Workshop 1 – Use-case hunt
Workshop 1 – Use-case hunt
Time: 20 minutes Where: this workbook + Copilot Chat Output: 5–8 AI use-case candidates from your department
Work on your real department. If you prefer not to, use TRAXIA’s Road Systems and Smart City division. Put nothing confidential in the prompt – the activity type and volume are enough.
Step 1 – Alone: activities that eat time (8 min)
Look for activities that repeat, take a lot of time, involve lots of text, data or searching, or frustrate you. Be specific: which report, how often, how many hours, for whom.
“Monthly project status report for management – 12 projects, monthly, ~6 h; pattern: Find and summarise + Analyse; risk: wrong numbers in the commentary.”
Step 2 – Copilot as a sparring partner (4 min)
Open Copilot Chat and fill in the brackets:
I lead the [X] department in a company that supplies intelligent transport systems (weigh-in-motion, variable message signs, level-crossing protection, smart city) with 5 branches in Slovakia and Poland. My department mainly does: [3–5 activities]. Suggest 10 concrete AI use cases. For each give: pattern (Create / Find and summarise / Analyse / Act), estimated benefit, main risk and suitable tool type (Copilot, agent, Cowork, custom solution). Output as a table.
Keep only what makes sense in your reality.
Step 3 – Assign a pattern
Create – drafts, bids, copy · Find and summarise – knowledge, contracts, meetings · Analyse and decide – numbers, risks, options · Act – multi-step, multi-system (agents)
Step 4 – In pairs: what could go wrong? (5 min)
For each use case your partner asks “What could go wrong?”. Write down the biggest risk.
| # | Activity / use case (what, for whom) | Volume (×/month, hours) | Pattern | What could go wrong? |
|---|---|---|---|---|
| 1 | ||||
| 2 | ||||
| 3 | ||||
| 4 | ||||
| 5 | ||||
| 6 | ||||
| 7 | ||||
| 8 |