What we build

Custom ERP, CRM and operations systems

We build the operational system a business runs on — clients, vendors, workers, orders, projects, purchasing, inventory, production, freight and finance — on one data model instead of a stack of disconnected tools. We model the business first; that model becomes the specification. Built so far for boiler manufacturing, PCB and electronics trading, and interior design.

Who it's for: Any business that has outgrown spreadsheets and off-the-shelf software — where a few people are the only ones who know how everything connects.

Systems built

4, for 4 client businesses

Industries

Boiler and pressure-vessel manufacturing, PCB and electronics trading, interior design, furniture

Outstanding balances

Computed from source transactions at read time, not stored as a running total

GST, TDS and statutory compliance, built in

We build accounting and statutory compliance into the operations system itself: ledger, GSTR-1, GSTR-3B, ITC reconciliation, TDS, reverse charge, fixed assets, bank reconciliation, audit log and books lock — and industry filings such as a boiler's IBR forms, generated from the BOM. Tally becomes optional. Rates come from a human-verified registry.

Who it's for: Manufacturers and traders who enter every purchase and sale twice — once in operations, once in Tally — and reconcile the two every month.

Reports and documents from one computation each

23

GST returns

GSTR-1 (B2B and HSN) and GSTR-3B

Bank reconciliation

Auto-matched only when mutually unique; the rest go to a person

Industry filings

IBR Forms II(1), III, III A and IV A, from the BOM and test certificates

TallyPrime integration for cloud apps

We connect cloud business apps to TallyPrime through a small agent on the PC that runs Tally, because Tally's XML gateway only listens locally. Approved invoices post as vouchers within 30 seconds, status syncs every 15 minutes, and masters nightly. Missing ledgers and Tally rejections are held for a person, never auto-created.

Who it's for: Indian businesses whose accounts live in TallyPrime but whose sales, purchase or operations work has moved to a web app — and who are tired of re-keying the same invoice twice.

Push cadence

30 seconds

Voucher and outstanding sync

15 minutes

Ledger, stock-item and voucher-type masters

24 hours

Open-source reference library

tally-voucher-xml, 32 tests

Multi-company finance and role-scoped access

We build finance systems for sister concerns and group companies: one shared client list and ledger, with each invoice carrying the right company's letterhead and GSTIN. Who can see what is enforced where the data is fetched, not hidden in the screen — staff see only their own cash entries, and bank data is refused to them outright.

Who it's for: Families and partners running two or more related businesses out of one office, who need one view of the money without every employee seeing all of it.

Staff view of the cash ledger

Own entries only, enforced in the API query

Staff access to bank data

None — every bank route rejects staff

Companies per invoice

Chosen per invoice: letterhead, logo, GSTIN

Analytics and operational intelligence

Once the business runs on one model, analytics stops being a spreadsheet export. We build reporting through to advanced analytics on the operational data itself: charges flagged automatically against reference rates, match suggestions ranked by a Laplace-smoothed confidence score, and reports computed from the transactions themselves, so every figure can be traced back.

Who it's for: Owners who already have the data but decide on gut feel, because every report means someone stitching exports together by hand.

Overcharge detection

Every vendor and freight charge compared against a reference rate; deviations flagged

Confidence scoring

(approvals+1) / (approvals+rejections+2) ≥ 0.75, minimum 3 approvals

Workflow blockers

What each milestone is waiting on, computed fresh on every read

Material yield

Every cut conserved: 157.00 kg → 127.17 used + 15.70 remnant + 14.13 scrap

Built for

Boiler manufacturing (Shanti Boilers), interior design and furniture (Savistar & Saag)

AI document extraction with human review

We build AI extraction for purchase invoices, freight invoices, bills of entry, purchase orders and bank statements. An LLM reads the PDF directly, with a prompt per document type. 88–95% of documents need zero correction, and every one still waits for a person to approve it before anything is posted to the books.

Who it's for: Trading, import-export and manufacturing businesses whose accounts team spends its day typing GST invoices, customs paperwork and bank statements into Tally.

Purchase order, zero-correction rate

95%

Purchase invoice, zero-correction rate

94%

Freight invoice, zero-correction rate

91%

Bank statement, zero-correction rate

89%

Bill of entry, zero-correction rate

88%

Documents posted without human approval

None

RAG and knowledge graphs over your business

Every system we build starts as a model of entities, relationships and decisions — which is already the schema of a knowledge graph. We build retrieval (RAG) and knowledge-graph layers on top, so people and AI agents can ask questions of your records, documents and past decisions and get answers that cite where they came from.

Who it's for: Businesses whose know-how lives in documents, inboxes and a few senior people's heads, and who want an assistant that answers from their own data rather than the internet.

Running on this site

Search and chat over every published page (Ctrl/Cmd+K), and the same index as an MCP server for AI agents

Running today

Ahrom Labs' own decision corpus, which the AI coding agents in 4 client codebases are instructed to check before any new design

Inferred relationships

Marked unconfirmed and kept read-only until a person confirms them

Answers

Cite the record or document they came from

How an engagement runs

Every engagement starts by modeling the business: its entities, the workflows that move work between people, and the decisions that change what happens next. That model becomes the specification, agreed before anything is built, so the structure isn't renegotiated halfway through.

Ahrom Labs takes on a small number of engagements at a time. The person who models your business is the same person who writes the code and answers your first message: Pujan Motiwala, Principal, based in Ahmedabad and working with clients across India.

Work is priced in fixed phases after the modeling phase, the code and data become yours, and support runs under an annual maintenance contract. Pricing, timelines, ownership and support in full