all the way back to the “Systems Development Lifecycle” (RAND, 1975) - today commonly referred to as the “Software Development Lifecycle” (SDLC), which defines the following phases:

  • Plan
  • Design
  • Implement
  • Test
  • Deploy
  • Maintain
  • Retire

AI has made the step that was previously the slowest and most expensive — implementation — the fastest and cheapest. That, in turn, has had an impact downstream: overwhelming the people responsible for all the other steps in the SDLC. This ranges from open-source maintainers bombarded with thousands of pull requests and issues, to production engineers trying to save production from falling over as the rate of software delivery increases orders of magnitude.

We are all trying to save our systems, our customers, and ourselves from slop.

The answer — paradoxically — is to empower agents to do more. It’s only fair! You’d never let an engineer on your team write code, expect someone else to validate it, merge it, deploy it, hold the pager in production, and triage incoming bugs. But that’s what most companies are doing right now with agents. Continue reading

Run CI/CD for millions of repos — on your platform, on Cloudflare

We are moving toward a world in which you can store, build, test, and deploy your code fully on Cloudflare. We built the first piece with Artifacts, versioned code storage that scales to millions of repos. 

We have stitched the store, build, and deploy steps together with the CI SDK, built on Cloudflare Workflows, so that you can run your continuous integration (CI) pipeline on Cloudflare. You can send artifact push events directly to your Workflow, triggering an instance of its execution — a CI job, essentially — through a new events field in your wrangler configuration file. 

Then, directly from the Workflow with @cloudflare/ci installed, you can:

  • Automate builds: compile code from your Artifacts repo in a safe, isolated environment 
  • Run linters and typechecks: enforce code style, catch type errors, and flag any potential issues
  • Cache dependencies: run your install once and cache dependencies across steps in the CI job
  • Execute unit tests: verify that each piece of your code works as expected
  • Self-heal: integrate an AI review agent to catch broken steps in your build and push commits to fix 
  • Deploy conditionally: automatically deploy your code, only if your build step is successful

Continue reading

How Cloudflare enforces engineering standards using AI

Over the past four months, our AI code reviewer has flagged nearly a quarter of a million deviations from Cloudflare engineering standards (what we’ll call “violations” in this post) and blocked 16,000 merges. Our spec reviewer agent has evaluated close to 600 technical designs against the same standards before implementation began. Both systems draw from the Cloudflare Codex, a shared source of engineering guidance built for people and agents. This post explains why we built the Codex, how it supports the engineering lifecycle, and what we plan to do next.

Before the Codex (which we briefly introduced in a previous post about our AI engineering stack), developer guidance at Cloudflare lived in many places: formal documentation, repository files, chat threads, and the accumulated knowledge of individual engineers. Engineers often spent too much time searching for guidance instead of working on the problem they were trying to solve. Even after finding an answer, they could not always tell whether it was current, authoritative, or applicable to their situation.

As Cloudflare grew, that model became increasingly difficult to sustain. No engineer could read every standard, and reviewers could not reliably check every requirement. Institutional knowledge became harder to recover when people moved Continue reading

Introducing: Cloudflare Agents

We're bringing together everything you need to deploy and manage hosted agents on Cloudflare, starting with observability.

We've spent the last nine years building a developer platform, and agents are the perfect use case. They're really just another type of application, but what you need to build them — model access, durable runtime, orchestration, sandboxed execution, persistent storage — happens to be exactly what we've already built.

Now, we’re making it even easier to deploy and manage your agents on Cloudflare. Cloudflare Agents brings all of your deployed agent sessions into a single experience, surfacing key information and insights into how your agents perform at scale.

First stop: agent tracing

We are launching agent tracing for more direct visibility and insight into agent behavior. With agent-aware traces, you can now understand exactly what your agent is doing and what it costs: every model call, tool execution, and token is measured and presented here. Agent tracing launches today with support for OpenTelemetry-compatible agent harnesses including Think, Flue, and AI SDK, and more.

