Artificial intelligence

Discover how Red Hat OpenShift 5 empowers developers with native AI agent sandboxing, dynamic GPU allocation, and upgraded local-to-cloud developer tooling.

See how the Red Hat Developer Hub intelligent assistant captures screen and DOM context on demand to accelerate debugging while safeguarding private user data.

Learn how to manage Spark resource quotas with Red Hat build of Kueue on Red Hat OpenShift AI to prevent contention and configure self-managed queues.

Learn how to use Claude Code to automate Testing Farm onboarding, generate TMT metadata, and configure multi-environment CI pipelines in GitHub and GitLab.

Learn how to integrate the Jev API for bounded semantic judgments by executing your first call and interpreting confidence scores.

This article explains how dynamic resource allocation (DRA) improves the performance of distributed LLM inference workloads by aligning GPU and network interface topologies. Traditional Kubernetes device plugins often assign GPUs and SR-IOV virtual functions (VFs) that are not on the same PCIe root, causing suboptimal RDMA bandwidth and increased latency for disaggregated architectures like llm-d.

Discover how Atos fine-tuned SLMs on OpenShift AI to outperform frontier models on structured extraction tasks using only 3 GPUs.

Implement LLM tool calling with Apache Camel using bounded loops, ai-tool components, and MCP for security-focused, vendor-neutral enterprise integrations.

Secure MCP gateways in Red Hat OpenShift with gateway isolation, NetworkPolicy, AuthPolicy, and RateLimitPolicy to enforce least-privilege access.

Learn how to benchmark local LLMs with Red Hat AI Inference and Red Hat Enterprise Linux by deploying vLLM and testing performance on your hardware.

This post showcases the agentic-partners-integration AI quickstart, built on Microsoft Azure and Red Hat OpenShift AI (Microsoft Azure Red Hat OpenShift) and integrated with the Microsoft Azure MCP server from the official MCP catalog. Learn how agents share context, orchestrate actions, and automate resolution.

Dive into the Q3’26 edition of Camel integration quarterly digest, covering the

Learn how to use Jev for bounded semantic judgments on messy text, returning typed probabilities to help you build reliable decision models.

Learn how the quickstart integrates LangGraph state machines, knowledge bases, and MCP tools to enable seamless agentic ticket resolution.

Learn how to choose between vLLM and SGLang for production LLM inference by comparing PagedAttention, RadixAttention, and independent benchmark results.

Deploy AI-driven people matching on Red Hat OpenShift with PeopleMesh, using Docling and LLMs to automate profile creation from resumes.

Set up MCP servers for Red Hat Lightspeed, Satellite, and RHEL using goose, and learn key operational lessons on LLM token limits and API budgets.

Learn how Red Hat built IdeaBot on OpenShift using isolated pods, auth proxies, and EARS-based BDD to secure and automate internal AI research.

Learn how Rossoctl manages agent security and observability on Red Hat OpenShift using A2A, SPIRE, and MLflow to prevent agent sprawl and enable zero trust AI.

Learn how to add NeMo Guardrails to LangGraph agents on Red Hat OpenShift AI using a proxy pattern to inspect requests without modifying agent code.

Compare Jev decision models with Red Hat guardrails to evaluate AI safety performance, cost, and latency for enterprise implementation.

Learn how to manage GPU quotas with Kueue and DRA on Red Hat OpenShift to enable fair sharing and accurate device-level accounting for AI workloads.

Learn how to test AI agent skills with skill-creator and promptfoo to prevent silent misfires and ensure reliable trigger behavior in CI pipelines.

Learn how to secure LLM supply chains by implementing behavioral probing and provenance verification to detect backdoors that evade standard model scanning.

Learn how to simplify distributed training with Kubeflow Trainer 2 on OpenShift AI by replacing framework-specific CRDs with a unified TrainJob resource.