BI you can query in a sentence, on numbers you can trace
Can I ask questions of my data without building dashboards?
The BI layer reads the same posted ledger the rest of the product writes, so there is no ETL lag and no second version of the truth. Ask a question in a sentence and the engines answer it; the model only phrases the reply.
Every figure in a LekhaPro answer is computed before any model sees it. A router picks the deterministic engines the question needs, those engines read your posted books and return a structured snapshot, and only then is the language model given that snapshot and told to write the reply. Switch the model off and an on-device narrator writes the same answer from the same numbers.
Every figure remains traceable to the documents behind it, which is the difference between a dashboard you present and one you defend.
Who does what
| Step | Who does it | Can the model change it? |
|---|---|---|
| Read the posted ledger | Deterministic engine | No |
| Compute the figure | Deterministic engine | No |
| Choose which engines to run | Router | No |
| Write the sentence | Language model | Wording only |
| Propose an action | Named, validated tool | Drafts it; you approve |
| Write to your data | Existing audited mutation | Never unattended |
What it does here
- Answers ad-hoc questions without building a dashboard first
- Traces any figure back to the posted documents behind it
- Reports a business health score with contributing drivers
The boundary
- Reads your LekhaPro data. It is not a general-purpose warehouse for external sources.
- Cloud edition for the conversational layer.
Questions
Can I ask questions of my data without building dashboards?
The BI layer reads the same posted ledger the rest of the product writes, so there is no ETL lag and no second version of the truth. Ask a question in a sentence and the engines answer it; the model only phrases the reply.
Does the AI ever calculate the numbers itself?
No. A deterministic engine computes every figure from your posted books and hands the model a structured snapshot; the model writes prose about it. Turn the model off and an on-device narrator produces the same answer from the same numbers — which is the test worth applying to any AI accounting claim.
Can it change my data?
Only through named tools bound to existing audited mutations, argument-validated before they run, and every tool that writes carries an approval requirement. Nothing bypasses the permissions your user account already has, and every write is logged like any other.