File sandbox
File profiling runs in an isolated container, without networking and with the main filesystem separated.
Secure AI
Business spreadsheets are not just any prompt.
Excel and CSV files contain customers, prices, defects, complaints, costs, suppliers and operational decisions. TalkToMyExcel puts a technical boundary around AI before generating an answer.
Boundary
Four controls before the answer.
Separate workspaces
Each user works on dedicated datasets, DuckDB storage and semantic index.
Controlled provider
Regolo.ai is the recommended choice for European inference, zero retention and no training on customer data, under the terms of the configured service.
Controllable context
The model receives selected evidence; users see estimated context usage and can clear the conversation.
Architecture
The model is not the data engine.
Filters, counts and calculations work on the imported data. During indexing, text from the selected descriptive fields is sent to the configured embedding provider to create the semantic index.
When an answer is generated, the model receives evidence selected by the engine, not the whole raw file. Results and tables remain checkable; source rows are shown when the analysis path makes them available.
Regolo.ai recommended
European sovereignty and zero retention for important data.
With the recommended Regolo.ai configuration, the provider does not retain prompts or outputs and does not use customer content to train shared models. Before production use, confirm the selected plan, contractual terms and effective configuration.
Details on Regolo.aiWhat to avoid
The difference from a generic chatbot.
Generic chatbot
- File copied into the prompt without structure.
- Provider chosen only for convenience or cost.
- Little visibility on retention and training.
- Answers difficult to trace back to rows.
TalkToMyExcel
- File profiled and imported as a dataset.
- Regolo.ai recommended for compliance and zero retention.
- Hybrid engine with selected evidence.
- Checkable results, sources when available and clearable context.
Assessment
Assess the most delicate use case too.
Start with synthetic or anonymized data; agree on scope, provider, roles and a secure channel before using real data.