Skip to content
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 an incident-triage prompt with clear roles, useful examples, structured outputs, evidence checks, and a separate authorization boundary.Preparation & PrerequisitesEasy14 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 & PrerequisitesEasy28 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 EngineeringMedium27 min
  4. 4Structured Output GenerationBuild reliable LLM interfaces with JSON mode, structured outputs, schema validation, and grammar-guided decoding.Advanced Agents & RetrievalHard36 min
  5. 5MCP & Tool Protocol StandardsTrace stateless MCP requests, test a local stdio tool, and separate connection health, protocol validity, and permission.Applied LLM EngineeringMedium23 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 & RetrievalHard62 min
  7. 7Context EngineeringCurate the evidence, tools, and notes in each model request. Test token budgets, package reusable Agent Skills, and resume work from checked artifacts rather than status claims.Applied LLM EngineeringMedium24 min
  8. 8Prompt 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 EngineeringMedium28 min
  9. 9Responsible AI GovernanceTurn a tool-bearing LLM workflow into auditable evidence: classify its use, own risks, version controls, preserve traces, and gate releases.Applied LLM EngineeringMedium31 min
  10. 10Guardrails & Safety FiltersBuild layered runtime guardrails for prompt injection, sensitive-data controls, structured outputs, policy enforcement, and safe tool use.Advanced Agents & RetrievalHard59 min
  11. 11Evaluating 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 EngineeringMedium31 min
  12. 12LLM Observability & MonitoringConnect answer-quality checks to latency, cost, traces, and actionable alerts without confusing missing evidence with a healthy service.Applied LLM EngineeringMedium31 min
  13. 13Code Generation & SandboxingBuild code agents that repair programs from runtime evidence while keeping untrusted execution separate from host authority and grading.Advanced Agents & RetrievalHard26 min
  14. 14Computer-Use / GUI / Browser AgentsBuild browser and desktop agents whose proposed clicks and keystrokes stay behind host policy, approval, verification, and sandbox controls.Advanced Agents & RetrievalHard49 min
  15. 15Human-in-the-Loop Agent ArchitectureBuild approval gates, durable checkpoints, and guarded resumes for agent actions that change external state.Advanced Agents & RetrievalHard50 min
  16. 16AI Coding Workflow with AgentsTurn coding tasks into bounded agent work with restricted execution, review branches, before-and-after evidence, and human-owned merge decisions.Advanced Agents & RetrievalHard32 min
  17. 17Agent Memory & PersistenceKeep coding-agent context across sessions with scoped stores, sourced recall, and checkpoints, without letting a recalled note authorize a merge.Advanced Agents & RetrievalHard54 min
  18. 18Agent Failure & RecoveryRecover from invalid proposals, lost replies, stalled plans, and dependency outages without duplicating actions or inventing success. Build and fault-test the runtime boundaries.Advanced Agents & RetrievalHard30 min
  19. 19Multi-Agent OrchestrationDecide when multiple agents earn their cost, then orchestrate them with typed shared state, parallel reads, a validated merge, and one approval-bound writer.Advanced Agents & RetrievalHard35 min
  20. 20Design an Automated Support AgentKeep invoice facts, policy evidence, draft generation, credit authorization, and human handoff separate in a runnable support workflow.Applied LLM EngineeringMedium38 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 EngineeringMedium31 min
  22. 22Capstone: Document QABuild an approved-policy lookup, test citations and refusals, and trace source-bound reviews through a research-job simulation.Portfolio CapstonesHard52 min
  23. 23Capstone: Eval DashboardBuild a document QA dashboard that exposes unsafe citations, checks comparable rows, and keeps display filters out of release gates.Portfolio CapstonesHard35 min
  24. 24Capstone: Fine-Tuned ClassifierFit a ticket classifier, compare held-out baselines, and check labels, thresholds, scoring evidence, and agent intake.Portfolio CapstonesHard44 min
  25. 25Capstone: Production AgentBuild and test an agent runtime with fixture-based intake and evidence, bound tool calls, durable local approvals, and execution-derived evaluation rows.Advanced Agents & RetrievalHard28 min