Agent traces are just the beginning. Once you have observability into your agent’s thought process and real-world behavior, you can start to Continue reading

How we built a software factory to drive Astro’s GitHub issue count to zero

Everyone is talking about software factories: the idea that AI agents can be assembled into a pipeline that produces working software on their own, the way a factory turns raw materials into finished goods. There’s endless debate over whether that’s actually possible, how far the automation can really go, and whether the “loops” people are demoing count for anything. Some have already written them off as a failure.

Running alongside that is a quieter, more worried conversation: open source maintainers are burning out. The AI boom has made it nearly free to generate issues, pull requests, and security reports, and enormously expensive for a maintainer to read through them all. The old ways of keeping a project healthy are buckling under the volume.

Everyone has a hot take on both topics. We think we have something rarer to offer: real results. For the past several months we’ve run an automated triage pipeline on the Astro repository. It reads incoming bug reports, reproduces them in sandboxes, diagnoses the root cause, and ships preview releases for the reporter to verify. The engine underneath it grew into Flue, an open framework for building this kind of agent automation, and it’s the same Continue reading

Announcing Cloudflare Wallets: the programmable wallet for the agentic Internet

Today, it is difficult for AI agents to try out new APIs. They often have to navigate through a login page designed for humans and not agents, contact a human to add a payment method, generate an API key, and then figure out how to call the API.

This flow is very difficult for agents for two reasons: Agents do not have a stable identifier to sign up for an API, and they do not have a native way to pay for APIs. Because they lack these things, they often struggle to onboard onto software, which limits the growth of agentic commerce. AI agents often give up on these tasks entirely, kicking registration, payment methods, and API key generation back to humans. This makes it very difficult for agents to try out and compare many APIs.

To solve this, we’ve created Cloudflare Wallets. Starting today, you can claim a Cloudflare Wallet handle for your account, which will provide a unique username to help you better connect with merchants. Soon, you will be able to set up and use your Cloudflare Wallet to pay for APIs and content.

Earlier this month, we announced the Monetization Gateway to help Cloudflare customers get Continue reading

Your agent can now debug Workers with local tracing

Starting today, wrangler dev and vite dev automatically capture OpenTelemetry traces for local Worker invocations. When Cloudflare's tooling detects an agent session, it points the agent to the Local Explorer API, a local debugging API where it can query those traces. You do not need to install an SDK, enable tracing, configure your agent, or even mention observability in the prompt.

A prompt can be as simple as:

This builds on years of investment in local development, from introducing Miniflare to making local mode the default in Wrangler 3. Local traces give coding agents structured feedback from that development environment before code is deployed.

Agents discover the Local Explorer API automatically

As part of its normal workflow, an agent starts wrangler dev or vite dev to run and test the Worker. When the development server recognizes a supported coding-agent session, it automatically prints a hint that looks like this:

The Local Explorer is a browser-based interface and REST API for viewing and editing local resource data and querying observability data during development. The API root serves an OpenAPI schema, so agents can discover available endpoints at runtime without hardcoded instructions.

The automatically captured traces are available through a read-only Continue reading

Your agent needs a computer, not a container — introducing @cloudflare/computer

The most capable agents have something simple in common: they are given their own computer to work with.

Coding agents work this way. You give them a filesystem, a shell, tools, packages, and the ability to run code. They inspect the environment, make changes, test their work, and keep going. The computer gives the model a familiar way to act on the world. At Cloudflare, we’re working hard to provide the right primitives on which to build the most capable agents.

Today we’re introducing an early preview of @cloudflare/computer. The @cloudflare/computer package provides an agent runtime where the details and mechanics of what code runs in an isolate, a container sandbox, or a web browser are handled by the platform. Each agent gets a computer, the runtime optimizes for efficiency, and scalability.

We believe that in order to meet the growing demand for compute required by agentic systems we need to look to solutions beyond traditional containerization. 

Changing how agents are built

We’ve seen a subtle evolution of this story over the past six months. At the start of the year, spinning up a container and running an agent inside of it was the norm. In recent months, we’ve Continue reading

Cloudflare Workers and Containers now support inbound TCP connections and gRPC

AI is changing how people interact with computers, and voice is becoming an increasingly important part of that shift. Real-time assistants, AI-powered dictation, and other voice interfaces need low-latency communication between clients, models, and supporting services. Many developers use gRPC, a Remote Procedure Call (RPC) framework built on HTTP/2 and TCP, for this infrastructure.

