Guide · Design patterns

Seven shapes that explain most AI solutions.

An AI solution can be built in a great many ways, and the technical literature catalogues dozens of them. But most of what you will meet in practice can be understood through a small number of recurring shapes. Seven is our choice, not a fact of nature: five workflows you design, and two agents that work more on their own — enough to make sense of almost anything you are shown, and few enough to hold in your head. Each gets a plain definition, a diagram and everyday examples, and the one question that tells you which to reach for: is the path knowable in advance? Written for everyone, from complete beginners to technical specialists.

Start here · the one question

Is the path knowable in advance?

Every pattern in this guide is a variation on a single question. If you can lay out the steps up front, you have a workflow — steps you design. If you can’t, because it depends on what the AI finds, you have an agent — it works out its own steps to reach a goal you set. Most everyday value, and almost everything worth trying first, sits on the workflow side.

Workflow

You design the steps

The path is known, so you lay out the steps and the AI runs them. Predictable, easy to check, cheaper. Most business value lives here.

Agent

The AI chooses the steps

The path isn’t knowable up front — it depends on what the AI finds — so you set the goal and the limits, and it works out the steps. Flexible, powerful, needs guardrails.

The questionWorkflowAgent
Is the path knowable in advance?Yes — you know the steps.No — it depends on what the AI finds.
Who chooses the next step?You — you set the steps.The AI — within limits you set.
The trade-offPredictable, easy to check, cheaper.Flexible, powerful, needs guardrails.

The useful question isn’t “is it an agent?” — it’s “how much have I handed over?” The more the AI decides for itself, the more it matters that you set clear limits and stay responsible for the result.

How to read the diagrams

A quick key.

Never read a flowchart before? Every diagram below is built from four simple shapes.

Input · Outputwhere the work starts and ends
Stepa step in the work
Decisiona choice or check point
Loopthe cycle repeats until done
The catalogue

The seven patterns.

Five workflows you design, then two agents that work more on their own. Each gets a plain definition, a diagram, when to reach for it, two everyday examples, how to direct it, and the one thing to watch.

Seven is a working selection, not an exhaustive list. There is no fixed number of AI design patterns, and no official catalogue of them — the open-source list this guide draws on runs to 35, and it keeps growing. These seven are the ones we find most useful for making sense of the AI systems people actually meet at work. Learn them and you will recognise the shape of most solutions put in front of you, including ones that go by a different name. The crosswalk for technical readers further down shows how they map to the fuller list.

01

Prompt chaining

Workflow

Break a task into a fixed set of steps, done in order. Each step’s result feeds the next, with a check in between where it helps.

Fail the check → back a step. Put your one check where the work is most likely to go wrong.

Reach for it when

the task has clear, ordered steps and the result is better when they are done one at a time rather than all at once.

Two examples
EverydayPlanning a trip: list the places you want to see, then check they’re open on your dates, then turn it into a day-by-day plan.
At workTurn a long new rule into a team summary: draft an outline → check it covers every part → expand it into a one-page guide.
How to direct it

You design the steps and run them in order — a classic workflow. The skill is clear instructions, and putting your one check at the step most likely to go wrong.

Watch out

A mistake in an early step carries all the way to the end. Put your check at the weakest link.

Competency it stresses Direction
02

Routing

Workflow

Sort each incoming request first, then send it to whoever — or whatever — is best placed to handle that type.

Reach for it when

the things coming in fall into clearly different types, each needing different handling.

Two examples
EverydayYou email a large company. An assistant reads your message and sends it to the right place — billing to the billing team, a fault to technical help, a complaint to a manager.
Public sectorA local authority’s contact inbox: planning questions to the planning team, refuse-collection queries to waste services, anything urgent to a duty officer.
How to direct it

Two parts: a sorter that reads and labels each request, and the specialist paths it feeds. A workflow — you decide the categories.

Watch out

Always include a clear “doesn’t fit → send to a human” exit. Without one, it will guess when it should have asked.

Competency it stresses Delegation
03

Parallelisation

Workflow

Split the independent parts of a task and do them at the same time — then bring the answers together. (Or ask the same question a few times and go with the consensus.)

Reach for it when

the parts don’t depend on each other, or you want a second and third opinion to be more confident.

Two examples
Public sectorReading replies to a public consultation: one pass gathers who supports a proposal, one who objects, one the new suggestions — then all three are combined into a single summary.
EverydaySizing up a flat to rent by checking three things at once — price, location and condition — then weighing them together.
How to direct it

The parts run side by side, then a final step combines them. A workflow. A handy variation: ask the same question a few times and only flag where the answers disagree — a simple reliability check.

