A virtual CFO for your business
A board-style briefing — cash-flow outlook, risks, opportunities and recommended actions — grounded in your real numbers.
You have ₹2.15L collectible now across 3 overdue accounts:
- Sharma Traders · 18d₹1,24,500
- Verma & Co · 9d₹62,300
- Patel Retail · 4d₹28,200
Want me to draft WhatsApp reminders for all three?
Live product UI — sample data.
Executive briefing on demand
Financial health, cash-flow outlook, key risks, opportunities and a prioritised action list — in plain language.
Grounded in your data
Folds in cash-flow forecast, revenue leaks, churn and benchmarks — never invented figures.
Enterprise, with a safety net
Powered by Claude/OpenRouter/OpenAI/Gemini via a metered gateway; keys never touch your machine, and the deterministic core still runs offline.
What this actually means in practice
The briefing assembles a snapshot before a single sentence is written. It pulls the health score and its recommendations, month and year-to-date sales, gross and net profit, the bank position and net GST liability, a twelve-week cash projection built from receivables by due date, payables, GST and post-dated cheques on their instrument dates, the total from the revenue-leak scan, customers drifting past their buying interval with the revenue attached, and your most profitable and loss-making products.
Every one of those figures is computed by the same deterministic engines that power the standalone pages — the health score, the cash-flow projection, the leak scan, customer intelligence, the profit analyser. They are assembled into a structured snapshot, and only then does the language model write the prose: financial health, cash-flow outlook, key risks, opportunities and a numbered action list. It is instructed to answer from that snapshot alone. It phrases the number; it never produces one.
Owners read it before a bank meeting, a monthly review or a decision to take on stock — one page saying where cash goes tight, what is bleeding and what to do first. Two boundaries matter. The written briefing is the Enterprise tier at ₹2,499 monthly and runs through the metered gateway, where the provider keys live rather than on your machine; with the gateway unavailable, an on-device narrator writes the same sections from the same snapshot. And it recommends — it never posts.
| Briefing section | Deterministic engine behind it | Figures it carries |
|---|---|---|
| Financial health | Business health score | Score, grade, month and year-to-date sales, profit |
| Cash-flow outlook | Twelve-week cash projection | Opening bank, projected low point, first deficit week |
| Key risks | Receivables, churn and leak scans | Receivable tied up, customers drifting, leak total |
| Opportunities | Profit analyser and customer scores | Best-margin products, highest-value relationships |
| Recommended actions | Rule-derived action list | Each with the rupee figure that triggered it |
| Offline fallback | On-device narrator | Same sections, same figures, no gateway needed |
What’s included
- Board-style markdown briefing
- Cash-flow & working-capital view
- Risk & opportunity callouts
- Prioritised recommended actions
- Metered, key-safe gateway
- Deterministic fallback offline
What it does not do
- · The prose is written by a language model; the figures are not. If something is absent from the snapshot the briefing says so rather than filling the gap — but read it as a well-organised account of your own books, not an independent opinion.
- · The written briefing is Enterprise at ₹2,499 monthly. The engines feeding it — health score, cash projection, leak scan, customer intelligence — are in every plan and readable on their own pages without any AI.
- · No external context. It has no view of your industry, your competitors, interest rates or the season ahead; every statement in it traces back to your own ledgers.
- · Advisory throughout. It drafts an action list; approving, paying, chasing and posting all remain with you and your team.
Frequently asked
Where do the AI keys live?
On our gateway, never on your machine. Usage is metered against your Enterprise quota.
What if I’m offline?
The deterministic cash-flow forecast, leak detector and benchmarks still run — only the written briefing needs connectivity.
What happens when the AI gateway is unavailable?
The briefing still appears. An on-device narrator writes the same five sections from the identical snapshot — health, cash outlook, risks, opportunities, actions — so what you lose is the polish of the sentences, not the content. The rupee figures are exactly those the language model would otherwise have been handed.
Can it act on its own recommendations?
