Governed AI: Power BI Dashboards from a Prompt or a Template

Internship

• Field: DEV & AI
• Duration: 4 months
• Start: February 2027, or according to the university’s calendar.
• Paid internship with a flexible workplace model allowing remote and on-site work where possible.

Project context and objectives

In a bank, a plausible wrong figure or a leaked row is worse than no answer. The AI must choose only from the project’s approved vocabulary; code writes the SQL, model, and visuals, and every step is checked and measured.

• Generate a governed Power BI semantic model from approved project knowledge, including business names, declared joins, lists shown by name, and calculated fields as measures.
• Enforce the platform’s row-level security, or Chinese wall, in the model outside the AI’s reach.
• Enable prompt-to-dashboard generation, with the AI selecting measures, dimensions, filters, and visuals from a closed list while code writes the Power BI pages and visuals.
• Enable template-to-dashboard generation by reading an existing Power BI file or a dashboard picture and rebuilding it on the governed model.
• Implement guardrails that drop and count invented labels, refuse partial requests, name gaps in words, and produce the same dashboard for the same request.
• Build a React product page with prompt, upload, preview, and download features based on an approved mockup.
• Define measurement through prompt and template evaluation sets, zero entitlement leaks, cost per dashboard, and comparison of governed versus free AI generation.
• Work using Scrum with two-week sprints, code reviews, and CI.
• Produce an end-of-study report and defence.

Candidate profile and requirements

• Final-year engineering student in software engineering, data, or AI.
• C# or another typed language and SQL.
• Interest in Business Intelligence, Power BI, and applied AI / LLMs.
• React / TypeScript is a plus.
• Rigorous approach to tests, measurement, and clean design.