CCA-P start here · Trap gym
CCA-P trap gym
On the exam, two options are usually good practices. One fact in the question decides which fits. Each page below shows a situation with four options; change one fact and watch the winning answer move. Then try three practice questions.
| # | Trap | Domain | Lines |
|---|---|---|---|
| 1 | Remove it, don't watch it When an agent holds a tool its role never uses, the answer is to remove the tool, not to log it, alert on it or ask for confirmation before it runs. | D3 | 3.1, 5.1 |
| 2 | Code for musts, prompt for shoulds A rule that must hold every time belongs in code or permissions; a prompt rule makes it likely, not certain. Soft preferences stay in the prompt, and judgement calls go to a person. | D2 | 2.2, 5.1, 7.1 |
| 3 | A bigger model is not the fix When answers are slow, costly or miss things, a bigger model or a bigger context window is rarely the fix; send the right context first, and move up a model only when the task itself needs more reasoning. | D2 | 2.1, 2.4, 3.8 |
| 4 | Check the inputs before the model When answers go wrong, look at what went into the model (the retrieved passages and the data) before blaming or replacing the model. | D4 | 4.4, 3.5 |
| 5 | The least autonomy that works Choose the simplest pattern that solves the problem: one call, then a fixed workflow, then a single agent, and several agents only when the work splits into independent parts worth the cost. | D1 | 1.3, 1.4 |
| 6 | Match the search to the question Vector search matches meaning; exact codes need keyword search, totals need a database query, and wrong-version or wrong-place results need metadata filters. | D3 | 3.6, 3.5 |
| 7 | Act with the user's own access An agent that serves people should reach data with each person's own scoped access, not a shared all-powerful account; use a service identity only when no person is behind the request. | D3 | 3.2 |
| 8 | Measure the outcome, not a proxy A model's self-rated confidence, a thumbs-up rate or an overall average can look healthy while the real outcome is poor; measure the outcome directly, on the slice that matters. | D4 | 4.1, 5.3, 5.5 |
| 9 | Evidence before you ship A few good-looking examples, or a test that changed two things at once, is not evidence: run the eval set first, change one thing at a time, then pick the live test that fits the question. | D4 | 4.3, 6.5 |
| 10 | Cache it, don't cut it When the same long text goes with every request, put it first and cache it; cutting it down or switching to a smaller model gives up quality for a saving that caching gives for free. | D2 | 2.5, 4.5 |
| 11 | Agree it in numbers No LLM system is 100% right, and “fast and accurate” is not a target: agree numbers against today's baseline, with a plan for the errors, and match the design to the value the sponsor named. | D6 | 6.3, 1.6 |
| 12 | Speak to the listener Shape the answer to who is listening and what they must do with it: value, cost, risk and a recommendation for whoever owns the decision; the how for whoever builds and runs it; a written record when the decision will be questioned later. | D6 | 6.2, 6.4 |
| 13 | The lightest protocol that fits Pick the lightest mechanism that meets the reuse, ownership and security needs: a direct API call or CLI for one known call, an MCP server for a capability many AI clients share, and agent-to-agent when another party's agent owns the whole job. | D3 | 3.7 |
| 14 | Load it when it's needed Load content up front only when it is small, stable and needed on almost every request; otherwise keep a short index in context and fetch the detail when a task calls for it. | D3 | 3.8, 2.4 |
| 15 | Review where the risk is Neither review everything nor review nothing: approval before irreversible or high-impact actions, automation plus random audits for low-risk volume, and full review only when every output carries real weight. | D5 | 5.3 |
| 16 | Measure fairness, don't prompt it An instruction telling Claude to be fair proves nothing: measure outcomes across groups on representative data, look for proxies, tell people when AI is involved, and keep a named person accountable. | D5 | 5.5 |