Investor RelationsSeptember 25, 20266 minutes

What Is a Source-Grounded IR Assistant, and Why Now?

A source-grounded IR assistant answers investor questions using only a company's own approved, published company information, citing each point back to the source. Here is what that means, how it works, and why it matters now that investors research through AI.

In short

A source-grounded IR assistant is a tool that answers investor questions about a company using only that company's own approved company information, and cites each point back to the source. The company decides what that information includes: financial reports and press releases, but also presentations, site pages, FAQ answers, and other material the issuer chooses to add. It does not draw on the open web or general commentary, and when the approved information does not cover something, it says so rather than inventing an answer. The reason it matters now is that investors increasingly research companies through AI, and this is the way a company can meet that shift with answers it controls and can stand behind.

Key facts

A source-grounded assistant answers only from a company's approved company information, not the open web.
Which sources count is the issuer's call: reports, releases, presentations, site content, FAQs, whatever the company chooses to add.
Every point it gives is cited back to a specific source.
Where the material is silent, the assistant says so instead of improvising.

The term "AI assistant for investor relations" covers a wide range of tools, and they are not all the same. The distinction that matters is not how fluent the answers sound, but where they come from. A source-grounded assistant is defined by a single constraint: it can only answer from the company information the issuer has approved. That constraint is the whole point, and it is what separates it from a general AI model pointed at a company.

What does "source-grounded" actually mean?

It means the assistant is restricted to a defined set of approved company information, and cannot answer from anything else. That set is broader than regulatory disclosures alone, and it is the issuer who decides what goes in: annual and interim reports, press releases, investor presentations, website content, FAQs, and any other material the company wants investors to be answered from. When an investor asks a question, the assistant retrieves the relevant passages from that set, answers in plain language, and attaches a citation to the source behind each point. If the answer is not in the approved set, it does not improvise one.

This is different from a general AI model, which draws on whatever public material it can find and blends it into a fluent answer; where it cites, the citations usually point to third parties writing about the company, not to the company's own record. Source-grounded means the boundary is fixed by the company, not chosen by the model, and the company can widen or narrow that boundary at any time.

How does a source-grounded IR assistant work?

Mechanically, it has two halves: the source, and the retrieval. The source is a controlled body of the company's own information, assembled through three routes. Material the company uploads and approves directly, which can range from annual and interim reports and results releases to investor presentations, FAQs, and other documents the issuer wants included. A live feed from the company's website, set up per client, that keeps the source current as new material is published. And integrations with third parties such as regulatory sources, so official filings flow in without manual handling.

The retrieval half is what happens at question time: the assistant finds the relevant passages in that source, drafts an answer from them, and links each statement to the document it came from. The design consequence worth understanding is legal, not technical. Because the assistant only ever repeats material that is already public, worded as the company worded it, it is not making new statements about the company. That is why it does not create new disclosure risk: there is nothing new to disclose.

Why does a source-grounded IR assistant matter now?

Because the way investors gather information has shifted. A growing share of investors and analysts research a company through AI tools before they ever make contact, and those tools answer from whatever sources they can reach. A company that does nothing leaves that first impression entirely to systems it does not control.

A source-grounded assistant is how a company meets that shift on its own terms. Instead of hoping a general model reaches the right material, the company gives investors a direct way to get answers drawn only from its own record, cited, on its own channels. The timing is not about the technology being new. It is about investor behaviour having changed enough that leaving the answer to chance now carries a real cost.

How is it different from a general AI model or a chatbot?

The difference is the source and the honesty about limits. A general model is built to always produce an answer, filling gaps with plausible text when it lacks material. A simple website chatbot usually follows scripted rules and cannot handle an open question. A source-grounded assistant sits between neither: it answers open questions in natural language, but only from approved company information, and it declines to answer beyond them rather than inventing.

That last behaviour is easy to underrate. An assistant that says "the filings do not address that" is more useful to a listed company than one that produces a confident guess, because a guess about a listed company can become a problem. Restraint is a feature here, not a limitation.

What should an IR team look for when evaluating one?

Most of these tools will demo well, so the useful test is to probe the edges rather than the happy path. Three questions separate a genuine source-grounded assistant from a general model with a company logo on it.

First, hand it a question your published information genuinely does not answer, such as a forward valuation or a target you have never published, and watch what it does. Inventing a plausible figure is a fail; saying the filings do not address it is a pass. Second, take any answer and try to trace it back: can you reach the exact document and passage behind each claim, or is the citation decorative? Third, ask to see the log of what investors have been asking, because that visibility is part of the product and a general tool cannot offer it.

Those three, behaviour at the edge of the source, traceable citations, and question visibility, tell you more in ten minutes than any feature list.

The bottom line

A source-grounded IR assistant answers investor questions strictly from the information a company has approved and published, cites each point, and is honest about what that material does not cover. With investor research moving into AI tools, it gives a company one channel where the answer is verifiably its own. The value is not fluency, it is the fixed source boundary and the citation behind every line.

MIRA is an investor relations assistant that answers investor questions from a company's own approved, published company information, part of the Finvictum group's tools for direct, compliant communication between companies and their investors.

More insights

Investor Relations

Why Does AI Give an Incomplete Picture of Smaller Listed Companies?