Methodology · Agent Constructionemergingneeds-verification

Agent Architecture Decision Ladder

also known as four-step architecture ladder, least-powerful-architecture rule

Applies to: agentmulti-agent-systemllm-app

Tags: architecturedecision-ladderleast-powerful-architecturestep-selection

Pick the agent architecture from a four-step ladder. The steps are: a plain model call, a single agent, a fixed multi-agent workflow, and an autonomous multi-agent system. Pick the lowest step that solves the task. This forces a choice you can defend, instead of jumping straight to an autonomous multi-agent system out of habit. Treat architecture as a cost-versus-benefit call, with clear criteria at each step.

Methodology process overview

Intent. Make the architecture choice a deliberate climb up a four-step ladder, backed by evidence, picking the lowest step that solves the task, instead of defaulting to an autonomous multi-agent system.

When to apply. Use this at project kickoff, before any architecture is built, and again at every big capability change that might push you up a step. Don't apply it when the architecture is fixed for you, such as a vendor mandate or an existing framework that already locks the step. Skip it too when the team has no habit of measurement. Without evals to compare steps, the ladder is just opinion.

Inputs

  • Task profileWhat kind of task it is: text generation, taking actions, structured teamwork, or open-ended exploration.
  • Determinism requirementHow much variation the stakeholders will accept in the agent's behaviour and output.
  • Cost and latency budgetThe limits per task: tokens, infra spend, and total response time.

Outputs

  • Architecture decisionThe chosen step, with the reasoning written down. It is one of: plain model, single agent, fixed multi-agent workflow, or autonomous multi-agent system.
  • Escalation triggersThe named conditions that would justify climbing to the next step later.

Steps (6)

  1. Profile the task on the ladder dimensions

    Rate the task on four things: does it need to take actions, does it break into parts, how deterministic must it be, and is it more about exploring or exploiting? These ratings decide the step.

  2. Step 1 — plain model call

    If the task is text generation with no tools, no memory, and no multi-step planning, stop at the model. Wrap it in an API and ship.

    usesAugmented LLMStructured Output

  3. Step 2 — single agent

    If the task needs tools, memory, or a loop, climb to a single agent with the four-component architecture. Most production agents stop here.

    usesTool UseReActPlan-and-Execute

  4. Step 3 — deterministic multi-agent workflow

    If the task breaks into a fixed graph of specialist steps, build a deterministic multi-agent workflow with orchestrator-workers or pipes-and-filters. The structure lives in the graph, not in the agents.

    usesOrchestrator-WorkersPipes and FiltersPrompt Chaining

  5. Step 4 — autonomous multi-agent system

    Climb here only when the task is truly open-ended, needs emergent coordination, or gains from agents negotiating with each other. Accept the cost of nondeterminism and coordination on purpose.

    usesHierarchical AgentsSwarmDebate

  6. Document the decision and escalation triggers

    Write down which step you chose and why. Name the conditions that would justify climbing higher later, so the next move rests on evidence, not vibes.

Framework-specific instructions

Pick a framework and generate a framework-targeted rewrite of this methodology's steps.

Choose framework

AI-generated for Agent Development Kit (ADK) (Google) — verify against official docs.

Principles

  • Pick the lowest step that solves the task.
  • The architecture choice is a written decision backed by evidence, not a reflex.
  • Each step has a defining capability and a defining cost. Know both before you climb.
  • Name the escalation triggers up front. Climb on evidence, not enthusiasm.

Known failure modes (4)

Related patterns (10)

Related compositions (3)

Related methodologies (2)

Sources (3)

Provenance

  • Added to catalog:
  • Last updated:
  • Verification status: needs-verification