The situation
The edtech (~45 staff) sells per-seat licenses to secondary schools in Spain, Portugal, and Italy and is preparing for a Series B; a believable usability story is part of the deck.
Your task
Redesign the AI tutor's chat interaction so students reason more and copy-paste less, with measurable usability evidence.
The brief
You start with
You receive a short Loom walkthrough of the live product, a CSV of 5,000 anonymized teacher-flagged sessions, and three teacher interview transcripts.
What you do
- Audit the existing sidebar against Nielsen's 10 usability heuristics (a classic usability checklist) and the Microsoft Guidelines for Human-AI Interaction.
- Redesign the chat affordances, error recovery, and visible-uncertainty cues so the assistant nudges students toward reasoning.
You deliver
A clickable Figma prototype that covers three core flows (asking for help, getting stuck, finishing a problem) plus a one-page rationale doc the product team will share with engineering.
What you will practice
- Apply Nielsen heuristics and Microsoft Human-AI guidelines to a real product
- Translate qualitative interviews and quantitative session logs into design decisions
- Design interaction patterns that surface AI uncertainty to non-expert users
- Communicate design trade-offs to a cross-functional product team
A suggested way in
- Use Microsoft's 18 Guidelines for Human-AI Interaction as a second checklist alongside Nielsen
- Map each flagged session to a heuristic violation before redesigning
- Prototype the 'stuck student' flow first — it carries the most pedagogical weight
Skills you will practice
User centered design, Heuristic evaluation, Interaction design, Figma prototyping, Human AI interaction, Usability evaluation
Where it leads
AI Product Designer, AI Product Manager, Prompt Engineer
How it is assessed
- Audit rigor30%
Issues are severity-ranked and traceable to specific sessions or interview quotes.
- Redesign quality30%
New flow addresses the top three audit findings with believable interaction patterns.
- Human-AI interaction fit20%
Uncertainty, recovery, and consent cues follow established Human-AI guidelines.
- Rationale clarity20%
A PM can read the one-pager and brief engineering without follow-up questions.
Resources
- FigmaTool
Industry-standard for clickable prototypes and design hand-off.
- NotionTool
Author the audit doc and the rationale one-pager.
- Google SheetsTool
Tag and cluster the 5,000 flagged sessions.
- LoomTool
Record the walkthrough deliverable cheaply.
- MazeTool
Run a quick unmoderated usability test on the prototype.
Finish it. Earn this.
A verified certificate with your name. Anyone can check it.
Time to practice.
Solve this challengeMore like this.
- Software EngineerGreedy Delivery-Slot Assignment for a Munich Grocery Startup
- Software EngineerDesign a Verified UART Receiver and Loopback for an FPGA Sensor Hub
- Data ArchitectDesigning a Data Warehouse for a Renewable Energy Firm
- Database AdministratorCut a 42-Minute Trino Query to Under Five Minutes
-
Greedy Delivery-Slot Assignment for a Munich Grocery Startup Software Engineer Using the provided order history sample, rider roster, and manual dispatch baseline, design and implement a greedy slot-assignment algorithm in Python greedy algorithmsalgorithm analysispython Open challenge → -
Design a Verified UART Receiver and Loopback for an FPGA Sensor Hub Software Engineer Propose and deliver a UART receiver for Helax's sensor hub that meets the functional requirements in the requirements brief (the 'uart-requirements-br veriloguartfpga Open challenge → -
Designing a Data Warehouse for a Renewable Energy Firm Data Architect You are given sample data from three sources: energy production logs, weather data, and equipment maintenance records. Your task is to: (1) design a s data warehousingstar schemaetl Open challenge → -
Cut a 42-Minute Trino Query to Under Five Minutes Database Administrator Using the slow query, the EXPLAIN ANALYZE readout, the Iceberg table schemas, and the 30-day execution-metrics dataset provided, design an optimizatio trinosql optimizationiceberg Open challenge →