Hi AI explorers :-) I have been working on a practical Copilot Guide - if you are working with MS copilot, check it out. There are 12 features explained with screenshots and some example use cases: https://www.notion.so/Microsoft-Copilot-Tips-Tricks-For-Non-Techies-2a1e97442c0e802bb540e61056803cb8?source=copy_link

I know most of you are very busy, so oftentimes you might not have the time to watch a 1h-video etc. So from time to time I will share these tips for quick wins, that you can try immediately WHILE doing your job. Here go the 3 for today: https://foil-crocodile-f76.notion.site/3-Lazy-AI-Tricks-That-Actually-Work-29de97442c0e8069b074fe2c21309844?pvs=143

There’s a major AWS outage right now that’s taking down lots of cloud services — news outlets report Perplexity, Canva, Fortnite, Snapchat and others are affected. Reuters+1 If you use AI tools that run on AWS (for example Perplexity), you may see slow responses, errors or temporary unavailability. Business Insider+1 What to do: - Save any work you can and retry later. - Check live status pages: AWS Health, Perplexity status and Downdetector for updates. AWS Health+2Perplexity Status+2

As a non-techie AI trainer I know that it can be hard to build complex solutions, even with no-code tools. I have no coding background, and still manage to build even AI Agents in N8N that save me hours every day 🤩 So, here go a few general tips: - always start simple, add complexity as needed - use AI to help you - I have a custom GPT for building AI agents and automations in N8N that guides me through the hard parts (link shared below, try him out!) - use templates! People keep sharing them on social media etc. - you don't need to reinvent the wheel - don't give up! - And don't let anyone tell you that a non-techie cannot do it. Build, experiment, improve! Here goes my James Bond (agent builder) 🙃: https://chatgpt.com/g/g-68388038230881919e24b5b6ff0ee42f-james-bond Any other non-techies here?

A pure LLM will only take its best guess at the answer to your question. That means that if it's supposed to calculate, it will probably get it wrong. UNLESS it uses code. So, when asking your LLM to analyze data or calculate something, make sure you put the phrase "use code" into the prompt. That's it! An AI developer sold me that trick, and today I saw it in action for the first ime, when working with Copilot + activate ChatGPT 5. Without this phrase it was not able to calculate, adding "Use code" made all the difference. Try it and let me know :-)