First week at Meta complete. Yes, really. This old dog, born long before the iPhone and social media, has joined the Kool Kids and will be “building the future of human connection and the technology that makes it possible.”
Read on for why I made the jump from Docusign and for my first impressions of Meta.
Continue reading “Old Dog Learns New Tricks”
My last day at Docusign is fast approaching, and what an experience it has been!
Let me take you back to January 2021: the UK is still reeling from the Covid-19 pandemic, Christmas has just been “cancelled” for many, and pubs are closed. It doesn’t get much more serious than that!
Continue reading “What is that over there?”
My photo library turns me into an intrepid explorer, spelunking through time and place. All those pictures of conferences and whiteboards become a treasure-trove of past lives, ideas and dreams. In this post I will take a look back over the past five years or so, from our “Smart Clause” mission as Clause.io, to the latest Intelligent Agreement Management developments at Docusign.
Disclaimer: I don’t make any promises about products, timelines or roadmap; that is not my role, and the past shows that progress is not a straight line, but is a meandering river — so don’t use any of this article to make purchasing decisions!
So, in the words of Eric Zenz, hop in my Deloren and let’s accelerate to 80 miles per hour!
Continue reading “Looking backwards to predict the future”
I repeated my experiment with the Miss Manners benchmark using Clause Sonnet (Clause 3.5 Pro). The results were the best I’ve seen so far.
Continue reading “Miss Manners with Claude Sonnet”
Docusign Extension Apps read data from systems of record and use it from Maestro workflows, or send signed PDFs to index, search and archive systems.
In this article I will show you how to create a Docusign Extension App that uses Auth0 for token-based authentication.
Continue reading “Docusign Extension Apps and Auth0”
Over the past few weeks I’ve been researching, and building a framework that combines the power of Large Language Models for text parsing and transformation with the precision of structured data queries over Knowledge Graphs for explainable data retrieval.
In this third article of the series (one, two) I will show you how to combine structured and unstructured semantic queries, and use LLMs to orchestrate question answering over a knowledge graph.
Continue reading “Knowledge Graphs: Question Answering”
This is a continuation of my previous article on creating a Knowledge Graph in 100 lines of code. In this article I will show you how you can use the “chat with your data” paradigm to convert natural language to graph queries, including using semantics search over vector embeddings.
Continue reading “Knowledge Graphs: Chat With Your Data”
The past couple of days I’ve been learning Zig, a relatively new low-level programming language, described by its creator as “a DSL for assembly”, and a potential successor to C.
Continue reading “Zig Programming — Trial by JSON”
I repeated my experiment with the Miss Manners benchmark using Clause Opus (Clause Pro). The results were better than GPT4, but inferior to Mistral (Large).
Continue reading “Miss Manners with Claude Opus”
Innovation That Matters 