Month: October 2023

I listened to a podcast interview with Christian Lanng (Christian Lanng: “How Being a Founder Almost Killed Me”  | E1065) about his next thing with Beyondwork and them trying find out what that means.

Christian says that he doesn’t want a future where a Clippy has to talk to a Clippy which talks to another Clippy and so on. In this context Clippy is some sort of an “AI” which can provide some answer.

I don’t know if that is true or not or if it’s the future we want or not – but right now, that seems to be where we’re headed.

• LangChain is about chaining prompts and answers together so that we can get better answers
• Microsoft Copilot Plugins is about enabling Microsoft Copilot to extend your prompts to other systems and consolidate the answers and perform tasks on your behalf
• Microsoft TypeChat is about providing types and structure to the data we want to pass between systems to make interoperability even easier and more precise

I’ve spent the first 20 years of my life as a developer and the last 20 or so as an “architect” in many different contexts and it almost always boils down to solving integration between business domains and figuring out how data can be accessed, translated and acted upon across the different domains either in real time or before some date and time.

I totally agree with the sentiment that most, if not all, business systems are really just a database with a UI on top and that actual business value comes from combining the data across all systems and extracting answers from it. However, as long as the “business” continues to lock data in silos and refuses to adapt business processes to standard systems and demands customization of systems to accommodate the last 20% of functionality in a way that almost makes integration impossible – then I think the Clippies are going to be around for some time to come.

I think short to medium term the scenarios with plugins to Microsoft Copilot (and similar) will prove valuable to most businesses. Longer term we still need to fix copyright (AIs will be stopped from scraping), privacy (business are scared of leaks) and authentication/authorization (who are you and what do you have access to across boundaries). For instance how can we safely solve problems where data is scattered across private and public domain.

It’s going to be interesting and some new rules/processes are going to have to be worked out.