Business analysts need to build data transformations — but can't write SQL. This is the design process behind a natural language interface that makes AI output trustworthy enough for financial services.
Before any sketching, I conducted 8 user interviews across two personas: business analysts who need the tool and data engineers who currently own the process. The gap between them revealed the core design problem.
| PRINCIPLE | WHAT IT MEANS IN PRACTICE | PRIORITY |
|---|---|---|
| Trust before speed | Never auto-apply AI output. Every transformation must pass through a human decision point — accept, edit, or reject. Speed is secondary to confidence. | Critical |
| Explainable uncertainty | Confidence scores alone are insufficient. Surface what the AI is uncertain about, not just how uncertain. "87%" means nothing. "Verify date cast on line 4" means something. | Critical |
| Engineer trust, always | Business users operate the tool; engineers must be able to override, audit, and inspect anything the AI generated. The governance layer is never hidden. | High |
I mapped two flows: the happy path (AI gets it right) and the exception path (AI is wrong or uncertain). Both paths had to be first-class design concerns — not just the happy path.
| NAV ITEM | PRIMARY USER | SECONDARY USER | BADGE LOGIC |
|---|---|---|---|
| Dashboard | Business Analyst | Engineer | None |
| Sources | Engineer | Analyst (read) | Error count |
| Transformations | Business Analyst | Engineer | Active count |
| Pipelines | Engineer | Analyst (read) | Running count |
| Audit Log | Compliance / Eng. | Analyst (limited) | Review-needed count |
| Destinations | Engineer | Analyst (read) | None |
I built the token system before any components. The dark theme was chosen deliberately: engineers live in dark code editors. The business user was new to this environment — the design had to feel precise and capable, not intimidating. Every color encodes semantic meaning.
The most important component in the entire product is the confidence signal. It's the bridge between AI capability and human trust. I iterated through 6 versions before landing on the final pattern: percentage + specific annotation + gradient fill encoding urgency.
| TIER | ELEMENT | VISUAL TREATMENT | RATIONALE |
|---|---|---|---|
| T1 · Primary | AI Output + Confidence Signal | Full width, primary text color, gradient bar | This is the moment of truth — nothing competes with it |
| T2 · Secondary | Accept / Edit / Reject actions | Color-coded, immediate below output | Decision follows output — spatial proximity = mental proximity |
| T3 · Tertiary | Version history, run count, timestamps | Mono text, muted color, bottom of screen | Available on demand; should not compete for attention during generation |
| T4 · Hidden | Schema details, column types, row counts | Tab-gated; only shown on request | Engineers need this; analysts shouldn't see it unless they ask |
This is the production-fidelity prototype. Type a prompt in the field below and hit Generate — the system will simulate AI generation, display the SQL output with confidence scoring and inline annotations, and give you the full accept/edit/reject flow. Switch between tabs to see version history and diff view.