A private AI platform lets an asset or wealth manager ask questions of its own portfolio data and documents on infrastructure it controls, not in a public chat tool. It answers with citations, converts currency exposure, tracks obligations and drafts memos. The firm chooses the model, sets the permissions and keeps the audit log.
It is an AI assistant that runs where the firm decides: on its own servers or in a private cloud. It reads the firm’s holdings, analytics and documents, and it answers inside the firm’s own permissions.
The difference from a public tool is custody. The firm decides where the data sits, which model answers, and who can see what. The record of every question stays with the firm.
Yes. In Super Chain the firm sets the model per organisation with three fields: a base URL, an API key and a model name. That can be a model the firm hosts itself or a provider it has contracted with. The firm, not the vendor, makes that choice.
It does not take the firm outside the rules. It makes the controls easier to show. In general terms:
Hong Kong. The SFC expects licensed firms using generative AI to manage risks including leakage of confidential information (SFC, 12 November 2024). Personal data stays under the PDPO, and the PCPD’s AI Model Personal Data Protection Framework sets out how to procure and use AI with it.
United Kingdom. FCA rules apply to AI as to any other system, and the FCA’s review notes firms keeping logs and audit trails of AI interactions (FCA, October 2026). Personal data falls under UK GDPR; the ICO publishes guidance on AI and data protection.
United States. Regulation S-P requires registered advisers and broker-dealers to safeguard customer information, and the 2024 amendments add incident response and customer notice duties (SEC, 16 May 2024).
For when on-premise becomes a requirement, market by market, read on-premise AI for wealth management.
It handles the questions an investment team asks every week, from the firm’s own data. Below, a manager asks for CHF exposure across vehicles and a one-page IC memo. The data is synthetic.
Five jobs it does today:
An investment committee will not act on a figure it cannot trace. Four controls carry the weight:
With one vehicle and one set of real questions. Load that vehicle’s documents, connect its portfolio data, and check the first answers against the cited pages with the person who owns them.
Super Chain is running at a family office on its own infrastructure. For obligations and covenants, read AI covenant and obligation tracking; for the full flow, read how Super Chain works; and to plan where to start, book a 30-minute AI implementation plan.
This guide is for asset and wealth managers, multi-family offices and fund teams in Hong Kong, the UK and the US who want AI on their own portfolio data and documents, and cannot put client files into a public tool.
It is not a trading or execution system, and it does not replace the portfolio management or accounting system. It reads from them and answers questions; decisions and orders stay with people.
Super Chain is accountable for the platform and its configuration. The office remains accountable for which documents go in, who may see them, and the terms of the model provider it chooses.
Super Chain is built by Super Cat Technology. The same team built a fully on-premise retrieval system for a Big 4 firm, where every answer returns with its source paragraph.
It is an AI assistant that runs on infrastructure the firm controls, such as its own servers or a private cloud. It reads the firm’s portfolio data and documents, answers with citations, and works under the firm’s own permissions. The firm chooses the model and holds the audit log.
Yes. The model and the data can sit on infrastructure the firm controls, and the firm chooses which model provider, if any, its questions reach. That keeps client files out of consumer chat tools. It does not remove the firm’s duties under data protection and conduct rules; it makes them easier to show.
It answers portfolio questions from holdings and analytics, converts currency exposure, searches fund documents with page citations, tracks obligations and deadlines, and drafts Word, Excel or PowerPoint files such as an IC memo. A person reviews each file before it is saved to the firm’s document vault.
Check the citation. Each answer from documents links back to the pages it used. When figures come from a connected data source set up for figure checks, Super Chain compares them with that source’s results and removes any sentence stating a figure it could not find, with a note saying so.
Only people with access to the underlying folder. Folder permissions decide what each person can read, and the AI searches only what that person may read. A file the AI drafts in chat stays visible to its author alone until it is saved to the vault, where the folder’s rules apply.
A 30-minute call with our team. We look at where your firm uses AI today, which documents and systems it would touch, and where it should run. You leave with a plan: what to start with, what to keep out, and which deployment fits. It is free.
Choose a time below. If you would rather see the platform first, book a private demonstration.