Business analysts need to work with data — but the tools have always required technical skills they don't have. This is the design process behind an AI-assisted interface that makes it safe and approachable for non-technical users to own that work.
Before any sketching, I interviewed 8 people across two groups: business analysts who needed the tool, and the engineers who currently owned the process. The gap between how each group thought about the work 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 scenarios: when the AI gets it right, and when it doesn't. Both had to be fully designed — the edge cases matter just as much as the smooth 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 |
The dark theme was chosen deliberately — engineers work in dark environments, and the design needed to feel precise and capable without intimidating the non-technical users coming in for the first time. Every color carries meaning.
The confidence indicator is the most important element in the product — it's what lets someone decide whether to trust the AI's output or push back on it. I went through 6 iterations before landing on a pattern that communicated urgency clearly without being alarming.
| 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 a production-fidelity prototype. Type a prompt and hit Generate — the system simulates the AI workflow, shows the output with confidence scoring and annotations, and walks you through the full review flow. Switch between tabs to see version history and compare changes.