As we go through the AI era, Microsoft continue to embed generative AI into the Microsoft 365 user experience in interesting ways. If you’re a Copilot user like me, you’ll most likely appreciate the capabilities in chat and meetings of course, and Copilot in Word and PowerPoint can be powerful for document work - drafting new content, rewording and enhancement, summarisation, identifying key points, and performing analysis on the text are all tasks Copilot can do well. But these are all single document scenarios – one consideration with Copilot is that there’s no way to process lots of documents in bulk, but for some use cases that’s exactly what you want to do. If you could effectively “run the AI” over many documents without having to open each one and type a prompt, this unlocks AI being applied to many processes and workflows. I list some examples below, but to call out one – the idea of having a 3-sentence summary displayed next to each document could be powerful. How many documents would that save you opening per week as you go looking for something? Or what about asking AI for the broad type of document (perhaps from some pre-defined categories), so you had more context than just the filename and location? There are lots of ways AI can be useful with documents in a ‘pre-processing’ way, where the AI has done it’s work before you come to the document.
The realisation is that Copilot itself cannot easily be automated. While the new Copilot Actions capability brings a certain level of this, the concept there is more about a scheduled prompt rather than something to run across your files. In terms of other options, a more technical maker could create a Copilot agent and find a way of looping through lots of files to do something with AI – but that’s not something most employees will do.
Microsoft have thought about this and have introduced a ‘built-in AI’ capability for files in Microsoft 365 – it’s part of the SharePoint Premium/Microsoft Syntex capability and is called autofill columns.
The idea is that you can run an AI prompt across every file in a SharePoint library and have the result stored in a column next to the document. You’re essentially passing each file automatically to a GPT model with the prompt of your choice. This offers a powerful new AI approach in how we manage information – I can foresee that every content management app and platform will have this in the future. As far as I can tell, Microsoft are the first to weave the capability into a core platform in this way.
Here are my top uses for SharePoint autofill columns – many of which you'll notice are forms of metadata generation:
- Document summaries – the full document summarised automatically in your preferred format (e.g. 3 bullet points, a few sentences etc.)
- Key takeaways – a summary focused not on the full document, but the conclusions only
- Key info extraction – identify the client/project/business unit this file relates to
- Key info extraction – list the people/organisations/concepts/[something else] mentioned in this document
- Classification – categorise the document, either generically or according to a list you provide (e.g. into “RFP”, “proposal”, “statement of work”)
- Automated assessment - based on the contents of the document, should this be approved or sent for human review?
- New info generation – based on the contents of the document, how does it correspond to X?
Of course, all those are quite generic approaches – even more powerful examples can come when dealing with specific document types. You might consider asking AI to extract contract values and start dates from contracts, to analyse the same contracts for specific risks, or to synthesise the key themes from research papers for example. There are lots of interesting possibilities arising here - we’ve had ways of automatically extracting information from or classifying documents before (in the Microsoft world, that’s where Syntex started), but nothing with the capabilities of today’s GPT-based AI models. If you're familiar with Microsoft Syntex, it's fair to see autofill columns as the new way of implementing many AI document understanding solutions in Microsoft 365 - a shift away from the 'machine teaching' Syntex approach of training a model to understand your document and then supplying some positive and negative examples - to something which uses GPT powers to understand the document via your prompt without the need for training. That said, the original approach will still suit some scenarios better and in some cases combining the two might be the best thing - nothing is going away at this point from Syntex.
Examples of autofill columns in action
As one example, let’s see what happens when we ask SharePoint to automatically summarise a bunch of project statement of work documents. These are real documents from my work at Advania but with client names redacted. In each case, the column on the right is what AI has generated.
Prompt:
“Summarise the project that this document relates to in around 200 words or less. If possible, provide any key dates or expected durations.”
Result:
So auto-generated AI summaries work great and can be very powerful, but as per my earlier list you can imagine lots of other prompts too - document classification, extraction, and analysis all have interesting possibilities.
Because autofill columns can work on images too, the capability can be used to solve one of the big challenges with images – search engines don’t work well with them because by default there’s no description or tagging.
Prompt:
“Describe the image, giving as many details of the context as possible.”
Result:
That’s pretty incredible in terms of image recognition (and all down to GPT-4 Turbo’s multi-modal capabilities), with the model even recognising that it can’t fully read the text on the road signs in the first image. Imagine if every image stored in SharePoint got an automatic text description and set of image tags – the impact on searchability alone would be huge.
Some other examples might be:
- What is the nature of the complaint in this document?
- Identify the main theme of this piece of event feedback into “optimism”, “constructive”, “appreciation” or “collaboration”
- Score the agent’s performance in terms of helpfulness and ability to resolve the caller’s issue between 1-5 (with 5 being the highest), and give your reasoning
- Propose a decision on this customer loan application based on the credit history and other background information in the file
I have ideas already! Should I apply autofill columns everywhere in Microsoft 365?
To my mind, a few interesting questions emerge - such as:
- Does this cost more, less, or the same as other AI tools I could use?
- How do I control costs?
- Documents are changing all the time in Microsoft 365 – does the AI run each time a document somewhere is edited and saved? That could cost a fortune!
- What types of files can the AI run across?
- Which languages are understood?
- If I have a have a document library with a million documents in and I create a “summarise this” autofill column, will all the existing files be processed?
Practical considerations for autofill columns
Summary
- Leon Armston also has a great article on autofill columns, covering potential uses and considerations - Game Changer: Autofill columns Now Available in SharePoint Premium - Leon Armston's Blog
- Microsoft documentation for autofill columns - Overview of autofill columns Microsoft Syntex - Microsoft Syntex | Microsoft Learn
