Agentic Engineering Roadmap

You can design, test, and debug a service with clear interfaces, handle errors deliberately, and reason about state, concurrency, and failure. Agents are ordinary distributed systems with a probabilistic component; the ordinary discipline still applies.

You are fluent in at least one of the two languages the ecosystem is built in: typing (Pydantic / Zod), async, packaging, and reading library source when the docs run out.

You can call HTTP/JSON APIs with authentication, streaming, timeouts, retries with exponential backoff, and rate limits, and you can run independent calls concurrently without corrupting shared state.

You can explain tokens, context windows, temperature, and why model output is probabilistic, and you can place a problem on the ladder from plain code to multi-agent before writing any of it.

• What Is Agentic AI?Not startedLearningPracticingMastered
• Choosing the Right AbstractionNot startedLearningPracticingMastered

You can construct the exact set of information a model sees on each call, stay inside a token budget, and know why placing a critical fact in the middle of a long prompt reduces the chance it is used.

• Context EngineeringNot startedLearningPracticingMastered
• Context Selection & CompressionNot startedLearningPracticingMastered
• Context Ordering & Lost in the MiddleNot startedLearningPracticingMastered
• Token BudgetsNot startedLearningPracticingMastered
• Dynamic Context AssemblyNot startedLearningPracticingMastered

You can force a model to return schema-conformant JSON, validate it at the boundary, and handle the case where validation fails instead of trusting the shape of the text.

• Structured OutputsNot startedLearningPracticingMastered
• Argument ValidationNot startedLearningPracticingMastered

You can define tool schemas the model selects correctly, validate arguments, handle errors, timeouts, and retries, make side effects idempotent, and grant each tool the minimum permissions it needs.

• Tool Calling BasicsNot startedLearningPracticingMastered
• Tool SchemasNot startedLearningPracticingMastered
• Argument ValidationNot startedLearningPracticingMastered
• Tool Errors, Retries and TimeoutsNot startedLearningPracticingMastered
• IdempotencyNot startedLearningPracticingMastered
• Parallel vs Sequential Tool CallsNot startedLearningPracticingMastered
• Tool Permissions and Least PrivilegeNot startedLearningPracticingMastered

You can build the full retrieval pipeline (chunking, embeddings, storage, hybrid retrieval, reranking, grounding with citations) and measure retrieval quality separately from answer quality.

• RAG OverviewNot startedLearningPracticingMastered
• Ingestion: Parsing & ChunkingNot startedLearningPracticingMastered
• EmbeddingsNot startedLearningPracticingMastered
• Vector StorageNot startedLearningPracticingMastered
• Dense, Sparse & Hybrid RetrievalNot startedLearningPracticingMastered
• Metadata FilteringNot startedLearningPracticingMastered
• RerankingNot startedLearningPracticingMastered
• RAG EvaluationNot startedLearningPracticingMastered

You can implement the observe-reason-act loop without a framework, choose between direct execution, plan-then-execute, and ReAct, and know when planning only adds latency and cost.

• The Agent LoopNot startedLearningPracticingMastered
• Single AgentNot startedLearningPracticingMastered
• Agent + RAGNot startedLearningPracticingMastered
• Planning StrategiesNot startedLearningPracticingMastered
• When Planning HelpsNot startedLearningPracticingMastered

You can separate context, short-term, and long-term memory, decide what deserves persisting, and explain why storing more makes agents worse rather than better.

• Memory TypesNot startedLearningPracticingMastered
• Memory ArchitecturesNot startedLearningPracticingMastered
• Memory PitfallsNot startedLearningPracticingMastered

You can build and consume an MCP server, explain tools, resources, and prompts, handle the connection lifecycle and auth, and argue when a direct integration or plain function calling is the better choice.

• MCP OverviewNot startedLearningPracticingMastered
• MCP Primitives: Tools, Resources, PromptsNot startedLearningPracticingMastered
• MCP Lifecycle: Init, Discovery, InvocationNot startedLearningPracticingMastered
• MCP vs Direct Integration vs Function CallingNot startedLearningPracticingMastered

You can model a multi-step process as an explicit state graph with checkpoints and routing, and can articulate why a deterministic workflow beats an open-ended agent for most business processes.

