28 posts · 5 companies · newest first
AI agents have rapidly become a new kind of software consumer. Where traditional applications analyze and recommend, autonomous agents can now interpret goals, make decisions, find tools, and take actions. Through API integrations and interactions, agents can coordinate actions across a range of systems and chain together their own workflows that might initially seem fairly ...
Ahead of her Nordic APIs Summit 2026 talk on API standards for agents, TM Forum’s Lorna Mitchell joins us to talk about how — or whether — agentic has changed what good API design looks like. There are those who believe that the rise of agentic API consumption will change what software development looks like ...
41 experiments in 6 days took LoCoMo memory from F1 0.392 to 0.666. Claude wrote the code; the human caught the metrics that were lying.
Not every message you send to Claude Code needs the most capable model. A quick question about a Git command runs on the same model as a refactor across three services, unless you remember to switch models first. Jev, a new model from TypeSafe AI, can make that decision for you in a few hundred milliseconds and for a fraction of a cent. So I built jev-router, an open source router that asks Jev which Claude model each of your messages needs, and sends it there. What Jev is After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?I’ve spent the last 2…
Pulumi Neo works on infrastructure the way an engineer does: it clones repositories, edits files, installs dependencies, runs previews, and produces intermediate work along the way. A task is not only a conversation with a model. It is also a working directory that has to survive long enough for the agent to keep making progress. Imagine asking an agent to upgrade a Pulumi provider version across a repository, regenerate SDK code, run previews and tests, inspect the failures, and open a pull request. Halfway through, the runtime restarts. Conversation replay can recover what the agent said…
The new AG-UI .NET SDK enables .NET services to expose and consume interoperable agent endpoints using Microsoft.Extensions.AI. The post AG-UI Protocol now has a first-class .NET SDK appeared first on .NET Blog.
It’s been a weirdly great time to be building software. We’ve never had so many tools that help us get things done: endless cloud providers, regions, deployment frameworks, and now AI agents that can actually build and manage infrastructure for us. That’s part of what made this past week feel so big. TypeSafe AI opened early access to Jev, their SystemOne model, and we here at Pulumi were bitten by the excitement bug and got straight to work building. Almost immediately we were able to whip up some test agentic workflows that were making real, live decisions about infrastructure. If you’re…
Non-determinism is a concept that has existed for decades. However, it has rarely been a central part of software design — until the rise of large language models (LLMs). These models enable developers to build probabilistic AI applications, such as autonomous AI agents. Traditionally, developers build deterministic software that initiates concrete, repeatable actions, where they ...
The age of AI is firmly upon us — and as more teams adopt artificial intelligence and agentic flows, providers are increasingly finding that their old strategies and approaches need to shift. One area where this is rapidly becoming a concern is in the domain of developer portals. Developer portals were built around a very ...
In May I told you to trim the root instruction file until it fits on one screen. I also said anything that needs a hard guarantee belongs in a hook. In June I argued that the model that wrote the code shouldn’t be the one grading it. Several papers published this summer tested related questions. Most of the findings support that advice, while the research on subagent costs calls for more caution. Below are ten tips for working with any coding agent. Each one is checked against what the research measured, which is sometimes narrower than the abstract suggests. Instructions kept only in chat…
AI agents are quickly rising in the enterprise. They’re granting more powers to knowledge workers across sales, finance, engineering, marketing, and other disciplines in the process. Yet, as most quick technological adoptions go, security is often falling by the wayside or being implemented after the fact. Ahead of Nordic APIs Summit 2026, we’re connecting with ...
For over two decades, API design and architecture remained remarkably consistent. Perhaps it’s the outsized influence of Roy Fielding’s RESTful dissertation, but API designers have stuck to the principles of stateless architecture, resource-based endpoints, and HTTP commands to an impressive degree. That’s all starting to change, now that we’ve radically recontextualized the way we use ...
A rewrite this size wasn't affordable before agents. Here's what porting the Copilot agent runtime to 800,000 lines of production Rust actually took. The post Migrating the GitHub Copilot runtime to Rust, using Copilot appeared first on The GitHub Blog.
Ahead of Nordic APIs Summit 2026, we catch up with speaker Claire Barrett on the mindset shift needed for adopting AI-enabled strategies. “Imagine driving around an old town,” responds Claire Barrett when asked to describe what it means to be AI-ready from an integration perspective. “Imagine a European city that’s been inhabited for thousands of ...
