Agent foundations
Define agentic systems by observable behavior and system structure, not by product labels.
Follow the chapters in order. Each one combines a clear explanation, local illustrations, traceable sources, and runnable examples where code helps.
Module Overview & Outcomes
Section titled “Module Overview & Outcomes”The reader can define an agent, trace a perception-decision-action loop, distinguish deterministic workflows from model-directed agents, identify autonomy levels, and state termination conditions.
Required Concepts & Scope
Section titled “Required Concepts & Scope”Define model, agent, environment, observation, action, goal, and policy. Build a manual loop. Distinguish its internal perceive-decide-act cycle from the external operating workflow sometimes called loop engineering. Compare fixed and model-selected paths. Add autonomy levels, feedback, errors, budgets, and stop conditions.
Published chapters in this section
Section titled “Published chapters in this section”What is an agent
Defines an agent as an autonomous software system combining a reasoning model with tools, environment observations, and goal-directed control loops.
- Distinguish a standalone language model from a complete agent system.
- Identify the core components of an agent: model, environment, goal, policy, actions, and observations.
- Differentiate between rigid deterministic workflows and model-directed autonomous agent loops.
The agent loop
Explains the internal mechanics of the agent execution loop, detailing how models perceive environment feedback, decide actions, and execute tools across iterative turns.
- Trace the step-by-step lifecycle of a single turn in an agent execution loop.
- Differentiate between the inner reasoning cycle and outer runtime wrappers.
- Implement a framework-free agent loop with step budgets, schema validation, and error recovery.
Workflows versus agents
Compares deterministic code-orchestrated workflows with model-directed autonomous agents, establishing clear criteria for when each architectural pattern should be used.
- Classify an AI system as a prompt chain, routing workflow, parallel pipeline, or autonomous agent.
- Select between workflows and agents based on predictability, latency, cost, and task ambiguity.
- Analyze the security and operational trade-offs of giving models control over execution paths.
Goals, policies, environments, and autonomy
Details how agent goals, operational policies, environment characteristics, and autonomy levels interact to govern agent behavior and safety.
- Define agent goals and differentiate declarative end-states from procedural instructions.
- Construct deterministic policies and guardrails that restrict tool capabilities.
- Classify software environments by observability, determinism, dynamism, and continuity.
Run lifecycle and termination
Defines the complete lifecycle of an agent run from initialization to termination, detailing execution states, pause mechanisms, and multi-layered stopping conditions.
- Map the state transitions of an agent run across initialization, execution, suspension, and termination.
- Implement layered stopping criteria including step limits, token budgets, and stuck-loop detection.
- Manage asynchronous pauses, human-in-the-loop approvals, and clean resource teardown.
Security & Threat Model Connections (Pass 2 Preview)
Section titled “Security & Threat Model Connections (Pass 2 Preview)”Link the security preview to threat modeling and end-to-end goal, action, and termination risks.