Finance · Financial sector and investors
AI for finance: market data in real time
News, research, chats, and private documents flow into a base you query by asking, with an answer and its source.
- Client
- Financial sector and investors
- Sector
- Finance
- Product
- Finora
In numbers
The initial problem
The market produces data minute by minute — news, reports, chats, audio, private documents, and investor signals — and information overload delays analysis and increases the risk of reactive decisions.
The previous process
Analysis required manually reviewing multiple scattered sources (messaging, specialist sites, PDFs, and presentations) before a view of the market could take shape.
The solution implemented
Crawlers and automatic ingestion from WhatsApp, Telegram, specialist sites, TradingView, PDFs, and presentations; cloud processing and a RAG agent to query assets, scenarios, and market context in natural language.
How we did it
Source map
We identified which channels the team actually watches — messaging, specialized sites, in-house research — and set up automatic ingestion for each.
Processing and normalization
All material, including PDFs and presentations, is processed in the cloud and indexed with its origin and date.
RAG agent over the base
Queries are made in natural language and the agent answers from the indexed material, citing where each figure comes from instead of inventing it.
Integrated systems
- Telegram
- TradingView
- PDFs and presentations
- Cloud
- RAG
The result
A consolidated view, immediate access to relevant information, less information overload, contextual analysis, and faster, better-founded investment decisions.
What changed in the operation
- Market tracking no longer depends on reviewing source by source.
- Queries are answered over the firm's own material with identified origin.
- The team's private research becomes available to the whole team.
- Analysis reaches the investment decision sooner.
Frequently asked questions about this case
Does the agent make up answers?
It answers from the client's indexed base and shows the source of each figure. If the information isn't in the loaded material, it says so instead of filling in.
Can the team's private documents be added?
Yes: reports, PDFs, presentations, and internal notes live alongside public sources within the same query base.
Where is the data hosted?
In the cloud the client defines, with role-based access. The architecture allows deploying the entire workflow within their own environment.
Keep exploring
Other work by the team, across different sectors.
Commerce and business managementCRM and Odoo connected to the business
Bidirectional connectors between Odoo and critical systems, plus an intelligent CRM that answers business questions.- Bidirectional sync
- Queries without IT
- Deployment in your cloud
EnergyAI applied to energy regulation: anticipated regulatory impact
Continuous ingestion of legislation, news, and socioeconomic context, with models that anticipate the impact on costs.- Continuous regulatory ingestion
- Correlation with costs
- Impact scenarios
AccountingAccounting automation with AI and tax filings
A workflow that receives, reads, validates, and files the firm's source documents with no typing, plus missing-item alerts per client.- Reading with OCR and AI
- Validation against ARCA and banks
- Alerts for missing documentation
Tell us which process you'd like to improve
We'll look at how it works today and send back a concrete diagnostic: what to automate, how, and what result to expect. No cost, no commitment.