Data strategy
Curated examples or document search: which one your data supports
· 9 min read
In short
Use curated examples to teach behaviour, format and tone. Use document search to supply facts that change, which needs a clean and current document library.

Both approaches get proposed for the same problem, and the honest answer usually comes from looking at what data the team can actually produce.
Curated examples fit when
- The output must follow a specific format or house style
- The task needs vocabulary and conventions from a narrow domain
- You can maintain a few thousand clean example pairs
Document search fits when
- The facts change often enough that manual updates cannot keep up
- Answers must cite a source the user can open
- You already maintain an organised document library
Most mature products use both
Use curated examples for behaviour and document search for facts. The data work then splits into two tracks: curated example pairs on one side, a maintained document library on the other.
Practical checklist
- Define the acceptance rule before any volume starts
- Review a small pilot before committing the full budget
- Track errors by category, language and reviewer
- Keep consent, source notes and version history with the files
Before you ask for a quote
A clear brief saves days. Share a sample file, target language or region, expected volume, deadline, quality threshold and any privacy restrictions. A supplier can then price the work on real effort rather than assumptions.
- Which languages, markets or user groups must be represented?
- What format does the final file need to arrive in?
- Who will approve ambiguous cases during the pilot?
- curated examples
- document search
- strategy
Need this done rather than read about it?
We run collection, annotation, transcription and localization projects for teams who would rather spend their time on the product.
Start a conversation