Traditional monitoring tools, such as application performance monitoring (APM), were engineered to monitor deterministic software where specific inputs reliably lead to predictable outputs through hard-coded logic. When a traditional API fails, it usually throws a 500 Internal Server Error. But when an AI agent fails, it might return a perfectly healthy 200 OK status code ...
Ahead of his Nordic APIs Summit 2026 talk on API coherence, London Stock Exchange Group’s Gareth Faull joins us to talk about the art of aligning APIs with organizational intent. Measuring the performance of an API is a relatively straightforward process: ensure observability is in place, follow governance best practices, measure uptime, track usage statistics, ...
Giving an AI agent unrestricted database access isn't safe. Scoped, read-only, database-enforced access can be. See the framework and guardrails.
The latest release of the Model Context Protocol (MCP) specification has created a lot of buzz in tech circles. Why? Primarily because this AI communication protocol has now gone stateless! This shift from stateful to stateless impacts how developers of MCP servers and AI tools use the protocol moving forward. In addition, the change impacts ...
How Uno Platform built two Model Context Protocol servers in C# so AI agents can ground themselves in real documentation and then see and drive a running cross-platform .NET app. The post How Uno Platform uses .NET, MCP, and AI to build high quality apps appeared first on .NET Blog.
In May 2026, Cloudflare released a new tool called isitagentready.com. It analyzes a URL for everything an agentic AI would need to interact with a site and then returns a score out of 100. Even better still, it breaks down its assessment by category, letting you know how your site performs for discoverability, accessibility from ...
Every platform team fields the same questions: What is running? What breaks if we change this? What can we safely delete? The answers exist, but they’re scattered across state files, cloud consoles, and the memories of whoever set things up. Today we’re launching the Pulumi Context API, a read-only API that connects Pulumi-managed and discovered resources, stacks, and their relationships into a graph. It’s designed agent-first: Pulumi Neo, our infrastructure agent, uses it out of the box, and other agents can fetch the current graph vocabulary and query guidance on demand. It’s available in…
Over the last decade, enterprises invested heavily in API infrastructure. They purchased API management platforms, deployed gateways across business units and regions, built developer portals, introduced security and observability tools, and encouraged teams to adopt API-first development. The business case was compelling. APIs would make enterprise capabilities easier to reuse, shorten integration timelines, improve partner ...
APIs are like the backstage crew of the digital economy. They’re not front and center, but they’re essential for putting on a show. Yet, from a business perspective, APIs have traditionally been regarded as a form of “operational plumbing,” with many enterprises treating them as technical infrastructure rather than strategic assets. However, companies like Stripe, ...
Claude Code calls the flag --dangerously-skip-permissions, and the community long ago renamed it YOLO mode. It lets your coding agent run any command it wants without ever asking for permission. Every agent has some version of it, Codex and Cursor included, and if you use these tools seriously, you are probably running one of them every day. I am. YOLO mode is also what makes a coding agent worth having. An agent that stops for approval before every command is not autonomous; it’s a slow pair programmer. But you cannot let it run wild on your machine without real guardrails either. You have…
In a 2018 Forbes article, Jedidiah Yueh and Randy Bean argued that every company is now a data company. “Leveraging data — in an ethical manner — has to be at the heart of your company and product strategy,” they wrote. “Collect, sift, then monetize.” Just shy of a decade later, virtually every company (in ...
Kubernetes has become the default place teams run agentic AI workloads: CNCF’s 2026 annual survey found that 66% of organizations hosting generative AI models use Kubernetes to manage some or all of their inference workloads.1 An entire ecosystem has grown up around that fact — agent runtimes, model servers, GPU schedulers — and most of it assumes the infrastructure underneath is already handled. It usually isn’t. An AI agent is not a stateless web service, and provisioning for one takes more than copying a Deployment YAML and swapping the image. I spend a lot of my time these days thinking…
A recent report from Salt Security published a truly alarming statistic. According to the report, 95% of API attacks come from authenticated sources. This should raise alarms for anyone who knows anything about cybersecurity, as it means API attacks are seemingly real transactions. These attacks won’t even be noticed by average cybersecurity systems, as, for ...
Five weeks ago I wrote that the least glamorous piece of an agent loop is also the one that decides whether it compounds: memory. A markdown file outside the context window that holds what is done, what is next, and what was learned, because the model forgets all of it between runs. Write the memory file before the loop. What I left open, because there was nothing to point at, was the format. My memory file looked nothing like yours, and neither of our agents could read the other’s. Three days after that post went live, Google shipped an answer. The pattern everyone copied Andrej Karpathy…