Living knowledge mapReviewed Jul 26, 2026

From a rough idea to a production agent system.

Explore the full lifecycle: agents, Skills, architecture, design, specifications, plans, tasks, memory, context, tools, multi-agent work, evals, safety, operations, governance, commerce, and more. Every topic exposes its decision rule, artifacts, questions, and primary evidence.

21

maintained topics

27

unique primary sources

7 days

new brief cadence

Content engine

New regularly. Updated carefully.

Automation checks official sources, validates every topic, and rotates six topics into a new source-linked brief each week. If a source breaks or the review window expires, publishing stops and a review issue opens instead of silently generating unsupported claims.

  1. 01

    Check sources

    Verify review age, structure, internal routes, and live primary documentation.

  2. 02

    Publish a rotation

    Create a deterministic weekly brief from six reviewed topics and their evidence.

  3. 03

    Block stale content

    Open a review issue and fail the workflow when evidence or freshness needs attention.

Topic library

Follow the lifecycle or jump to a decision.

Foundations

What the system is and how its responsibilities are divided.

Delivery

How intent becomes designs, specifications, plans, and tasks.

Runtime

How context, tools, agents, protocols, and workflows execute.

2 sources

Memory and context

Context is the information available for the current inference; memory is persisted state that may shape later runs. Reliable systems separate conversation history, durable facts, user preferences, project policy, and derived summaries so each can be governed and refreshed appropriately.

Read the field guide
2 sources

Context engineering

Context engineering controls which instructions, examples, tools, retrieved facts, messages, and summaries reach the model at each step. The objective is not maximum context; it is the smallest current set that makes the desired behavior likely and reviewable.

Read the field guide
2 sources

Tools and MCP

Tools let models request deterministic functions; MCP standardizes how compatible hosts discover and call external tools, resources, and prompts. Good tool design minimizes ambiguity, constrains inputs, makes side effects visible, and returns results the model can interpret reliably.

Read the field guide
2 sources

Multi-agent systems

Multi-agent systems divide work among specialized or isolated agents and synthesize their outputs. They are valuable when work partitions cleanly or trust boundaries differ, but they add coordination, context transfer, conflict resolution, and observability costs.

Read the field guide
2 sources

Agent interoperability

Interoperability allows hosts, tools, and independently operated agents to discover capabilities and exchange work through explicit contracts. MCP primarily connects models to tools and context; A2A primarily coordinates agents and task artifacts across service boundaries.

Read the field guide
2 sources

Workflows and automation

Workflows encode known control paths; automations trigger those workflows on a schedule or event without continuous human initiation. Reliable automation requires idempotency, retry policy, durable state, ownership, observability, and a clear boundary for escalation.

Read the field guide

Operations

How quality, telemetry, releases, and recovery stay accountable.

Governance

How authority, safety, review, and organizational policy are enforced.

Ecosystem

How models and transaction protocols connect the wider market.

Weekly source-linked publishing

Follow new rotations in the AgentAtlas feed.