Custom GPTs retire on 11 December. Here is where yours can go
Blog

Get more out of AI at work

Practical, tested advice on working with AI agents. Useful whichever AI tool you use.

25 AI requests to try at work this week

Copy-ready AI requests for research, writing, documents, meetings, email, repeat work and decisions. Change the names and send.

Prompting8 min read

Claude vs GPT: how to prompt each one

GPT does exactly what you write. Claude fills the gaps. How to prompt each model family, pick a model and effort, and use one to check the other.

Models7 min read

How to check AI's work without redoing it yourself

AI states wrong things with confidence. Ask for proof, check in proportion to the stakes, and get a second opinion from another model family.

Ways of working6 min read

How to move your custom GPTs out of ChatGPT

Custom GPTs retire on 11 December 2026. How to move yours out of ChatGPT: what to copy, how to test it, and how to share it with your team.

Ways of working6 min read

How to write an AI request that works the first time

Five ingredients turn a vague AI request into one that works first time: the goal, the context, what done looks like, an example and the limits.

Prompting7 min read

Shared AI chats: how a team can work with AI agents together, safely

How a team can share AI agents in group and team chats, keep private chats private, and stop repeating the same background in every chat.

Teams7 min read

Stop using AI like a chatbot: think like a manager

One question, one answer leaves most of AI's value unused. Delegate outcomes, use helpers in parallel and move from doing the work to reviewing it.

Ways of working7 min read

Using AI at work safely: what to share and what to keep back

Practical habits for using AI at work safely: passwords, actions that reach the outside world, private chats, emails and what AI should remember.

Safety6 min read

Why your organisation's AI shouldn't belong to one AI lab

Claude, GPT, Gemini and Grok think differently and catch each other's mistakes. Why a model-neutral AI platform makes your team sharper and harder to stop.

Models6 min read

Your AI is going in circles. Here is how to get it unstuck

When AI keeps trying the same fix, asking harder rarely helps. Spot the loop, switch model, restart with a handover note or shrink the problem.

Ways of working7 min read

New tips in your inbox

One useful idea at a time for working with AI. No spam, leave whenever you like.