2.6 — Curating Information and Selecting Output Formats

CCAO-F Domain 2 · Task 2.6

What You Need to Know

A long, productive conversation is not a deliverable. Curation extracts what the deliverable needs. Format selection gives it the container its reader will use.

Three Format Homes

Format	Fits
Inline chat response	Quick, one-off answers consumed in the moment
Structured table	Anything the reader compares or scans (options against criteria, schedules)
Artifact	Significant, self-contained content you are likely to edit, iterate on or reuse outside the conversation

Choice follows the reader’s use: ask-and-move-on → inline; compare-and-scan → table; reuse-and-revise → artifact.

From Working Material to Work Product

Curation starts from the deliverable, not the conversation: who reads it, what they do with it, whether it will be reused. Most of a working conversation is scaffolding; the deliverable owes its reader the decisions alone. Forwarding the whole conversation delegates curation to the reader — who will not do it.

What Each Mismatch Costs

• Reusable runbook left as loose chat prose → gets lost and re-created
• Comparison delivered as paragraphs → every reader rebuilds the table in their head
• Everything in a table → flattens narrative judgement
• Everything in an artifact → adds ceremony to throwaway answers

Key Concept: For every output, ask: what does the reader do with this? Read it once, compare across it, or come back to it? The answer is the format.

Exam Traps

• Answering a format question with Projects, Research mode or a model choice (Domain 3)
• Defaulting every output to the same container
• Sharing the whole conversation instead of curating the deliverable