LeetLLM
Tracks
Intermediate25 lessons

Agents and Tool Use

Move from prompting to tool calls, MCP, structured output, code agents, memory, recovery, and human review.

Engineers building coding agents, workflow agents, browser agents, or production tool-use systems.

You can design agent loops with tools, state, recovery policy, evals, and review gates.

  1. 1Prompt Engineering FundamentalsBuild and test grounded prompts with clear roles, few-shot examples, structured outputs, evidence checks, and failure-focused evaluation.Preparation & PrerequisitesEasy18 min
  2. 2Calling LLM APIs in ProductionTurn a grounded prompt into a reliable API boundary with server-side secrets, typed results, bounded retries, safe actions, and useful telemetry.Preparation & PrerequisitesEasy17 min
  3. 3Function Calling & Tool UseBuild a safe tool-calling runtime that validates model requests, executes controlled actions, feeds observations back, and evaluates complete workflows.Applied LLM EngineeringMedium16 min
  4. 4Structured Output GenerationBuild reliable LLM interfaces with JSON mode, structured outputs, schema validation, and grammar-guided decoding.Advanced Agents & RetrievalHard37 min
  5. 5MCP & Tool Protocol StandardsTrace a pinned MCP compatibility session, build a working stdio integration, and apply current deprecation and trust-boundary guidance.Applied LLM EngineeringMedium19 min
  6. 6ReAct & Plan-and-ExecuteCompare ReAct for tightly coupled tool use with Plan-and-Execute for longer workflows with explicit planning and replanning.Advanced Agents & RetrievalHard34 min
  7. 7Context EngineeringMove past fitting tokens into the window and learn context engineering: curate a high-signal working set, package reusable Agent Skills, and build resumable harnesses with durable checkpoints.Applied LLM EngineeringMedium24 min
  8. 8Agent Memory & PersistenceDesign agent memory systems with scoped storage, sourced recall, tenant isolation, and durable checkpoints without letting recalled context authorize side effects.Advanced Agents & RetrievalHard35 min
  9. 9Agent Failure & RecoveryLearn how to implement validation checks, retries, checkpointed recovery, state reconciliation, loop breakers, and graceful degradation when LLM agents hallucinate, stall, or drift from their tools.Advanced Agents & RetrievalHard51 min
  10. 10Prompt Injection DefenseBuild a prompt-injection-resistant agent boundary: quarantine untrusted tool content, validate typed action proposals, require approval, and measure unsafe side effects.Applied LLM EngineeringMedium16 min
  11. 11Responsible AI GovernanceTurn a tool-bearing LLM workflow into auditable evidence: classify its use, own risks, version controls, preserve traces, and gate releases.Applied LLM EngineeringMedium17 min
  12. 12Guardrails & Safety FiltersBuild layered guardrails for prompt injection defense, sensitive-data controls, structured outputs, policy enforcement, and safe tool use.Advanced Agents & RetrievalHard40 min
  13. 13Evaluating AI AgentsEvaluate model-promotion agent runs by final state, observable trace, safety gates, cost, and repeatability, then map private tests to public benchmarks.Applied LLM EngineeringMedium18 min
  14. 14LLM Observability & MonitoringTurn claim-level answer traces into production metrics, actionable alerts, privacy-safe debugging records, and reproducible incident evidence.Applied LLM EngineeringMedium18 min
  15. 15Code Generation & SandboxingBuild code agents that test candidate patches inside bounded sandboxes with runtime evidence and defense-in-depth controls.Advanced Agents & RetrievalHard33 min
  16. 16Computer-Use / GUI / Browser AgentsBuild browser and desktop agents whose proposed clicks and keystrokes remain behind host policy, approval, verification, and sandbox controls.Advanced Agents & RetrievalHard28 min
  17. 17Human-in-the-Loop Agent ArchitectureBuild approval gates, durable checkpoints, and guarded resumes for agent actions that change external state.Advanced Agents & RetrievalHard36 min
  18. 18AI Coding Workflow with AgentsScope coding-agent tasks, isolate execution, keep patches on branches, verify behavior, and preserve human merge ownership.Advanced Agents & RetrievalHard26 min
  19. 19Multi-Agent OrchestrationMaster multi-agent orchestration with LangGraph, AutoGen teams, and OpenAI handoffs. Learn DAG-style routing, typed shared state, protocol boundaries, and human-in-the-loop controls for reliable AI systems.Advanced Agents & RetrievalHard43 min
  20. 20Design an Automated Support AgentAssemble a stateful support agent that grounds replies, gates credit actions, preserves gateway policy, and hands difficult cases to humans.Applied LLM EngineeringMedium21 min
  21. 21Model Versioning & DeploymentTurn an evaluated LLM change into an immutable release bundle, promote it through measured traffic, and roll back without losing lineage.Applied LLM EngineeringMedium19 min
  22. 22Capstone: Document QAShip a policy-evidence service with controlled admission, cited answers, abstention, replayable eval rows, and source-bound semantic adjudication.Portfolio CapstonesHard36 min
  23. 23Capstone: Eval DashboardBuild a release dashboard for document QA that turns replayable evidence rows into exact-coverage gates, uncertainty checks, and inspectable decisions.Portfolio CapstonesHard22 min
  24. 24Capstone: Fine-Tuned ClassifierTrain and gate an access-ticket encoder that exports exact-receipt evidence and safe intake decisions to a production agent.Portfolio CapstonesHard24 min
  25. 25Capstone: Production AgentAssemble classifier intake, cited policy evidence, approval-gated actions, and episode release tests into a production agent.Advanced Agents & RetrievalHard21 min