Workflows, agents, and the pattern vocabulary

Every architecture question on this exam is a vocabulary question in disguise. They describe a system, and you have to name it. So learn the names properly, because "it's an agent" is wrong roughly half the time.

The line that splits everything

Anthropic's own framing, and it is a clean one:

• A workflow orchestrates models and tools through predefined code paths. You wrote the steps.
• An agent lets the model dynamically direct its own process and tool usage. The model decides the next step at runtime.

The dividing line is who decides what happens next, not how complex the diagram looks. A monstrous 40-node pipeline with hardcoded branches is still a workflow. A twelve-line while loop where the model picks tools until it stops is an agent.

Underneath both sits the augmented LLM: one model call with retrieval, tools and memory attached. That is the base unit. Everything else is composition.

The five compositions worth memorising

Prompt chaining. Split the task into fixed steps, each call feeding the next. Add a programmatic gate between steps if you want to bail early. Best when the decomposition is genuinely known up front.

Routing. Classify the input, then dispatch it to a specialised path. Wins when different input types need genuinely different handling and lumping them into one prompt makes all of them mediocre.

Parallelization. Two flavours and they get asked separately. Sectioning splits a task into independent subtasks run at the same time. Voting runs the same task several times and aggregates, which is what you want for a judgement call where one sample is noisy.

Orchestrator-workers. A model decomposes the task into subtasks it invents at runtime, delegates them, then synthesises. That runtime invention is the difference from routing, and it is what makes this one agentic.

Evaluator-optimizer. One call produces, another critiques, loop until the critic is happy. Needs a critic that can actually tell good from bad, otherwise you have built an expensive way to churn.

The framework question, and where your other study pays

The CCDV-F exam guide, under Agent Patterns and Frameworks, names agentic abstraction frameworks with the examples Strands, LangGraph and PydanticAI.

Read that again, because it is genuinely good news. LangGraph is named on an Anthropic exam. If you are also sitting the LangChain LCAE, or you have been through the LangGraph course in this app, the state-graph-nodes-edges-checkpointer model you already have in your head is directly on syllabus here. The two certs overlap at exactly this point.

What that section wants is not framework trivia. It wants you to know what an abstraction framework buys you: a state model, explicit control flow, persistence and resumability, and observability, in exchange for a dependency and a layer of indirection between you and the raw message list. And it wants you to know the counterweight, which is that plenty of production agents are a while loop over the Client SDK, and that is a legitimate answer rather than a naive one.

The judgement they grade

Reach for the simplest thing that works: single call, then augmented call, then workflow, then agent. Agents trade determinism, latency and token spend for flexibility. If you already know the steps, encoding them is cheaper than asking a model to rediscover them on every request.