Resources.
Everything we've written about building, shipping, and governing AI agents in production — in one place.
Guides
Long-form, opinionated walk-throughs of MCP design, agent governance, and the operational realities of enterprise AI.
Glossary
Clear, quotable definitions of the terms that come up in production enterprise AI conversations.
Blog
Shorter-form writing on deployments, research, and industry patterns worth noting.
Latest guides
The long-form pieces we've written most recently.
Multi-agent orchestration: CrewAI, LangGraph, and Agno compared
CrewAI, LangGraph, and Agno are the three most common multi-agent orchestration frameworks in enterprise deployments today. This guide compares their actual operational properties — programming model, state management, debugging surface, and production readiness — and when a simpler architecture is actually the right call.
AI agents for healthcare: HIPAA-safe architectures that actually ship
Healthcare AI agent deployments live or die on compliance posture, EHR integration, and clinical escalation design. This guide walks through a reference architecture that meets HIPAA obligations and actually ships — what to build, what to avoid, and how to stage rollout.
AI agent governance: a practical guide to writing an agent constitution
An AI agent constitution is the written policy that defines what your agent can and cannot do. This guide covers the structure of a good constitution, how to enforce it at runtime, how to test it, and how to evolve it over time.
Commonly looked up
Definitions for the terms that come up most often in discovery calls.
An AI agent is a software system that uses a large language model to perceive its environment, reason about tasks, and take actions in external systems on behalf of a user.
An AI voice agent is an AI agent that interacts with users through voice — answering inbound calls, placing outbound calls, and conversing in real time.
An AI chatbot — more accurately, an AI chat agent — is an AI agent that interacts with users through text: web chat, WhatsApp, SMS, Slack, Teams, or social messaging.
Retrieval-augmented generation (RAG) is an architecture that grounds a language model's responses in a specific knowledge base by retrieving relevant passages at inference time and conditioning the response on them.
Multi-agent orchestration is the practice of coordinating multiple specialized AI agents to accomplish a task that is too complex or too broad for a single agent.
Constitutional AI is an approach to training and deploying AI systems in which model behavior is guided by an explicit written set of principles — a "constitution" — rather than only by reinforcement from human feedback.