How an AI agent can turn investment research context into a structured brief with comparisons, risks, assumptions, and follow-up questions
This workflow gives an AI agent a defined job, a bounded set of records, and a result a person can review. The agent reads the relevant Morningstar context, applies the rules in the prompt, and keeps the source behind every recommendation. It returns a proposed handoff rather than taking consequential actions on its own.
Can an AI agent turn investment research context into a structured brief with comparisons, risks, assumptions, and follow-up questions?
Yes. Start with the scope, date range, decision rules, and fields that identify the right records. The agent can collect the evidence, compare states or sources, mark conflicts and missing data, and organize the result around the outcome above. A reviewer then checks the matches and judgment calls before approving messages, record updates, bookings, purchases, publishing, or other write actions. The guide below shows the records, boundaries, prompt, and handoff needed for this specific workflow.
What this agent helps you do
A Morningstar investment research agent helps organize available fund or investment context into a structured comparison. It can summarize observations, risks, and questions for an analyst.
When to use this workflow
Use it before portfolio reviews, fund screening, client research preparation, or investment committee discussions. Keep final decisions with qualified humans.
How Morningstar gives the agent context
Connect the plugin and define the tickers, funds, peer set, or research question. Ask the agent to distinguish data points from recommendations and to flag missing context.
Example starter prompt
Prepare a Morningstar research brief comparing these funds. Summarize available data, key differences, risk questions, assumptions, and follow-up research needed. Do not provide personalized investment advice.Suggested workflow steps
Define candidates, gather research context, compare relevant dimensions, identify risks, and prepare follow-up questions. The agent should explain confidence and data limitations.
Record the Morningstar identifier, share class, data date, currency, category, and benchmark for every fund. Keep observed measures separate from the analyst’s interpretation and from any suitability decision.
Expected handoff
The output should include a comparison table, summary, risk notes, and next research steps. It can feed an analyst memo or review meeting agenda.
Questions this workflow answers
Could an agent prepare an analyst-ready brief on selected investments without turning incomplete data into a buy or sell recommendation?
Yes. Define the securities or funds, investment question, as-of date, currency, benchmark, time horizon, and measures the analyst wants reviewed. Morningstar supplies available profile, performance, risk, holdings, valuation, and category context. The agent organizes those records into an evidence brief and leaves professional judgment to the analyst.
Identity comes first. Share classes, tickers across exchanges, renamed entities, and similarly titled funds can produce a wrong comparison. Ask the agent to preserve the exact identifiers, period, units, and source field behind each figure. Missing values, stale dates, and calculated measures should be labeled rather than filled with estimates.
The brief can describe differences in objective, exposure, concentration, historical behavior, fees, and reported risk. It should avoid presenting historical correlation or performance as a forecast. A surprising value becomes a follow-up question and source check, not an automatic insight. If the selected measures do not answer the investment question, the agent should identify the gap.
The final handoff contains an executive summary, evidence table, tradeoffs, risk notes, caveats, and next diligence steps. A qualified analyst verifies the data and applies mandate, suitability, tax, and market context. The agent reduces collection and comparison work without making an investment decision or disguising incomplete evidence as certainty.
The research question determines which facts belong. A brief about income reliability needs distribution history, yield methodology, holdings that drive income, fees, and any return-of-capital concern. A brief about downside behavior needs comparable drawdown periods, portfolio concentration, duration or factor exposure, and benchmark context. The agent should not fill both reports with every available metric. It can explain why a measure answers the stated question and put attractive but irrelevant numbers in an appendix or omit them. That discipline gives the analyst a trail from question to evidence rather than a profile page rewritten as prose.