How to build, run and watch AI agents. Guides, engineering deep dives and product updates from the Rerun team.
The Model Context Protocol (MCP) is the open standard connecting AI apps to tools and data. Learn how MCP works, its architecture, primitives, transports, and security, plus how to run MCP servers safely.
How AI agent memory works: short-term vs long-term, the episodic, semantic, and procedural types, how agents store and retrieve with vector search, how they learn, and how to govern memory in production.
Gartner says 40% of agentic AI projects will be canceled by 2027, mostly over governance. Here are 7 CrewAI alternatives compared on human-in-the-loop, observability, and audit, from frameworks to governed no-code platforms.
What AI agents really cost in 2026: the five pricing models, the hidden token spend that dwarfs the sticker price, and the ROI math to justify buy vs. build.
ReAct agents solve tasks by looping through Thought, Action, and Observation. Here is how the reasoning-and-acting loop works, a real worked example, how it compares to Chain-of-Thought and function calling, and why the raw loop needs a control plane in production.
Learn how to test AI agents that actually work: golden datasets, LLM-as-a-judge, trajectory evals, and the runtime governance that turns testing into reliability.
AI agents can take real work off clinical and admin teams, from scheduling to prior authorization to ambient documentation. The hard part is not the use cases, it is deploying them safely under HIPAA and human oversight. Here is how.
OpenClaw and OpenCode are not really competitors. One is a synchronous coding agent, the other a self-hosted personal assistant. Here is how to choose, when to use both, and how to run either safely in production.
The five core types of AI agents, from simple reflex to learning agents, ordered by autonomy. Real examples, where agentic and multi-agent systems fit, and how to match the type to the job.
Codex writes code on demand. Hermès Agent orchestrates and governs it 24/7. A 2026 decision framework, plus how to drive Codex from inside Hermès.
68% of Realtors use AI, but 46% see no impact. AI agents for real estate qualify leads, book showings, and update your CRM, not just chat. Here's how to deploy governed, compliant agents step by step.
OpenClaw runs autonomous agents; n8n runs visual workflows. Neither ships production governance. Here is how the governed middle ground beats both in 2026.
© 2026 Rerun. All rights reserved.