No. Each action arrives as a proposal carrying the figure that triggered it and a link to the screen where you would carry it out — send the reminder, set aside the GST, review the loss-making line. Nothing is posted to your books, sent to a customer or paid to a vendor unless you do it.
What exactly is included in AI · Enterprise?
board-style markdown briefing, cash-flow & working-capital view, risk & opportunity callouts, prioritised recommended actions, metered, key-safe gateway and deterministic fallback offline. Every item on that list is a working screen you can open in the trial rather than a capability described in the abstract.
How is ai · enterprise handled differently here?
It rests on executive briefing on demand, grounded in your data and enterprise, with a safety net. The distinction that matters is that these are structural rather than cosmetic — the behaviour is built into how records are posted, not layered on as a report you have to remember to run.
Does AI · Enterprise post to the real books?
Yes, and that is the whole reason it lives in this product rather than beside it. What executive briefing on demand records lands in the same posted double-entry ledger the Trial Balance, P&L and GST returns are built from — so there is no second set of ai · enterprise numbers to reconcile against the first.
How does AI · Enterprise affect my GST?
It feeds it directly rather than sitting alongside it. CGST/SGST and IGST are split from HSN or SAC and place of supply as each document is raised, so whatever ai · enterprise produces is already correct when GSTR-1, 3B and 2B reconciliation are drawn off the same books. The return matches the accounts because it was never a separate exercise.
Does AI · Enterprise cost extra?
No. AI · Enterprise is part of the accounting core rather than a paid add-on, so grounded in your data is there on the entry tier exactly as it is on the highest one. What the tiers change is reach and depth — devices, multi-branch and multi-warehouse reporting, and whether the conversational AI copilots are switched on.
Can I try AI · Enterprise before committing?
Yes — 14 days, no card. Test ai · enterprise against your own masters and your own transactions rather than sample data: the questions worth answering here are about your business's edge cases, and a demo dataset is built not to have any.
A board-style briefing, built from your figures
The CFO report and month-end close are assembled from your real numbers — the same sections, every time.
The CFO report — five fixed sections
- Financial Health
- Cash-Flow Outlook
- Key Risks
- Opportunities
- Recommended Actions
Illustrative. Generated from the figures you provide — nothing invented.
Month-end, closed with confidence
- Summary
- Outstanding Items
- GST & Compliance
- Sign-off readiness
Illustrative. Built from your checklist data, ending in a sign-off readiness view.
Your business, briefed every morning
One executive read — a single health score and the few signals that actually need you today. Computed offline by the deterministic engine, not guessed by a chatbot.
Most owners do not lack data — they have a dashboard with forty numbers on it and no time to read them, which is the same as having none. The brief is the opposite bet: one score to say whether anything changed, at most six signals to say what, and one recommended action specific enough to act on before the first customer walks in.
Deterministic Business Health Score & signals — computed offline, available in every plan. Sample data.
What the score is made of
Six sub-scores, not a vibe
Revenue growth, profitability, cash flow, collections, inventory turns and tax compliance. Each is computed from your posted books, each carries its own number, and the headline score is what they compose into — so a drop always has a component you can open.
The same figure the ledger holds
Collections come from real ageing, cash flow from real bank and receivable positions, tax compliance from returns actually filed. Nothing here is a separate calculation that could disagree with your accounts, because there is no separate calculation.
Computed, not generated
The engine runs on your machine and needs no connection and no model. Switch AI off entirely and the score, the sub-scores and the signals are all still produced — what you lose is the sentence wrapped around them, not the arithmetic.
A recommendation names the row
The action line points at one invoice, one customer, one amount and how overdue it is. That is the test we hold it to: advice that cannot name the record it came from is a horoscope, and we would rather show nothing that morning.
Six signals is the ceiling
The brief is capped deliberately. A list that grows every day until it is thirty items long is one nobody reads by the second week, so the engine ranks by exposure and shows only what has changed enough to deserve your attention.
It tells you; it does not act
Nothing in the brief posts an entry, sends a reminder, chases a customer or files a return on your behalf. It is a read of the business, and every decision that follows from it stays yours to make.