Generative AI Insights, an InfoWorld blog open to outside contributors, provides a venue for technology leaders to explore and discuss the challenges and opportunities presented by generative artificial intelligence. The selection is wide-ranging, from technology deep dives to case studies to expert opinion, but also subjective, based on our judgment of which topics and treatments will best serve InfoWorld’s technically sophisticated audience. InfoWorld does not accept marketing collateral for publication and reserves the right to edit all contributed content.
Golden paths gone gray? Avoid these common mistakes that sink platform engineering initiatives.
AI agents trained on their own experiences have the potential to revolutionize operations. Practical applications are already emerging.
Eventually the industry will develop predictable patterns, trusted standards, and robust governance for autonomous agents. How do we secure agentic AI in the meantime?
AI is increasing both the number of pull requests and the volume of code within them, creating bottlenecks in code review, integration, and testing. Here’s how to address them.
Understand the merits of large language models vs. small language models, and why knowledge graphs are the missing piece in the equation.
Familiar patterns—and familiar lessons—are emerging as enterprises get serious about agentic AI and Model Context Protocol and Agent2Agent implementations.
Modular orchestration, fail-safe design, hybrid memory management, and LLM integration with domain knowledge are essential to agentic systems that reason, act, and adapt at scale.
A community-driven effort is bringing native support for AI inference to Kubernetes, featuring the vLLM library, an inference gateway extension, inference benchmarks, and more.
Autonomous systems are quietly changing the way we work. Bigger benefits will come when businesses redesign their workflows with agents at the center.
Researchers are racing to develop more challenging, interpretable, and fair assessments of AI models that reflect real-world use cases. The stakes are high.
Model Context Protocol makes it far easier to integrate LLMs and your APIs. Let’s walk through how MCP clients and servers communicate, securely.
Consider these six ways to approach AI to help your organization unlock efficiencies while preventing major setbacks and significant cost overruns.
An introduction to the open-source LMOS platform and its Kotlin-based Arc framework for building, deploying, and managing cloud-native, multi-agent AI systems.
Large language models can generate useful insights, but without a true reasoning layer, like a knowledge graph and graph-based retrieval, they’re flying blind.
Model Context Protocol, Agent2Agent protocol, and Agent Communication Protocol take slightly different approaches to AI agent communications. Let’s unpack them.
Organizations gain a strategic advantage with a life-cycle approach to AI cyber risk that acknowledges the rapid evolution of AI technologies, threats, and regulations. Here’s how.
Getting retrieval-augmented generation right requires a deep understanding of embedding models, similarity metrics, chunking, and retrieval techniques. Here’s a brief guide.
An agentic mesh is a way to turn fragmented agents into a connected, reliable, enterprise-grade ecosystem. It lets agents find each other, and safely and securely collaborate, interact, and even transact.
Most organizations lack the foundational infrastructure needed to deploy AI agents effectively, with fragmented knowledge access and security concerns the biggest barriers.
Large language models and small language models will play different roles in ensuring that we deliver valuable generative AI applications at cost-effective levels.