What this covers
Ask questions about approved metrics in plain language, with clear definitions and links back to the data.
Tools
Read-only APIs, SQL validation, Metric definitions, Charts. The exact stack depends on what you already use.
Where it helps
- Explaining a change in a defined metric
- Writing a summary from an approved dashboard export
- Helping staff find the right report
We agree what “done” means before work starts.
What you get
- Plain-language questions over approved metrics
- Visible definitions and links back to the data
- Source code, setup notes and an agreed definition of done
The final list depends on the agreed scope. The estimate and schedule follow from it.
Data and security
Read-only access, query limits and row-level permissions. AI-written SQL is never run without restrictions.
How I work on it
Define the metrics, approve which queries are allowed, prototype questions, compare answers with known results, and add refusal and review steps.
What helps me get started
- A short description of the process and who uses it.
- Sample data, any API documents, and what access is available.
- How much it will be used, who reviews the work, and your release priorities.
A short outline is enough for a first call. Please send sample data, not real records or passwords.
Related services
Read the planning guideQuestions
Can it prove why a metric changed?
No. It can show what changed and suggest possible reasons, but proving a cause needs more evidence.
How do you price the work?
I look at the workflow, the systems involved, the access needed and what “done” means, then send an estimate. If there are big unknowns, we start with a short discovery or a prototype.