Skip to main contentSkip to footer
Agentic AI
HandbookExamplesMCPAgent rules

The doctrine and tooling standard for production agentic AI systems.

The doctrine and runtime standard for teams building production agentic AI systems — 10 principles, 96+ implementation examples, runtime architecture guides, public MCP endpoint, and installable agent rule files for Claude Code, Cursor, Codex, Windsurf, GitHub Copilot, and more.

Join the waitlistFor agents

Key Facts

For
Product designers, PMs, founders, AI builders, and engineers shipping agentic systems
Handbook
10 principle pages connected to implementation examples and runtime architecture patterns
Learning
2 course pages with linked labs and implementation references
Practice
96 implementation examples mapped to principles, runtime patterns, and problem types
What does this platform help a team do?

It helps teams understand the doctrine, study working implementations, and apply the principles to real product decisions. Courses, readiness review, and certification launch with the full platform.

Learn the operator-to-supervisor shift and the ten core principles
See real examples of orchestration, tool use, approvals, retrieval, and background execution
Prepare your own product or workflow for review, evidence, and certification — available at launch
How should someone use the site?

Start with principles to build a shared language, then study examples for concrete implementation evidence. Structured courses, labs, and certification are available at launch.

Start with principles if you need a shared language for trustworthy agentic behavior
Move to examples when you need concrete implementation patterns and technical evidence
Join the waitlist to be notified when courses, review, and certification open

Personalized activation

Do not start from the generic path. Surface your context first and let the platform prepare the right route.

Activation turns a small set of structured signals into a concrete next step. If you are here to figure out what to do next, this is the fastest useful shortcut: it routes you into learning, build, runtime, or review based on your actual situation.

Match the journey to your current stage
Avoid irrelevant pages and patterns
Get an operational route in minutes
Start activationOpen overview
Study working implementations

Level 1: Augmented LLM — Single API Call

One model call with structured output, system prompt, and context. No loops, no tools.

Level 2: Prompt Chains & Routing — Deterministic DAGs

Multiple LLM calls in a fixed sequence. Code controls the flow, not the model.

Level 3: Tool-Calling Agent — Scoped Autonomy

The agent decides which tools to call and in what order, but only within a fixed set of well-defined capabilities.

Level 4: Agent Harness — Full Runtime Access

Give the agent a full runtime via the agent runtime SDK. It can search files, read docs, and reason through problems autonomously.

Level 5: Multi-Agent Orchestration — Delegated Autonomy

An orchestrator delegates to specialized subagents defined via the agent runtime SDK. Each subagent has its own prompt, tools, and model. The orchestrator coordinates.

Intelligence: The "brain" that processes information and makes decisions using LLMs.

This component handles context understanding, instruction following, and response generation.

Runtime architecture

From agent demos to runtime discipline

A capable model is not a runtime architecture. If agents are going to trigger workflows, load files, use tools, delegate work, and act across channels, the runtime needs clear patterns for control, visibility, and recovery. This cluster helps teams design those patterns deliberately.

Define triggers, context, and boundaries before increasing autonomy
Make control, observability, and recovery explicit in the runtime
Choose the right operational patterns before delegating to workflows
Explore runtime patternsOpen principles