Byte-sized AI: Say hello to Claude
I’m back for another Byte-sized AI issue, and as promised here are my three things: 😁
- Something techy from the news
- Something that made me laugh
- Something that you can do to improve how you work
And, below is a cheeky plug to a webinar that I am doing with the Kent Invicta Chamber of Commerce, join me on the 16 January. 😉
📰 The one item of news:
My new friend Claude
For the more technical parts of my job, I use an AI called Claude, which was created by Anthropic. Amazon are big backers of Claude, and they have just rolled out the latest version, known as Haiku 3.5, for all users including the free service.
I wouldn’t give Claude data to read, but it can be really good at coming up with ways of thinking about things, and for those of a more code-y mindset it can lay out the syntax of quite complex structures for you. And of course, if you’re working with public domain knowledge it’s fine.
For example, if you wanted an Office Script for use in Excel you can describe what it should do and reference cell addresses or tables named “Table1” or similar without sharing anything confidential with it.
See? And you thought I was all about the Microsoft world!
😂 The one thing that made me laugh:
Not this time!
On this occasion, it’s something that didn’t make me laugh. At all.
In the spirit of the season, I asked Copilot for three jokes that connect AI to Christmas:
- Why did the AI get a Christmas tree? Because it wanted to branch out!
- What do you call an AI that loves Christmas carols? A neural netcracker!
- Why did Santa’s sleigh get an AI upgrade? So it could sleigh the competition!
🤦Grim. Sorry, but the Nutcracker is not a Christmas Carol. I had to endure those jokes, so it seems only fair that you should too!
Prompt: A Christmas card from a small British technology company to all its customers
💡 The one thing you can do next week:
SharePoint metadata columns
OK, I accept that this isn’t exactly ‘fun’. But it is pretty useful.
In a SharePoint document library you can add columns to store additional data. The traditional way to do this is with folder structures, so perhaps a sales team might have a folder per customer, then a folder for each of proposals, contracts, amendments and budgets. With metadata you can stick it all in one folder!
For the example above, I would add two columns – the first a list of customer names, and the second a list of document types. Then you can go to the same folder every time and simply filter the columns to show, for example, ‘proposals for McDonalds’ or ‘Budgets for Sainsburys’. It’s quicker and easier than trying to remember a complex folder structure, but better than that you can now use Copilot agents to do the filtering for you, and to answer questions like “How many proposals have I done for McDonalds?” or “How old is the latest budget for Sainsburys?” or “What’s the typical air speed of a migratory swallow?” (it might struggle on the last one unless you have documents about that sort of thing).
If you are interested to find out how AI, automation and all things clever can help your organisation why not take a look at Future Workplace, our super special IT consultancy service that can supercharge productivity, business efficiency and so much more.
Subscribe to Byte-sized AI
Check out past Byte-sized AI issues:
- Byte-sized AI: The machines have taken over Sainsburys
- Byte-sized AI: An extra brain in the room!
- Byte-sized AI: Up, up and… back down! 😕
- Byte-sized AI: Something special is happening in the UK!
- Byte-sized AI: A llama with AI and an admission!
- Byte-sized AI: Granny is here to make it all better!
- Byte-sized AI: Say hello to Claude