Ever since Workers launched in 2017, we’ve been expanding their capabilities, including adding the ability to open outbound TCP connections and a JavaScript-native RPC system built on Cap’n Proto. And so as part of Agents Week, we’re extending Workers in the other direction, supporting inbound TCP connections and adding new ways to run gRPC applications on Cloudflare.

Today, we’re announcing:

  • connect(socket) — a new handler in the Workers runtime that lets your Worker directly accept an inbound TCP socket provided by Spectrum (Cloudflare’s ingress proxy for non-HTTP traffic)
  • Full-duplex, bi-directional gRPC from Cloudflare Containers — forward the socket from your Worker to your gRPC server running in a container
  • Workers can serve unary and server-streaming gRPC APIs and call gRPC servers — you write your code using gRPC-web, and Cloudflare automatically converts incoming and outgoing requests to gRPC

We’re introducing this in private beta — Continue reading

Introducing the Billable Usage API: programmatic cost visibility for Cloudflare

Agents Week is about the shift already underway: agents write code, deploy Workers, and provision infrastructure on your behalf. That shift changes what you need to see. If a program is spending money in your Cloudflare account, you need to know what it's spending; throughout the day, per product, in a shape another program can consume. The dashboard is the right answer for humans. It's not the right answer for automation.

So we're launching a new Billable Usage API for self-serve accounts: a single endpoint that returns your account's usage and cost, broken down by product and by service period. It covers every usage-based Cloudflare product on the account, including Workers, R2, D1, Workers AI, Vectorize, Images, and Stream, all with one call. And if you already work in a FinOps toolchain, the column names should look familiar.

You'll get back an HTTP 200 OK with Content-Type: application/json and the usage rows in the response body. Today, usage and cost data are updated daily while we work towards providing more real time data. 

What comes back

Each row in the response is one charge period for one product on your account.

Smaller, faster, safer: running Kimi and GLM at scale

Workers AI runs inference for some of the best open models in the world on GPUs in Cloudflare data centers close to your users. Two of the most capable, and most demanding, are Moonshot's Kimi K-series and Z.ai's GLM. They are large, long-context, mixture-of-experts models, and they are wonderful to use. They are also very hard to serve efficiently because of memory constraints.

We've written before about how we serve large models on Workers AI and about separating the prefill and decode phases of inference to get more out of each GPU. This post looks at three techniques we layer on top of that to fit these models into memory and keep them fast: quantizing the KV cache, compressing the model weights, and, because both of those pack more requests onto shared hardware, protecting the cache those requests share. These optimizations enable us to support more customers at lower costs, with no change in model accuracy.

All our experiments and production traffic are running and benchmarked with SGLang, an open-source inference serving framework. We found that SGLang offers the best performance in the market, and we work closely with the SGLang team to upstream patches and new Continue reading

Workers RPC now works across Python and JavaScript

Two years ago, we introduced Workers RPC, built on Cap’n Proto RPC. This made it possible for Workers to call other Workers and Durable Objects’ methods, return live objects and call their methods, return functions, streams and get all the benefits of a Remote Procedure Call (RPC) system, without defining schemas or adding any dependencies. We called it “JavaScript-native RPC” because it made using RPC feel native to the language.

Last year, we made this work between web browsers and servers, and introduced Cap’n Web.

Now we’re taking it cross-language.

Normally, getting programs written in different languages to talk to each other is complicated: developers usually have to build custom APIs or adopt language-agnostic serialization formats like protobuf, so the two systems can understand each other. The RPC system built into Workers is able to translate across JavaScript and Python without any additional work.

You can now call methods defined in a Python Worker from a JavaScript Worker and vice versa. You can share objects across Python and JavaScript, and call methods on a Python object from TypeScript. It all just works.

If you define a method add() in a Worker written in TypeScript:

…you can simply call Continue reading

1 … 19 20 21 22 23 … 3,914