Case

Fintech startup

Financials

Building a trustworthy investor relations AI chat

GenAI / agentsUser experienceNew business

Retail investors want plain-language answers about listed companies, and companies want to know what their investors are asking. A newly founded startup set out to serve both. Modulai built the entire GenAI pipeline and cloud backend, delivering a grounded, real-time investor chat in six weeks.

Outcome

6 weeks

From idea to production

1,000+

Listed companies supported

Challenge

Swedish retail investors struggle to interpret financial disclosures, annual reports, and press releases, while listed companies lack visibility into what their investors are actually asking. The startup set out to solve both with one platform. The hard part was trust: an unreliable investor relations answer does active harm, so responses had to stay fully grounded in approved public sources across 1,000+ companies, all on a fast launch timeline.

Solution

Modulai designed and built the GenAI pipeline and cloud backend: a streaming API, LLM integration, GCP infrastructure, and CI/CD. The chat streams answers in real time, discloses its sources, and suggests follow-ups. A system prompt is built per company, so the agent acts as an expert on whichever company is asked about, and it declines investment advice and off-topic questions. The design is provider-agnostic, currently running Gemini on Vertex AI.

Tools

The service is built on Python and FastAPI, streaming responses over Server-Sent Events. The production model is Gemini 3.1 Flash Lite on Vertex AI, using Google Search and URL Context tools to ground answers. It runs on GCP Cloud Run and deploys through GitHub Actions. Observability uses Cloud Trace with OpenTelemetry GenAI conventions for full audit logs, and quality is tracked with an offline RAGAS pipeline logged to Vertex AI Experiments.

Value created

For retail investors, complex financial information is now accessible in plain language, on demand. Going live let the startup begin collecting data on which questions arise and how sentiment shifts around earnings and announcements. Delivering the full AI component in six weeks got the startup to market faster than a typical custom build, and the provider-agnostic design avoids vendor lock-in, so cost and capability can be optimized over time.

Learn more

Related content

Financials

Building deep research AI assistants for an investment firm

Modulai built an agentic research system for a leading European investment firm that enriches reports by performing iterative research. It autonomously analyzes documents, reasons about potential gaps, and conducts structured investigations to surface overlooked insights and recent developments, providing a more complete picture for high-stakes decision-making.

Case

Financials

Forecasting future balances to identify high-risk customers and reduce credit losses

Modulai developed an interpretable, robust time-series forecasting solution for a major e-commerce checkout provider. By decomposing a complex credit-risk challenge into distinct ML subproblems, the system produced forecasts that enabled earlier detection of high-risk customers and reduced credit losses.

Case

Close-up of a cryptocurrency trading screen with candlestick charts and an order book, a stylus pointing at the chart.

Financials

Predicting a company's future financial performance

Modulai built a deep learning system that predicts a company's annual report one year into the future. By using a single transformer-based model that learns the interdependencies between financial features, it produces more consistent and accurate predictions than separate models for each KPI.

Case

Financials

Transaction risk model for a major online payment platform

Modulai built a transaction risk prediction model that processes millions of payments annually across thousands of e-commerce sites. The project covered feature engineering, model development, decision engine specification, and a full deployment plan, enabling the client to proactively contain financial risk across their payment network.

Case