Learning track · 17 concepts

Agent Systems

Agent loops, tools, memory, MCP, coordination, durable execution, permissions, computer use, and long-running work.

What mastery looks like

This track contains 17 connected concepts rather than an unordered reading list. Mastery means you can move from vocabulary to mechanisms, predict how the system behaves under pressure, and support a design decision with code, measurements, or a failure-recovery exercise. For Agent Systems, use the track description as the boundary: learn enough detail to reason clearly about agent loops, tools, memory, mcp, coordination, durable execution, permissions, computer use, and long-running work.

A useful explanation names the state involved, the operation that changes it, the resource or safety constraint, and the observable signal that tells you whether the mechanism works. Avoid stopping at product names. Compare at least two approaches, state what each optimizes, and identify what breaks first as scale, concurrency, latency, or uncertainty increases.

Suggested study sequence

Start with the core concepts at the top of the list and write a one-paragraph mechanism note for each. Continue through the core concepts by alternating explanation with an executable drill. Treat Agent Loops, Independent Agent Verification, Agent Run Lifecycle, Harness Evaluation as integration work: they should combine earlier mechanisms rather than introduce disconnected facts.

At the end of each session, record one decision you can now make, one failure mode you can now predict, and one unanswered question. Revisit that question through the linked primary sources, then prove the answer in the Playground or a real repository. The track is complete when you can transfer the reasoning to an unfamiliar system, not when every page has been opened.

Roadmaps

Concepts in this track

core

Tool Calling

Letting an LLM invoke functions/APIs via structured calls.

advanced

Agent Loops

The plan → act → observe loop, with memory and stopping conditions.

core

MCP & Integrations

Model Context Protocol hosts, clients, servers, tools, resources, prompts, transports, capability negotiation, and trust.

core

Multi-agent Coordination

Delegation, specialization, shared state, handoffs, arbitration, budgets, and avoiding coordination overhead.

core

Durable Agent Execution

Checkpointed loops, resumable tools, idempotency, leases, event histories, retries, and crash recovery.

core

Browser & Computer-use Agents

DOM and accessibility-tree control, screenshots, visual grounding, action planning, waits, recovery, and confirmation.

core

Repository Instruction Topology

Repository-wide and path-local instructions, precedence, ownership boundaries, and concise executable guidance for coding agents.

core

Agent Environment Contracts

Deterministic bootstrap, dependency and runtime discovery, readiness probes, isolated workspaces, and explicit validation commands.

core

Agent Work State & Handoffs

Versioned goals, plans, checkpoints, evidence, blockers, and next actions that let a new session resume without relying on hidden conversational memory.

core

Agent Scope Control

Bounded task decomposition, allowed edit roots, budgets, change-size limits, and escalation when evidence invalidates the plan.

advanced

Independent Agent Verification

Maker-checker role separation, independent evidence gathering, adversarial review, and acceptance gates that do not trust the producer's self-report.

advanced

Agent Run Lifecycle

Run initialization, leases and heartbeats, progress transitions, budgets, completion evidence, cancellation, escalation, and safe termination.

advanced

Harness Evaluation

Task suites, outcome rubrics, trajectory metrics, cost and latency budgets, ablations, and regression gates for the harness rather than the model alone.