-
Is your AI summary reliable? Build a five-case evaluation pack
A five-case exercise for checking AI summaries without letting invented actions or deadlines slip into a handover.
-
Your sprint is full of finished code. Why is nothing ready to release?
A practical queue review for sprint planning: inspect waiting work, identify the next action and agree one team experiment.
-
Before asking AI to fix it again, write a debugging evidence note
Turn repeated AI fixes into a focused investigation with a reading-list example and a reusable debugging evidence note.
-
When an AI feature fails: design a recovery route users can understand
Plan a clear recovery route for an AI feature with a fictional rota example, message comparison and reusable planning note.
-
How to mentor junior developers when AI can finish the task for them
A practical mentoring session that checks understanding, makes questions easier to ask and builds independent problem-solving.
-
How to review AI-generated code when you are still learning
A small booking-page exercise to help you question AI-generated code, test awkward inputs and leave useful review notes.
-
AI personas are not customer evidence: a practical research sorting exercise
Separate observations, interpretations and AI-generated suggestions before they become product decisions.
-
Stop reopening the same product decision: use a six-part decision log
Make recurring product discussions actionable with a clear question, decision owner, evidence and review trigger.
-
How to learn to code with AI without skipping the fundamentals
AI can produce a working page before you understand why it works. That can feel exciting, then frustrating when you want to change one small thing and have no idea where to start.…
-
AI literacy for women in tech: 7 skills to practise this week
You do not need to build an AI model to ask useful questions about one. If an AI tool is helping your team write, analyse, code or make recommendations, you need enough understanding…
