Coding agents promise to revolutionize software development, but how do we know if they're any good at the kind of work enterprise teams do every day? SWE-bench, a benchmark for evaluating large language models (LLMs) on real-world software issues, established the...
Evaluating local large language model (LLM) performance before scaling to enterprise production doesn't require complex infrastructure. With Red Hat Enterprise Linux (RHEL) and Red Hat AI Inference, you can launch, benchmark, and test an OpenAI-compatible server on...
What if your standard-issue CPU infrastructure could serve as a hub for enterprise AI? With the right tools, it can. You can deploy a large language model on CPU inside a container on Red Hat Enterprise Linux (RHEL), query it via an OpenAI compatible REST API, and...
Deploying large language models (LLMs) on enterprise hardware requires a balance of reproducibility, security, and performance. Accurately benchmarking model performance under production-like workloads is both challenging and crucial for optimizing infrastructure...
A primary reason many AI pilot projects fail to reach production is lack of confidence in the security of the systems. One of the most common and pernicious security issues affecting generative AI (GenAI) systems is the prompt injection attack—now listed by OWSAP as...
In multi-agent systems, agents delegate work based on capability declarations. When agents chain autonomously, each routing decision relies entirely on what the target agent claims about itself. But what happens if those declarations are inaccurate? An agent can...
When an AI agent introduces itself to another agent, it hands over a digital identity document called an agent card. Our previous post, "Who's really calling? Securing agent-to-agent communication," discussed whether that card is authentic at runtime. This post...
As AI workflows and agents become more capable, the skills they rely on matter more than ever. Most teams start building AI agent skills organically—a script here, a prompt there—and that's a natural way to get going. But as the number of skills grows, so do the...
OpenClaw is now available on Red Hat Developer Sandbox. One click, one API key, and you get a personal AI assistant running in your own Red Hat OpenShift project. The AI agent never sees your credentials and can’t escape its network sandbox. OpenClaw on Developer...
Successfully getting an AI model up and running in a closed lab environment is one thing. Trying to get that same model to run reliably on remote edge devices is a whole other problem entirely. Any MLOps workflow follows the same cycle: develop a model, package it,...
AI models no longer just read and write text. The latest generation of open source models—Qwen3-Omni, Hunyuan-Image3, MiMo-Audio—can reason across text, images, audio, and video simultaneously, generating rich multimodal outputs from a single prompt. But the...
Key takeaways: The last mile problem is translating a verified zero trust delegation token into credentials that external resources will accept while preserving the permission intersection. This is solved by a credential gateway that validates the token, computes the...
This is the second article in our series on Triton kernel profiling. In our first post, Triton kernel profiling with NVIDIA Nsight tools, we introduced how to profile and optimize custom Triton GPU kernels on NVIDIA hardware. In this post, we focus specifically on...
Key takeaways: The identity plumbing for zero trust delegation is accomplished by wiring three technologies together: SPIFFE for service-to-service cryptographic workload identity (mTLS), AuthBridge via RFC 8693 token exchange to pass user delegation context (JWTs),...
Have you ever felt that every conversation you have with an LLM across sessions feels like starting over from scratch? LLMs have a problem: they have the memory of a goldfish (no disrespect to goldfish intended). This article explores the solution: Agent memory. Agent...
As enterprises look to optimize the total cost of ownership (TCO) of Large Language Model deployment, utilizing existing enterprise CPU infrastructure alongside GPU resources for specific inference workloads has become a strategic initiative. However, infrastructure...
When an AI agent acts on your behalf, how much of "you" should it become? In AI systems, agent impersonation creates security risks by granting overly broad permissions. This post introduces a delegation model using a permission intersection' pattern, ensuring agents...
The gap between what an agent claims and what the platform can verify is a real attack surface, and it grows with every new agent you onboard. As agents increasingly discover and call each other at runtime, protocols like Agent2Agent (A2A) have introduced a useful...
As the number of tools connected to an AI agent grows, JSON Schema definitions become a massive scaling bottleneck. Every tool carries a full schema that gets loaded into the LLM’s context window on every turn. Our tests show that replacing these schemas with a...