Enterprise AI that keeps your keys and your audit trail
Is AI in this product safe to put enterprise data through?
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.
The enterprise questions are about control, and each has a concrete answer. Every AI action that writes is a named tool bound to an existing audited mutation, argument-validated before it runs, and gated behind an approval — only read-like refreshes run unattended. Nothing bypasses the permissions the user already has, and every write is logged like any other.
Bring your own key: the model provider is configurable, and turning the model off leaves the deterministic engines and the on-device narrator working.
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
- Binds every write to an audited, permission-checked mutation
- Requires approval for anything that changes data
- Runs on a configurable model provider, or none at all
- Logs AI-initiated actions in the same audit trail as manual ones
The boundary
- AI features are Cloud-edition; the Desktop edition runs the engines and the local narrator.
- Single sign-on and multi-factor authentication are not yet shipped.
Questions
Is AI in this product safe to put enterprise data through?
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.
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.