Watch out

Only split parts that are truly independent. If one part needs another’s answer first, that’s step-by-step (Pattern 01), not side-by-side.

Competency it stresses Direction
04

Orchestrator and sub-agents

Workflow → Agent

A lead AI — the orchestrator — looks at the job, works out what the pieces are, and creates helper AIs (sub-agents) to handle each one, then combines their work. The sub-agents are AI helpers, not people.

Unlike a fixed split, the orchestrator decides how many sub-agents there are, and what each does, at run time.

Reach for it when

you can’t list the pieces in advance, because they depend on the particular job in front of you.

Two examples
Public sectorA regulatory impact assessment comparing policy options: the lead works out which options and tests matter, sends one sub-agent to weigh up each option (costs, benefits, risks), then combines them into a clear comparison.
EverydayOrganising an event: the lead works out the tasks — venue, catering, invitations — hands each to a sub-agent, then pulls the results together.
How to direct it

You hand the lead AI a goal and let it plan and split the work. This is where a workflow starts to become an agent. Give it a budget and a stopping point — and you still own and sign off the final result.

Watch out

Left open-ended, it can keep expanding the task. Give it a budget and a clear stop signal.

Competency it stresses Delegation + Ownership
05

Evaluator–optimiser

Workflow

One part produces the work; another checks it against clear standards and sends back feedback. This repeats until it passes.

Doesn’t meet the standard → back to the generator, until it passes.

Reach for it when

quality matters and “good” can be written down as a checklist.

Two examples
At workAn important email: one part drafts it, another checks it’s clear, complete and follows your organisation’s rules on tone and language — sending it back until it’s right.
Public sectorA public notice: each draft is checked against plain-language and accessibility standards before it’s published.
How to direct it

Write the standards down and give them to the checker. This is the machine version of a human review — the same skill of checking work before you rely on it.

Watch out

A vague checker either loops forever or waves everything through. Clear, checkable standards are what make it work.

Competency it stresses Evaluation
06

Autonomous agent (ReAct)

Agent

Give the AI a goal and a set of tools; it works in a loop — Reason, Act, Observe — choosing each step itself until the goal is met.

Reason → Act → Observe repeats, the AI choosing each step, until the goal is met.

Reach for it when

the path depends on what the AI finds along the way, so you can’t lay out the steps in advance.

Two examples
PersonalBuying a used car: you say “find me a reliable family car within my budget, within 50 km.” It searches listings, compares options, checks reviews and comes back with a shortlist — deciding each step itself.
At work“Find out what the new rules mean for us and draft a short summary” — it searches, reads, checks and writes, without being told each step.
How to direct it

You give the goal and let the AI choose the steps. Because it acts on its own, the key is staying in control: set clear limits, keep a human check, and approve anything irreversible before it happens.

Watch out

Never let an agent take an irreversible action — send, pay, delete, publish — unsupervised. Limit which tools and actions it can use.

Competency it stresses Ownership
07

Multi-agent — an “agent team”

Agent

Several AIs, each with a different role, work together as a team — often called an agent team. For example a researcher, a writer and a checker, passing the work between them.

The critic sends the draft back to the writer until it’s approved.

Reach for it when

different roles genuinely improve the result and the work can be shared between them.

Two examples
EverydayPlanning a big trip as a team: one AI researches destinations, one works out the budget, one double-checks everything fits together.
Public sectorProducing a briefing: one AI gathers the facts, one writes it up, one plays devil’s advocate to test it before it goes out.
How to direct it

The most capable shape, but the hardest to keep predictable — more moving parts. You set the roles and stay accountable for what the team produces.

Watch out

More agents is not better. Add a role only when it genuinely changes the result.

Competency it stresses Ownership
Two capabilities — not patterns

Two things you will hear about constantly are not shapes in their own right. They are options you can switch on inside any of the seven above.

Grounding

often called “RAG”

Giving the AI your own documents to work from, so that answers are based on real sources rather than guesswork.

Memory

across steps, or across sessions

Letting the AI carry what it learned from one step, or one conversation, into the next instead of starting from nothing each time.

This is why two systems described as “a RAG chatbot” and “an agent with memory” may in fact be the same shape underneath. Identify the shape first, then ask which capabilities are switched on.

From patterns to governance

An agent is more like a new colleague than a new tool.

A chatbot is a tool: you operate it, one turn at a time, and nothing happens unless you ask. An agent is different. You give it a goal and it acts on its own — planning, using tools, making choices along the way. That is much closer to handing work to a capable new member of staff than to using a piece of software. And it is the thread running through the seven patterns: as you move from the workflows to the agents, you hand over more of the path.

