The agent development lifecycle

The agent development lifecycle (ADLC) is seven phases an agent goes through, from setting its goal to monitoring it in production. It is the order in which the other notes in this notebook get used.

The phases

1. Goal setting and scoping. Decide what the agent is for, who it acts as, and the guardrails around it (see guardrailsLLM guardrailsChecks around the model, so a bad input or a bad output is caught by something that does not rely on the model behaving.Opens in a new tab and agent principlesAgent design principlesFour properties that make a loop an agent: goal-directed, reactive, stateful, autonomous.Opens in a new tab).
2. Design. Pick the agentic patterns and workflows, and plan the context (see agentic patternsWhy agentic patternsA prompt is a tactic and breaks easily. A pattern is the strategy around it.Opens in a new tab, choosing a multi-agent patternChoosing a patternRouter, handoff, group chat or swarm: what each one trades away.Opens in a new tab, context engineeringContext engineeringDeciding what the model sees on every call, because the window is finite.Opens in a new tab and flow engineeringFlow engineeringDesign the task as a flow of steps: a model where judgement is needed, plain code everywhere else.Opens in a new tab).
3. Framework, model and tool selection. Choose the LLM, the framework and the tools (see tool useTool useFunction calling gives the model hands: it asks, and code does the work.Opens in a new tab, MCPMCPModel Context Protocol: one standard way for an agent to reach tools and data.Opens in a new tab and agent protocolsWhy agent protocolsAgents need a shared language to find each other, say what they can do, and swap context.Opens in a new tab).
4. Build. The dev loop: a context assemblerThe context assemblerThe step that builds the prompt from scratch on every loop.Opens in a new tab, tool integrations and the agentic workflow (see planningPlanningBreak a high-level goal into steps, store the plan, and work through it.Opens in a new tab and ReActReActReason, act, observe, repeat: planning, tool use and a loop in one pattern.Opens in a new tab).
5. Training, optional. Fine-tuning, or tuning the context instead of the model. Many agents never need it.
6. Evaluation. Test for safety, quality and goal adherence (see agent evaluationAgent evaluationTest the flow an agent took and what it left behind, against the goal and the guardrails.Opens in a new tab, test datasetsTest datasets and mock toolsReal scenarios as a dataset, and tests that swap the tools for fakes.Opens in a new tab and LLM as judgeLLM as judgeA second model scores the result against written criteria.Opens in a new tab).
7. Deployment and monitoring. Watch token cost, latency, tool call failures, user feedback and hallucination rate (see agent opsAgent opsAfter deployment, watch performance, safety and cost, and whether the agent is thinking straight.Opens in a new tab, traceabilityTraceabilityLog the whole reasoning trace, so any answer can be explained afterwards.Opens in a new tab and agent metricsAgent metricsSix numbers that say whether a deployed agent is healthy.Opens in a new tab).

A loop, not a line

The last phase feeds the build. LangChain describes the lifecycle as build, test, deploy and monitor, and the order is intentional: testing starts before production, not after, and monitoring is what turns real failures into the next round of tests. Other write-ups group the work differently, but they keep that order.

Anthropic’s advice sits over all of it: keep the design simple, and add complexity only when it demonstrably improves outcomes. Phases 6 and 7 are how that gets measured. Where a phase leans on a person in the loopHuman in the loopA pause in the agent's decision, where a person approves before a high-risk action runs.Opens in a new tab or a secured toolSecure toolingTools are where an agent touches the world, so each one is described, versioned and watched.Opens in a new tab, the safety notes cover it.