You can query Maxwell’s database directly from your current AI assistant, like Claude, OpenAI, CoPilot or Mistral.

You simply use Maxwell’s MCP (Model Context Protocol). This is allows AI models (like LLMs) to connect securely to external data sources. An MCP has been well-described as a "USB-C port for AI". So you don’t have to build an interface, you can just write a natural language query. Or even use the queries Maxwell has already written for users.

This refers to artificial intelligence systems designed to be safe, reliable, transparent and fair in order to respect ethical principles and legal regulations and so build users’ trust.

More than that, it is also an approach to interacting with users in a way that they can find the technology trustworthy in the same way as other real world systems, like government, academia and policing.

Building on our original academic research and real world experience of trust systems, we have designed Ask_Maxwell and Ask_Cameron to build trust in the same way as humans build trust. That is, which types of trust are most relevant in the situation, how much trust is enough for the user to make a decision, and how to reinforce and refresh trust over time.

An investment approach that generates long-term financial returns while actively supporting positive environmental, social and goverance (ESG) outcomes. It involves selecting companies with strong sustainability practices - such as low carbon emissions, good labour standards - to reduce risk and create a better world.

When preparing an assessment (ISSB, CSRD), guidance is clear: compare the entity in question to a peer group and a benchmark to give context. This is correct and sensible. But it's remarkably hard to do objectively, in a data-driven methodology, with an auditable process.

The reason is well-known in classical mechanics or astrophysics. It is called "The three body problem". It is the mathematical study of how three celestial objects (like stars or planets) interact purely through their gravitational pull. While a "two-body" system (like the Earth and moon) has predictable orbits, adding a third body (like the Sun) creates a chaotic, unpredictable system with no general mathematical formula to solve it.

In our terms, the reporting company is the Earth, the peer group is Moon and the benchmark is the Sun. Using publicly-available data from traditional, trade and social media correlated to closing day share price, we can build a materiality profile of a company (Earth), aggregate several peer companies to build a peer group's profile (Moon), and aggregate all the companies in a benchmark to build a benchmark's profile (Sun). The three profiles act on each other in a chaotic, unpredictable way. To be clear, we have a reasonable answer one, two, three month into the future but, beyond that, there is no way to predict the where the Earth will be. So we struggle to fully answer the question: "What is the most material sustainability topic for the company?"

With a grant from UKFin+ Network, Maxwell Data and Brunel University of London are working on this "wicked problem" over the summer through a number of proof-of-concepts. We will be convening an industry workshop in September at UCL Centre for Sustainable Business to review a potential industry standard solution.

• We believe in trustworthy AI so we make our methodologies publicly available.

• We believe that the best way to build a more sustainable world is to surface the metrics that prove real world performance.

• We believe that generative AI, used appropriately, is an ideal way for many users to interrogate and understand the data according to the questions they want answered.

In that way, capital will be allocated most efficiently to the most sustainable companies.

Getting started is simple. Use our contact to set up an initial conversation. We will walk you through the next steps with Ask_Maxwell or Ask_Cameron and answer any questions along the way.

You can reach us anytime via our contact page or email. We aim to respond quickly—usually within one business day.