Wednesday 12 July 2023

My real-world Microsoft Syntex demo videos - and a note on Copilot

I've written quite a lot about Microsoft Syntex AI on this blog and spoken about it at various conferences, and my firm view is that while the arrival of ChatGPT and Microsoft Copilots changes many aspects of how we work, neither fundamentally change the value Syntex can bring to an organisation. I recently gave a talk with the snappy title "AI choices for apps and automation in 2023 - understanding AI Builder, Azure Cognitive Services, Microsoft Syntex, and Azure OpenAI" at the excellent European Power Platform Conference in Dublin, and as you might infer, this covered Syntex alongside other options in the Microsoft AI toolbox. Along with some other fun conversations, I had feedback from a couple of attendees along the lines of "those Syntex demos are great, how could we show our colleagues?" - so this prompted me to get the videos narrated and uploaded to YouTube. Here's a shot from the conference by the way, it was a great event:

You can find these videos below. If you watch them, I'd suggest that listening to the voiceover or enabling captions will give you a better understanding of what's being shown. But while we're here, I think it's worth expanding on the the relevance of Syntex today - does Syntex get disintermediated by ChatGPT and Microsoft 365 Copilot, given their ability to directly answer questions of your documents and data?

Syntex in the era of ChatGPT and Microsoft Copilots

AI has always had a wide variety of tools and approaches, but for many it's more confusing than ever now - notably, I find some execs are conflating ChatGPT with AI in general, rather than seeing a broader pictire. Regarding Microsoft Syntex, it's certainly true to say generative AI like ChatGPT didn't exist a couple of years ago when Syntex was introduced - the AI landscape has truly changed dramatically in that time. So it's entirely valid to question how things fit together and whether the newer technologies remove the need.

In short, neither of those technologies diminish the value Syntex AI can add to a business - if anything, they will be increasingly used together, as Microsoft have shown with the Syntex plugin for Microsoft 365 Copilot.  

Syntex has unique capabilities when it comes to understanding what's in your documents and allowing you to derive insights and automate processes in which they are involved. Because Syntex is trained  specifically by a human on a representative set of your key documents (machine teaching, not machine learning) - it builds a greater understanding of the different variations, and ultimately a more granular comprehension of your documents. If you want to reliably detect (i.e. classify) which documents are which in your Microsoft 365 tenant - and this is powerful because contracts, board packs, proposals, statements of work, order forms, purchase orders, receipts, safety reports, risk assessments etc. are all very different documents used in different ways - Syntex is the technology to do that. Syntex is also the technology to extract the most relevant info from your documents, thus helping you to unlock data trapped inside documents and automate processes. The possibilities are endless, and Microsoft 365 and SharePoint have evolved to be an intelligent platform capable of so much more than simply allowing documents to be thrown in there.

The examples below try to give a flavour of this. They are both real-world scenarios from either inside my company (Advania/Content+Cloud) or work we've done with clients. While not shown in these videos, we also have a few more examples - such as implementing Syntex in the insurance industry to understand insurance policy documents and accelerate approvals. One powerful aspect of Syntex is that because it's AI rather than OCR (which looks for content in a specific place in the page or document, such as would be the case for invoices from one company), the AI has more intelligence and allows for a lot of variation within instances of the document. Consistency or uniformity between the documents is not necessarily required. 

Both videos have 1-2 mins of context setting before the demo starts.

Example 1: Syntex fundamentals - accelerating our SOW process

In this first example, we look at Microsoft Syntex AI fundamentals in a real-world process - bringing automation to our client engagement process at Advania/Content+Cloud. We run a lot of projects for our clients, and in each a Statement of Work is created to describe the work, it's scope, the project costs, and more. Syntex helps accelerate the weekly pipeline review of upcoming projects and creation of the engagement documentation. Take a look:

Example 2: More advanced Syntex - automating a risk assessment process

Where the first example focuses on identifying Statement of Work documents in our tenant and analysing the documents to understand the project pipeline, this next example relates to risk assessments - in this case, AI is used to automate the first pass of documents received by subcontractors. Syntex reads the documents and if certain information is not found, it automatically rejects the submission and e-mails the subcontractor - attaching the original document along with a message detailing the missing information. A Power BI analytics dashboard provides insights on the process and overall compliance levels. In this case, Syntex AI is taking the burden off a human team and ensuring they focus on the more complex/higher risk cases:


Hopefully those videos give you more insight into how Microsoft Syntex works and how it gets used in practice. As more emerges on Microsoft 365 Copilot (still not expected until end 2023 for General Availability), it's becoming increasingly clear that it is designed to work alongside Syntex rather than replace it. Any time a lower level of understanding of your documents is required than is supported by Microsoft 365 Copilot - and there will be many such scenarios as you pursue your AI and automation goals - Syntex will still be needed to provide that in-depth, process specific capability. Copilot will be able to call into Syntex if you have it, unlocking more scenarios such as asking questions of a document or asking Copilot to summarise the document based on Syntex capabilities. In other words, another example of the "better together" product story that Microsoft work hard on. 

You didn't think Microsoft were going to cannibalise one of their own products unnecessarily did you? :)