Learning track 04

Agent Systems

Study pipeline patterns, tool loops, protocols, orchestration frameworks, and operational agent design.

Guides
6
Sections
46
Cards
210

Suggested sequence

Follow the track or enter where the problem begins.

Every guide is self-contained. The sequence only preserves prerequisite order when one topic depends on another.

  1. 01
    Vol. 01

    LLM Pipeline Patterns

    A comprehensive catalog of steps and tricks for building production systems based on language models. Each pattern is atomically parsed.

    Sections
    10
    Cards
    47
    Open guide
  2. 02
    Vol. 06

    LLM Scaffolding: Tool Calling, Structured Output & Agent Loops

    Full analysis of the orchestration layer over LLM: function calling, JSON schema, constrained decoding, ReAct/CoT patterns, agent cycle, context memory management, error handling and comparison of API providers.

    Sections
    8
    Cards
    27
    Open guide
  3. 03
    Vol. 11

    MCP, A2A & Agent Protocols

    Model Context Protocol (Anthropic, 2024) - architecture, creation of servers in TypeScript and Python, all transports, primitives, security. Agent-to-Agent (Google, 2025) - task model, AgentCard, streaming. Comparison of ecosystem protocols.

    Sections
    7
    Cards
    34
    Open guide
  4. 04
    Vol. 21

    LangChain & LangGraph Under the Hood

    This volume is not about “which framework is more fashionable,” but about the modern architecture of the LangChain Inc. stack. In the current version, `LangChain` is a high level with models, messages, tools, middleware and fast `create_agent`, and `LangGraph` is a low-level runtime for stateful agents: `State`, `Nodes`, `Edges`, `Command`, `thread_id`, `checkpoints`, `interrupts`, replay and long-running execution. Below is how this is really connected and what exactly happens during startup.

    Sections
    7
    Cards
    32
    Open guide
  5. 05
    Vol. 30

    Reasoning Models & Tool Loops

    This volume is about a new layer of LLM engineering: models that know how to spend more inference-time compute on reasoning, and applications that make them alternate with tools. It is important to understand two things at once: what is the reasoning runtime itself and how is the loop model -> tool -> model, where state, budgets, stop conditions and engineering invariants live.

    Sections
    7
    Cards
    35
    Open guide
  6. 06
    Vol. 31

    The OpenClaw Phenomenon and What to Learn from It

    The project started as Clawdbot, was renamed Moltbot on January 27, 2026, and then OpenClaw on January 30, 2026. But the essence of the phenomenon was not in the title. This was a rare case of an open-source LLM product hitting the right intersection of UX, architecture, distribution, and memetics. This volume looks at what decisions it really made, why it went viral, and what lessons to learn from it without copying its mistakes.

    Sections
    7
    Cards
    35
    Open guide
Track complete?Keep a live route into the next relevant area.