Domain 6 · 11.0% of the CCDV-F exam
Prompt and Context Engineering
Decide what stays in the window, how the instruction and the case are placed, and how a program checks the text that comes back.
Task statements
- 6.1 · 3.8%
Context Engineering
The context window is the only memory a call has. Drift and bloat happen when old tool dumps crowd out the instruction. Prune tool output, compact a long transcript into a summary, and isolate a subtask so its scratch work never enters the parent.
- 6.2 · 4.6%
Prompt Engineering
A prompt is a placement problem as much as a wording problem. Durable rules go in the system turn, this call's data goes in the user turn, and examples cover the edge the rules keep missing. Change one thing, score it, and keep untrusted text in a data slot.
- 6.3 · 2.6%
Output Handling
A confident answer is still model output. Structured output makes the shape parseable. Your code validates the values, parses defensively, and refuses a field the source does not support.
Build exercises
Cut a transcript down to the decision
6.1 · Intermediate · 35 minutes
- Which lines are bloat.
- What a compaction tail must preserve.
- What a subagent should return.
Split one prompt into roles
6.2 · Intermediate · 40 minutes
- What is durable and what is the case.
- When an example is the next edit.
- How untrusted text stays data.
Put a check behind a schema
6.3 · Intermediate · 35 minutes
- What a schema guarantees.
- Which failures are retryable.
- How a confident string gets verified.