A map of each job's actions, sorted into 'do alone', 'ask first' and 'never'
Limits by amount, customer and risk, set by you and changed in one place
Yes or no cards on your phone with the facts and the AI's reason attached
Limits that widen as the AI's track record grows, and only when you agree
A monthly review of every automatic action and every override
For example, in your trade
A hotel's assistant may move a booking date on its own, but any refund over Rs 5,000 waits for the duty manager's yes.
A transporter's AI agent books loads at the rate card by itself and sends anything below the floor rate to a manager.
What we never promise
Rules only cover the cases you've described, so anything new goes to a person by default, and the AI never acts alone on money without your written limit.
What we have built that shows it
Agent in the team chat, built for a relocation company with teams across India.
Mail engine, built for our own company.
An agent for every delegate in a room, built for an industry body in Asia Pacific, at a leadership workshop.
Alerts on risky sign-ins, leaked passwords and laptops missing updates
Backups proved every week by restoring a sample
A watch on large downloads and files going to personal mail or drives
A morning note in plain words: what happened, what it means and what to do
An incident plan with who to call, including the six hour report to CERT-In
For example, in your trade
A CA firm is told within the hour when a staff login comes from an unusual city, with what to do next.
An IT reseller runs this watch for 40 small customers and sends each a monthly report under its own name.
What we never promise
Watching shortens the time an attack goes unnoticed but can't stop every one, so we test your backups and your plan too and never promise you can't be breached.
A daily search for lookalike domains, fake apps and social accounts using your name
Takedown requests drafted for each one, with the evidence attached, for your approval
Call-back rules and code words for any payment or bank detail change
Checks on video interviews for stand-ins and swapped faces
Drills for your accounts team with fake calls and mails, made with consent
For example, in your trade
A food brand learns within a day when a new site starts selling fake franchises in its name, with the takedown drafted.
A finance team refuses an urgent transfer asked for on a video call that looked like the CFO, because the code word didn't match.
A staffing firm spots a candidate whose face and voice don't match between two interview rounds.
What we never promise
No tool spots every deepfake, so we pair detection with call-back rules, and takedowns depend on the platforms and registrars acting. Candidates are told and agree before any face or voice check.
Replies on your social pages and ads read as they arrive, with scams, abuse and spam hidden
Listings, reviews, photos and profiles on your platform checked against your rules before they go live
Accounts pretending to be you or your staff found and reported
Takedown requests tracked against the hours the IT Rules allow
Appeals sent to a person, and a monthly read of what was removed and why
For example, in your trade
A fashion brand's ad comments hide replies offering refunds through fake WhatsApp numbers within minutes of posting.
A rental platform checks every new listing's photos and text for fake addresses and known scam patterns before it goes live.
An edtech app keeps abuse and phone numbers out of its student forum, and a moderator sees anything borderline.
What we never promise
Automatic checks miss some posts and catch some innocent ones, so appeals go to a person, the rules are yours, and takedowns meet the hours the IT Rules set.
A sample audit trail for IT: an access request approved by the IT head, a customer list kept out of a public AI tool, and a leaver's accounts closed. Shown with sample data.
Trust, in your trade.
The same capabilities, said the way they would work in a business like yours. Pick your trade.
For example, in your trade
A lender's AI summarises collection calls with every account number and Aadhaar masked before the transcript is read.
We never name a client or show how they run inside. Each piece says what kind of company it was built for, and every number says what it counts and when.
Overnight checkDone at 03:40
3 broke
212jobs, tools, rules and memories checked
3broke, each with one step to fix it
Invoice sync stoppedFor: sending invoices to the accounts. Fix: sign in to the accounts again.
Weekly report job did not runFor: the Monday numbers. Fix: restart it.
A rule names a folder that movedFor: filing quotes. Fix: point it at the new folder.
Built for our own company, for every agent at work on its machines
Every AI agent at work, what each is doing this minute, and one queue for the moments they need a person, in their own words with one button each, built on the alarm rules of industrial control rooms.
45 minutes on a video call with our founder and the people who live with the problem. Nothing to sign. You leave knowing what we would build first, and why.