An AI ERP whose numbers are not written by the AI
What does "AI ERP" actually mean, and can I trust the figures?
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.
That distinction is the whole product. An ERP that lets a language model compute your closing stock or your tax liability has produced a number nobody can defend in an audit. LekhaPro treats the model as a writer, never as a calculator: the ledger, the valuation method, the ageing buckets and the tax splits are all engine output, deterministic and reproducible.
The AI surface spans the modules you already run — sales, purchase, inventory, receivables, GST — because it reads the same posted data those modules write. There is no separate AI database and no training on your books.
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 plain-language questions about your own posted ledger
- Explains a movement — why profit fell, which customers are drifting
- Proposes actions as named, permission-checked tools you approve
- Writes an executive morning brief from the same engines
The boundary
- The model never computes a figure. If an engine has no answer, the reply says so rather than filling the gap.
- Cloud edition for the full copilot. The offline Desktop edition ships the deterministic engines and the on-device narrator, not a hosted model.
- No payroll or HRMS data, because neither module exists.
Questions
What does "AI ERP" actually mean, and can I trust the figures?
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.