Agentic AI · Design patterns

Agentic workflows & agent design patterns

Most agentic systems aren't one big autonomous loop — they're composable patterns. Learn the six core agent design patterns, when each one wins, and how to decide between a predictable workflow and a fully autonomous agent.

  • 11 min read
  • Intermediate
  • Updated 2026

Agentic workflows are reusable patterns for orchestrating language models, tools, and control flow to get a job done. The single most useful idea in this whole space is that workflows and agents are two ends of a spectrum, not two different technologies. In a workflow, a human designs the path through the system ahead of time — the steps and their order are predefined in code. In an autonomous agent, the model itself decides the path dynamically at runtime, choosing which tools to call and how many times to loop.

Why does the distinction matter? Because autonomy is not free. Every decision you hand to the model adds latency, token cost, and variance. A well-designed system pushes as much as possible into predictable workflow structure and reserves true agentic decision-making for the moments that genuinely need it. The best engineers reach for the simplest pattern that solves the problem — and only add autonomy when the task is open-ended enough to justify it.

This guide walks through the six agent design patterns that show up again and again in production: prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer, and reflection. Together they cover the vast majority of real LLM agent systems, and they compose cleanly into larger multi-agent systems.

The mental model

The workflow-to-agent spectrum

Think of control flow as a dial, not a switch. The further right you turn it, the more decisions you delegate to the model.

Fixed pipelineEvery step hard-coded
Routed workflowModel classifies, code dispatches
OrchestratedModel plans, code executes
Autonomous agentModel directs the whole loop
Systems range from fully scripted pipelines to open-ended autonomous loops — most real products live somewhere in the middle.

Rule of thumb

Move right on the spectrum only when you can articulate a concrete task that the previous, more predictable pattern cannot handle. If you can write the steps down in advance, you probably do not need an autonomous agent — you need a workflow.

The building blocks

Core agentic workflow patterns

Six patterns cover almost every agentic system you'll build. Each is simple on its own; the power comes from composing them.

Prompt chaining

Decompose a task into a fixed sequence of LLM calls, where each step's output feeds the next. Add programmatic gates between steps to validate output before continuing — e.g. outline → draft → polish.

Routing

Classify the input, then dispatch it to a specialized prompt, model, or tool. Lets you send easy queries to a cheap model and hard ones to a stronger one, keeping each path focused and accurate.

Parallelization

Run independent subtasks concurrently and aggregate the results. Two flavors: sectioning (split work into parts) and voting (run the same task multiple times for a consensus or guardrail check).

Orchestrator-workers

A lead model breaks a goal into subtasks at runtime and delegates each to a worker. Unlike parallelization, the subtasks aren't known in advance — the orchestrator decides them based on the input.

Evaluator-optimizer

One model generates a candidate while a second evaluates it against criteria and returns feedback. The loop repeats until the output passes — ideal when quality has clear, checkable standards.

Reflection

The model critiques and revises its own output before returning it. A lightweight, single-model cousin of evaluator-optimizer that catches obvious errors and improves reasoning quality.

Patterns compose

These aren't mutually exclusive. A real system might route an incoming request, fan out subtasks with parallelization, then run an evaluator-optimizer loop on the aggregated result. Treat each pattern as a Lego brick, not a whole architecture.

Pattern in motion · Routing

Example: a routing workflow

A classifier inspects the input once, then dispatches it down the cheapest path that can handle it — improving both accuracy and cost.

Incoming requestSupport ticket arrives
ClassifierLabel intent & difficulty
RouteFAQ · refund · escalation
Specialized handlerRight tool, right model
Routing keeps each downstream path specialized: simple FAQs hit a small model, refunds trigger a tool, edge cases escalate to a human.

Routing shines when inputs fall into distinct categories that are better handled separately. By classifying first, you avoid stuffing one mega-prompt with instructions for every case — which both dilutes accuracy and burns tokens. A cheap, fast model often makes a perfectly good router, even when the downstream handlers use a larger model.

