Choosing an AI Assistant for Investor Relations: The Questions to Ask Any Vendor
The AI IR assistant market is young and the demos all look impressive. This buyer guide lists the questions that separate the systems: the source boundary, the edge test, citations, languages, question visibility, setup, and what deliberately is not included.
In short
Every demo in this market looks impressive, because fluent answers are the easy part. The differences that matter for a listed company sit underneath the fluency: what the system is allowed to answer from, what it does when it does not know, and what the IR team gets besides answered investors. This is the question list we would put to any vendor, ourselves included, grouped by what each question actually reveals.
Key facts
- Fluency is table stakes; the differentiators are the source boundary, absence behaviour, and citations.
- The most revealing minute of any evaluation is asking a question the company's materials do not answer.
- Question visibility, languages, and setup model decide the operational value beyond compliance.
- A serious vendor will also tell you what the product deliberately is not.
Which questions expose the source boundary?
Start here, because everything else depends on it. Ask: what exactly can the assistant answer from, and who controls that set? The safe answer is a defined body of the company's approved information, controlled by the issuer, with a clear route for material to enter and leave it. Follow with: can it ever reach outside that set, to the open web or its own training data, and under what circumstances? Any ambiguity here is the finding. Then ask how the set stays current: uploads only, or also a feed from your website and integrations with regulatory sources, and who verifies what entered.
The compliance logic behind these questions, why the boundary determines the disclosure risk, is covered in is an AI assistant on your IR website a disclosure risk.
What is the edge test, and why is it the most revealing minute?
Ask the assistant, live, a question you know your materials do not answer: a valuation multiple you never published, a forecast you never gave. There are only two behaviours. It says plainly that the published information does not cover it, or it produces something plausible. The second behaviour, however eloquent, is the failure: a system that improvises under pressure in a demo will improvise in front of an investor. Run the test more than once and rephrased; consistency of refusal is the point.
Pair it with the citation check: ask a question the materials do answer, open the citation, and verify it lands on the passage that supports the answer, not just on a document. Citations that resolve to real passages are what make the system auditable after the fact.
Which questions reveal the operational value?
Three areas. Question visibility: does the IR team see what investors ask, and in what form? The questions are market signal, and a system that answers investors without showing IR the questions leaves the more valuable half of the product on the table; why that signal matters is covered in what are investors actually asking. Languages: can investors ask and be answered in their own language while the source documents stay as published, and is the citation preserved across languages? For an international register this is daily value, not a feature checkbox. And setup: what does implementation actually involve, who does it, how long does it take, and what does the issuer maintain afterwards? Distrust both extremes: "instant" suggests nobody is checking what enters the source set, and a months-long project suggests you are buying consulting, not a product.
What should the vendor say the product is not?
A serious answer to this question is a strong signal in itself. An investor-facing answering assistant is not a data room, not a document or engagement tracker, not a file-sharing system, and not an analytics suite bolted onto a chatbot. A vendor who claims everything is describing a roadmap, not a product, and roadmaps do not pass compliance reviews. The boundary of what a product refuses to be is usually where its discipline shows; the same discipline you are testing with the edge test, applied to the company itself.
For the category definition underneath all these questions, what a source-grounded assistant is and why the constraint is the point, see what is a source-grounded IR assistant. MIRA is such an assistant, and we are happy to be evaluated against every question on this page.
The bottom line
Evaluate an AI IR assistant on what sits under the fluency: a source boundary the issuer controls, honest behaviour when the information is absent, citations that resolve to real passages, visibility of the questions for the IR team, languages that keep the citation intact, a setup model between "instant" and "endless," and a vendor who can say what the product is not. One live edge test tells you more than any deck.
Bring this list to a demo. Book a MIRA demo and run every question on this page against your own documents, including the one your company information does not answer.
About the author: Sander van Prooijen is Head of Commercial Strategy at Finvictum, where he leads the European rollout of MIRA and works with listed companies on AI-era investor communication. He has presented at Better Finance EU alongside speakers from Repsol, the European Commission, and DSW. Connect on LinkedIn.