In the rapidly evolving landscape of AI-powered solutions, there's a tendency to build platforms that promise to solve every problem across every business area. At DiligentIQ, we've taken a different approach. We're laser-focused on one critical area: post-signing, VDR due diligence in private markets through specialized generative AI.

DiligentIQ’s latest research explores the strengths and limitations of standalone Large Language Models (LLMs) like ChatGPT and Claude compared to our integrated platform. Our findings reveal a clear advantage: DiligentIQ delivers superior accuracy, relevance, and thoroughness, enabling businesses to access comprehensive insights...

DiligentIQ's new Agent Mode is our latest step in making Large Language Models (LLMs) work better for you. The Agent Mode feature adds an intelligent decision-making layer to query processing. At its core, Agent Mode acts as an intermediary, refining user queries and determining the most effective path for information retrieval and analysis.

In the expanding world of artificial intelligence, prompt engineering has become an important tool to obtain the best output. Prompt engineering is the process of optimizing prompts to improve the quality, accuracy, and relevance of responses. Large language models (LLMs) are sensitive to minor changes in prompts, proving that prompt...

In the fast-paced world of AI, it's crucial to grasp how our tools are evolving. Last month AI researchers, Lila Karl and Michael Van Demark, conducted a comprehensive analysis comparing the May and August versions of the ChatGPT-4 Omni model. Their findings reveal both significant improvements and ongoing challenges that are crucial...

At DiligentIQ, we are continually pushing the boundaries of data visualization and chart analysis through the integration of Generative AI. Spearheaded by Software Engineer, Michael Scoleri, our recent efforts have focused on addressing the challenges of accurately reading and interpreting charts using Large Language Models.

In the ever-evolving world of data analytics, the ability to create effective and insightful visualizations is crucial. At DiligentIQ, we leverage the Assistant API from OpenAI to enhance our Data Chat capabilities, making it easier than ever to generate high-quality charts and visualizations from datasets in xlxs files.

Stay updated with the latest in AI through this curated collection of articles, research, and innovations. Highlights include Andrew Ng’s course on advanced retrieval, emerging AI research themes, Anthropic’s legal protections, OpenAI’s prompt engineering guide, and DeepMind’s FunSearch. Discover AI's role in healthcare, legal models, video search

As if GPT4 API wasn’t enough to change the landscape, OpenAI is now rolling out Code Interpreter to all paid ChatGPT Plus customers over the next week (it will not available via the API). I’ve got it and it’s very cool. I feel like a kid in a candy store with $20 circa 1980s! It’s literally a magic box that allows you to upload data files...

2023 was a wild year in the world of Generative AI. It also has so much potential to dramatically impact business workflows (not to mention personal creativity) that with a strong nudge from Matthew Brandman, I came out of retirement and started DiligentIQ. We put together a team with deep PE and Credit industry knowledge...

This guidance from Anthropic for their top end model is fascinating: Adding the sentence “Here is the most relevant sentence in the context:” to the start of Claude’s response was enough to raise Claude 2.1’s score from 27% to 98% on the original evaluation.‍ Anthropic’s Claude is one of the major foundation LLMs alongside OpenAI’s GPT4.

Here we go again … Gemini is actually multiple products (similar to OpenAI’s GPT). It will initially be the “new” back end to Google Bard for consumers and the API is supposed to be available to developers and enterprise customers in early 2024. It’s designed to be multi-modal from the start. Things are going to get interesting...

Here are some cool custom instructions if you’re playing with chatGPT. This provides grounded and deterministic answers from the LLM. Copy the section after “What would you like chatGPT to know” into the top custom instruction and then the bottom section starts after “How would you like chatGPT to respond”...

As we ramp up our pilot clients at DiligentIQ, we are learning a lot about the art of constructing system prompts, prompt engineering to get at the right data, how 3.5 vs 4 behave differently, what temperature adjusts in a conversation and the different ways of embedding, chunking and meta tagging documents to discover...