Pattern in motion · Evaluator-optimizer

Example: the evaluator-optimizer loop

When quality can be judged against explicit criteria, a generate-then-critique loop reliably lifts output quality — at the cost of extra calls.

GenerateOptimizer drafts a candidate
EvaluateScore vs. explicit criteria
Feedback loopRevise if it fails the rubric
AcceptPass or stop at retry limit
The optimizer drafts, the evaluator scores against rubric criteria, and feedback flows back until the output passes or a retry limit is hit.

Cap your loops

Any pattern with a feedback loop — evaluator-optimizer, reflection, or an autonomous agent — needs a hard stopping condition: a maximum number of iterations, a budget ceiling, or a confidence threshold. Without one, a stubborn task can loop indefinitely and quietly run up cost.

Pattern in motion · Orchestrator-workers

Example: orchestrator-workers

When the subtasks can't be known in advance, a lead model decomposes the goal at runtime and delegates to dynamically spawned workers.

Orchestrator

Plans subtasks at runtime

Researcher

Gathers sources

Data worker

Queries the warehouse

Coder

Writes & runs code

Writer

Drafts the answer

The orchestrator decides which workers to spawn based on the input, then synthesizes their results — the defining trait that separates it from static parallelization.

The key difference from parallelization is that the subtasks are not predefined. The orchestrator reads the input and decides — at runtime — how to break the work down and how many workers to spawn. That flexibility is exactly why this pattern edges toward the agentic end of the spectrum. For a deeper dive into coordination, delegation, and shared memory, see multi-agent systems.

The core trade-off

Workflows vs autonomous agents

Neither is universally better. The right choice depends on how predictable the task is and how much you value adaptability over cost and reproducibility.

DimensionFixed workflowAutonomous agent
Control flowDefined by the developerDirected by the model
PredictabilityHighLower
Cost & latencyLow, boundedHigher, variable
FlexibilityLimited to designed pathsAdapts to novel inputs
Debugging & reproducibility
Steps known in advance?
Best forClassification, extraction, templated tasksOpen-ended, multi-step problems
6

Core patterns

cover most systems

2x

Typical cost

of a loop vs. one call

1

Stopping rule

every loop needs one

100%

Traceable

log every step

The practical takeaway: don't default to autonomy. An autonomous agent is the most flexible and the most expensive, least predictable option. If the steps are known, a workflow will be cheaper, faster, and far easier to debug. Save the autonomous loop for tasks where the path genuinely cannot be planned in advance — and read how to build AI agents for the implementation mechanics.

Decision guide

Choosing the right pattern

Run through this checklist before reaching for the heaviest tool. Most of the time, a simpler pattern wins.

  • Can you write the steps down in advance?If yes, use prompt chaining — no autonomy needed
  • Do inputs fall into distinct categories?Route them to specialized handlers
  • Are subtasks independent of each other?Parallelize and aggregate the results
  • Are subtasks unknown until runtime?Use orchestrator-workers to decompose dynamically
  • Is there a clear quality rubric?Add an evaluator-optimizer loop
  • Does every loop have a stopping condition?Cap iterations, budget, or confidence
  • Could a smaller model handle this step?Reserve strong models for hard decisions
  • Is full autonomy genuinely required?Only if the path truly can't be planned

Start simple, then escalate

Build the smallest pattern that works, measure it, and add complexity only where the data shows you need it. Many teams find a routed prompt chain outperforms an autonomous agent on real workloads — at a fraction of the cost and with far better observability.

FAQ

Agentic workflows, answered

Agentic workflows are structured patterns for chaining LLM calls, tools, and routing logic to solve a task. They sit on a spectrum: at one end are fixed workflows where the path through the system is predefined in code, and at the other are autonomous agents that decide their own steps at runtime. Most production systems mix both — a predictable skeleton with agentic decision points where flexibility is genuinely needed.

Get started

Build agentic workflows that ship

Compose routing, chaining, and orchestration into production-grade agents — with tracing on every step. Free to start, no credit card required.