Build a Multi-Criteria Vendor Selection Tool for an AI Consulting Firm
Overview
What this challenge is about.
You will design a Multi-Criteria Decision Analysis (MCDA, a structured way to score options against weighted criteria) tool that accepts 6-10 vendor options, 6-12 weighted criteria, and produces (a) a ranked recommendation, (b) sensitivity analysis (which weights would flip the ranking?), and (c) a 2-page client-ready memo. Build it in Streamlit so a consultant can run it on a client call. Pre-populate it with a realistic LLM-vendor evaluation as a worked example. Deliverable is the tool, the playbook, and a 30-minute internal training script.
The Brief
What you'll do, and what you'll demonstrate.
Replace one-off vendor-selection spreadsheets with a reusable MCDA tool that produces a defensible recommendation memo in under 90 minutes per engagement.
Earning criteria — what you'll demonstrate
- Apply MCDA methods (weighted sum, AHP, TOPSIS) to a real consulting decision
- Design sensitivity analysis that surfaces ranking fragility
- Build internal tooling consultants actually adopt
- Communicate decision rationale to a non-technical client audience
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Career paths this builds toward
Canonical rolesAI Solutions Architect
Building structured vendor-selection tooling is a high-leverage deliverable for any AI solutions architect on the buy-side of LLM adoption.
This challenge sharpens
- mcda
- consulting-tooling
- sensitivity-analysis
AI Product Manager
Translating fuzzy vendor trade-offs into a reusable decision framework is a transferable AI PM skill.
This challenge sharpens
- decision-support-systems
- mcda
- consulting-tooling
AI Engineer
Shipping internal-tooling Streamlit apps that consultants actually use mirrors the AI-engineer's day-to-day at consulting and platform teams.
This challenge sharpens
- streamlit
- python
- consulting-tooling