A copilot that reads your books before it opens its mouth
What is an AI copilot for a business actually good for?
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 useful questions are the boring ones — how much GST do I owe, who owes me money, why did profit fall, what should I do this week. Each is answered by an engine that reads your posted books, and the model contributes wording only.
It can also propose an action: a follow-up task, a renewal reminder, an invoice against a contract milestone. Each is a named tool with an approval requirement. It drafts, you approve.
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 ledger questions in plain language
- Proposes actions you approve before anything is written
- Works from your permissions, never around them
The boundary
- Cloud edition. The Desktop edition uses the on-device narrator.
- It will say it does not know rather than invent a figure.
Questions
What is an AI copilot for a business actually good for?
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.