Meet Lipik
An AI assistant for your practice — that keeps client data in India.
Lipik reads your firm’s documents, pulls out the figures and drafts working papers — so you spend the hour on judgement, not the three weeks on data entry. The model runs in India, never trains on your data, and the CA reviews, computes and files. A munshi for the modern practice.
Runs in India Never trained on your data You review, compute and file
What Lipik does
It reads, extracts and drafts. You decide.
Lipik takes the reading and re-keying off your plate and hands you drafts with their sources attached — the work a diligent junior would do before you pick it up.
Answers from your documents
Ask about a client’s file in plain language. Lipik answers from what your firm has uploaded — and cites the documents it used, so you can verify in seconds.
Pulls the figures out
Point it at a Form 16, a 26AS or a set of accounts and it extracts the values into a structured form — so you review numbers instead of re-keying them.
Drafts a working paper
It assembles a draft tax-estimate worksheet in Excel — labelled a draft for your review. The arithmetic is done in code, not guessed by the model.
Checks the latest rules
For a current due date or rate change, it searches the public web using a generic question only — never a client’s name, PAN or any figure — and shows its sources.
The data boundary
Your clients’ data never leaves the system.
Most AI tools ask you to trade useful answers for sending data somewhere you cannot see. Lipik is built to avoid that trade — four guarantees make it hold.
Powered by Sarvam — sovereign AI, built and hosted in India
The model runs in India
The AI that reads your documents runs on Sarvam — sovereign AI hosted in an India region — under terms that keep processing in-country. Nothing is shipped abroad to be read.
Never trained on your data
Your firm’s documents are not used to train, tune or improve any model. What you put in answers your question and nothing else — no retention for model-building.
Documents and index stay sealed
The private search index and the documents themselves sit in encrypted storage in India, isolated to your firm alone — one firm’s data is never visible to another.
Web search is scrubbed
The only thing that ever leaves is a generic public question; a guard removes anything resembling a PAN, Aadhaar, email or phone number before a search goes out.
What stays your job
Advisory, not autonomous.
Lipik does not compute or file returns, and it is not a tax, audit or legal adviser. You continue to compute and file wherever you do today; every figure it surfaces is a draft for you to verify, and every worksheet says so.
We named it after the munshi — the scribe — on purpose. A scribe prepares the record; the principal reads it and signs. That is the relationship we want you to have with it: it prepares, you decide. The professional judgement, and the responsibility, stay yours.
Questions
The questions every firm asks first.
Does my clients’ data leave India when I use Lipik?
No. The model that reads your documents runs in an India region, the documents and their search index are stored in India, and embeddings are generated in-region. The only outbound request is a web search for a public rule, which carries a generic question with all client identifiers stripped out.
Is my firm’s data used to train the AI?
No. Lipik runs on an in-region model under no-training, no-retention terms. Your documents are used only to answer the question you ask, and are not used to train, tune or improve any model.
Does Lipik compute or file tax returns?
No. Lipik is advisory. It drafts working papers and surfaces figures for your review; you continue to compute and file in your own software (Winman, Computax, KDK, or the income-tax and GST portals). Tax arithmetic in its drafts is done in code, not by the language model.
Can my clients use Lipik?
No. Lipik is a tool for the CA team inside the firm’s admin workspace. It is not exposed to your clients, and it is not a tax, audit or legal adviser.
How is one firm’s data kept separate from another’s?
Every firm’s documents, search index and conversations are isolated at the database level by tenant, so one firm’s data is never visible to another. This is enforced by row-level security and verified by an automated isolation test on every change.
See Lipik inside your own branded portal.
We’re rolling it out firm by firm. Book a demo and we’ll show you how it reads a document, pulls the figures and drafts a worksheet — without anything leaving India.