Think about what you actually do when a capable person joins your team. You don’t give them every system and walk away. You define their role and its limits. You brief them on the goal and the context. You decide what they can sign off alone and what has to come back to you. You review their work before the organisation relies on it. And whatever they produce, the responsibility for it stays with you. Do none of that and a capable hire becomes a liability rather than an asset — decisions no one can explain, work no one checked, mistakes no one caught. Exactly the same is true of a capable agent.

Delegate

Decide what to hand over

With a colleague: which work is theirs, and which stays with you.

With an agent: which tasks and tools it gets — and which decisions never leave a human.

Direct

Brief it well

With a colleague: the goal, the context, and what “good” looks like.

With an agent: the same, written as a brief it can act on — the G-C-O-V method.

Evaluate

Check the work

With a colleague: you review it before the organisation relies on it.

With an agent: the more it does unsupervised, the more this matters — so build the check in.

Own

Stay accountable

With a colleague: their work is your organisation’s responsibility.

With an agent: “the AI did it” is never an answer to a client, a regulator or a colleague.

Write those four down and apply them across the organisation, and they have a name: AI governance.

Governance is simply that management discipline made explicit and organisation-wide: who may use which system, for what, with which limits; who checks the output; who can stop it; and where the record lives. It isn’t a binder you buy or a single person you hire — it’s an operating model, and it pays for itself. It’s the third factor in the AI value equation — the governed organisation that turns capable AI and capable people into value instead of exposure. And it’s the honest answer to the agents your staff may already be running without asking: shadow AI. The wider picture of what can go wrong, and where these controls attach, is the risks of AI, mapped.

One caution, so the comparison doesn’t mislead. Treating an agent like a colleague is about the discipline of managing delegated work — not a claim that the agent is a person. It has no judgement of its own to fall back on and carries no accountability: both stay entirely with you. That is precisely why the limits, the checks and the human sign-off are not optional — and why the most agentic patterns need the most governance around them.

Quick reference · the pattern-picker

Find your task, find your pattern.

Look at a real task from your own work or life, find the row that fits, and you have your pattern. If more than one fits, pick the simplest — a workflow beats an agent whenever it can do the job.

PatternReach for it when…ExampleMain skill
Prompt chainingthe task has clear, ordered stepstrip plan; team summaryClear instructions
Routingrequests fall into different typessorting incoming enquiriesDeciding what goes where
Parallelisationthe parts are independentsummarising consultation repliesClear instructions
Orchestrator + sub-agentsthe pieces aren’t known up frontimpact assessment of optionsHanding over + owning it
Evaluator–optimiserquality can be checked against a standardemail to your house styleChecking the output
Autonomous agentthe path depends on what it findsbuying a car; research + draftStaying in control
Multi-agent (agent team)different roles need to collaboratebriefing with a fact-checkerStaying accountable

The companion worksheet, Map your work to a pattern, turns this into a short exercise in our AI-agents seminars.

For technical readers

How the seven map to the fuller list.

You can skip this. The seven here are a plain-language distillation of a larger, open-source catalogue of 35 patterns — which is itself one catalogue among several, not a closed list. If you want to go deeper, or compare notes with a technical colleague, this is the crosswalk.

In this guideRelated names in the technical catalogue
Prompt chainingPlanning; Self-Discover
RoutingSafety & Routing (Dry-Run, Meta-Controller); Adaptive RAG
ParallelisationSelf-Consistency, Ensemble; Debate (voting variant)
Orchestrator and sub-agentsPlanning, PEV; Meta-Controller; STORM
Evaluator–optimiserReflection, Reflexion, Chain-of-Verification, Constitutional AI
Autonomous agentTool Use, ReAct, SWE-Agent, BrowserAgent, Computer Use
Multi-agent (agent team)Multi-Agent, Blackboard, Debate, STORM
Capability: grounding (RAG)Agentic / Corrective / Self / Adaptive / GraphRAG
Capability: memoryEpisodic + Semantic, Graph Memory, MemGPT, Voyager, AWM
Advanced / researchTree of Thoughts, LATS, RLHF Self-Improvement, Cellular Automata

Where this comes from. The workflow-and-agent distinction follows Anthropic’s Building Effective Agents. The pattern names draw on two open-source catalogues — all-agentic-architectures by Fareed Khan and a companion project by The AI Automators — both freely reusable under the MIT licence. The explanations, diagrams and examples here are Kramer Consulting’s own work, written for a general audience.

From understanding agents to building one.

Our AI-agents seminars run the whole arc — understand what agents are and why they matter, then build your first one in a hands-on day. Small groups, practical from the first hour.