AI that watches batch and expiry, not your compliance sign-off
Can AI help with pharma stock and expiry?
Expiry is the money question in pharma, and it is arithmetic: batch, expiry date, quantity and movement history. LekhaPro computes near-expiry exposure deterministically and the copilot tells you about it in a sentence you can act on.
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.
Nothing about a regulatory sign-off is automated or inferred. The system records what happened; a person still signs.
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
- Flags near-expiry and slow-moving batches before they are written off
- Answers stock, batch and MRP questions from posted movements
- Summarises purchase, sales-return and breakage-expiry positions
The boundary
- Not a regulatory compliance system — it does not produce or validate statutory pharma filings.
- Batch genealogy is recorded from what you post, not inferred.
Questions
Can AI help with pharma stock and expiry?
Expiry is the money question in pharma, and it is arithmetic: batch, expiry date, quantity and movement history. LekhaPro computes near-expiry exposure deterministically and the copilot tells you about it in a sentence you can act on.
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.