• Workflow State GraphNot startedLearningPracticingMastered
• Router ArchitectureNot startedLearningPracticingMastered
• Architecture TradeoffsNot startedLearningPracticingMastered
• What Agentic Engineers BuildNot startedLearningPracticingMastered

You can choose between supervisor, pipeline, hierarchical, and swarm topologies, design the messages agents exchange, and recognise the many cases where a single agent with better tools is the right answer.

• Multi-Agent Systems OverviewNot startedLearningPracticingMastered
• Supervisor ArchitectureNot startedLearningPracticingMastered
• Supervisor PatternNot startedLearningPracticingMastered
• Pipeline PatternNot startedLearningPracticingMastered
• Hierarchical PatternNot startedLearningPracticingMastered
• Swarm / Peer PatternNot startedLearningPracticingMastered
• Agent-to-Agent CommunicationNot startedLearningPracticingMastered
• When Not to Use Multi-AgentNot startedLearningPracticingMastered

You can build a golden dataset, pick metrics that match the failure you care about, combine deterministic evaluators with LLM judges, and run regression evals before every prompt or model change.

• Evaluating Agents: Testing Probabilistic SystemsNot startedLearningPracticingMastered
• Eval Metrics: What to Measure and HowNot startedLearningPracticingMastered
• Golden DatasetsNot startedLearningPracticingMastered
• LLM-as-JudgeNot startedLearningPracticingMastered
• Deterministic EvaluatorsNot startedLearningPracticingMastered
• Regression Gates and Online EvaluationNot startedLearningPracticingMastered

You can trace every LLM call, tool call, and state change as spans, read a trace to find the step where a run went wrong, and alert on token, cost, latency, and error rates.

• Tracing AgentsNot startedLearningPracticingMastered
• Trace Inspection: Debugging from a TraceNot startedLearningPracticingMastered
• Logging, Metrics and AlertsNot startedLearningPracticingMastered

You treat all retrieved and tool-returned content as untrusted data, scope tool permissions to the task, keep secrets out of the context, and put guardrails on both inputs and outputs.

• Security Overview: Guardrails and the Threat ModelNot startedLearningPracticingMastered
• Prompt InjectionNot startedLearningPracticingMastered
• Indirect Prompt InjectionNot startedLearningPracticingMastered
• Tool Misuse and Data ExfiltrationNot startedLearningPracticingMastered
• Permissions, Authentication and AuthorisationNot startedLearningPracticingMastered
• Input and Output GuardrailsNot startedLearningPracticingMastered
• Secrets and Untrusted OutputNot startedLearningPracticingMastered

You can classify actions by risk, insert approval gates where reversibility is low, and design escalation with confidence thresholds so humans review the cases that matter instead of every case.

• Human-in-the-Loop OverviewNot startedLearningPracticingMastered
• Approval Gates and Risk ClassesNot startedLearningPracticingMastered
• In-the-Loop vs On-the-Loop and EscalationNot startedLearningPracticingMastered
• Confidence ThresholdsNot startedLearningPracticingMastered

You can enumerate the ways an agent run fails (loops, overflow, provider outage, drifting arguments) and have a named mitigation for each: budgets, termination criteria, fallbacks, caching, routing.

• Reliability Overview: The Seven Failure ScenariosNot startedLearningPracticingMastered
• Failure Scenarios: Detection and RunbooksNot startedLearningPracticingMastered
• Budgets, Limits and TerminationNot startedLearningPracticingMastered
• Fallbacks, Caching and Model RoutingNot startedLearningPracticingMastered

You can take an agent from demo to production: fallback chains, caching and routing for cost, metrics and alerts, real business-process automation, and a defensible choice of framework or none at all.

• Reliability Overview: The Seven Failure ScenariosNot startedLearningPracticingMastered
• Fallbacks, Caching and Model RoutingNot startedLearningPracticingMastered
• Logging, Metrics and AlertsNot startedLearningPracticingMastered
• Business Process AutomationNot startedLearningPracticingMastered
• Frameworks: What They Abstract and What It CostsNot startedLearningPracticingMastered