CCA-F start here · Trap gym · Fixed chain or Claude decides?

Fixed chain or Claude decides?

Some work has steps you can write down before you start. Other work only reveals its next step once you see what the last one found. The trap runs both ways: an open investigation gets a rigid script, or a known checklist gets handed to an agent to improvise. A third wrong answer stuffs everything into one big prompt.

D1 Agentic ArchitectureExam guide 1.6About 15 minutes

At a glance: if the steps are known in advance, use a fixed chain of prompts; let Claude choose the steps only when they depend on what is found along the way.

Start here: the recipe and the detective

Baking a cake follows a recipe: mix, pour, bake, ice, the same every time. You can write every step down before you switch the oven on.
Finding out why the cake sank is different. Was the oven too cool? Then check the thermometer. Was it fine? Then check the baking powder. What you check next depends on what you just found.

Use a recipe for the first job and a detective for the second. With Claude, the recipe is prompt chaining: a fixed sequence of prompts, where each one handles one piece and the output feeds the next. For a code review, that means one focused pass on each file, then one integration pass that reads all the file notes together and looks for problems between files. The detective is adaptive decomposition: Claude is given the goal and the evidence, and it creates each next subtask from what it has just discovered.

The third shape, one big prompt with everything in it, is not a plan at all. It works for a small job. As the prompt grows, the model's attention spreads thin (the exam guide calls this attention dilution), so later items get less care and the answers can contradict each other.

Fixed chain: the steps are written down before you start file 1alone file 2alone … file 14alone Integration passacross all the file notes Claude decides: each next step comes from the last finding Goal +evidence so far Checkone thing Findingwhat it showed Causewhen the trail ends the next step is chosen from it One big prompt everything at once; fine when small, attention thins as it grows Hard-coded decision tree a fixed chain with branches: only the causes you foresaw
The one question to ask: can you write down every step before you start, or does the next step depend on what you discover?

Words in the question that tell you which side you're on

Fixed chain

  • every file, each section
  • “the same steps each time”, “known stages”
  • “review each file, then…”
  • predictable, must be replayed or audited

Claude decides

  • “depends on what it finds”
  • open-ended investigation, unknown cause
  • “follow the leads”
  • a fixed plan finished but missed the real cause

Try it: play out the job

Pick a job, then pick how you split the work. The simulator plays out the steps that run, marks what was missed in pink and what was wasted in grey, and gives a verdict. The diagram above highlights the shape you picked.

1. The job
2. How you split the work

    Share of what was there to find, found

    The jobs, files and findings are illustrative, made up to show the shape. They are not measurements. The exam guide's point is that known steps suit a fixed chain (each file on its own, then a cross-file integration pass), and that an open investigation should generate subtasks from what is discovered.

    Things to try: pull request + one big prompt to watch later files get skimmed, then + fixed chain. Then pull request + Claude decides: it mostly works, at a cost. Then nightly job + fixed chain, and + Claude decides to see why the detective wins there. Last, config file + one big prompt: for one small file, simple is right.

    The four traps

    TrapWhat the wrong option looks likeWhy it loses
    Overbuilt“Give one agent everything and let it decide the steps”, for a job whose steps are knownIt works, but it adds unpredictability and cost for no gain, and a run can skip what a checklist would not.
    Too rigid“Hard-code the investigation steps as a decision tree”, or add more steps to a fixed planIt works for the cases you foresaw. An open problem needs the next step chosen from what was just found.
    Attention dilution“Process all the files in one large prompt”, or “use a model with a bigger context window”Fine for a few files, but quality drops as the prompt grows. Per-file passes plus an integration pass keep each one sharp.
    Chain without the joinEach file reviewed on its own, with no step that looks across themBugs that live between files are never seen. The integration pass is half of the pattern.

    Practice: three exam-style questions

    Answer first, then open “Think it through”.

    Rule to remember

    Known steps get a recipe; unknown steps get a detective. A recipe here is each item on its own, then one integration pass across them.

    Exam guide 1.6: “Fixed sequential pipelines (prompt chaining) vs dynamic adaptive decomposition based on intermediate findings.” “Prompt chaining: analyze each file individually, then a cross-file integration pass.” “Adaptive investigation plans generate subtasks from what's discovered.” Exam guide 4.6: “Multi-pass: per-file local analysis + cross-file integration passes (avoid attention dilution, contradictions).”

    ← All traps