Real availability checked, appointments taken, moved and cancelled — written to the same calendar your staff use, not a parallel one.
WhatsApp AI Assistants
An assistant on the channel your customers already use. It books, answers and follows up in the thread they are already in — and hands over to a person the moment it should. No app to install, no portal login.
What we build
What we build
Some of what an assistant handles. Ask about anything you do not see here.
Hours, location, pricing, what to bring. Answered from your own documents rather than the model’s general knowledge.
Sent through approved templates, which is the part that actually reduces no-shows.
Where something is, when it will arrive, what happens next — without anyone picking up the phone.
Enquiries answered, the useful details collected, and a warm one handed to a human while they are still interested.
Photos, IDs and forms requested, received and filed against the right record.
Anything sensitive, ambiguous or complained about goes to a person with the whole thread attached. Designed, not an afterthought.
Business verification, display name, number provisioning and template submission — the part that stalls most first attempts.
Built and running
ClinicDesk
Our WhatsApp assistant for clinics, in production today.
A patient messages the clinic and books in about a minute — in Urdu, Roman Urdu or English, at any hour. Only genuinely free slots are offered, and anything that needs a person goes to staff.
Most customer software fails on distribution rather than features — people will not install an app to book one appointment. WhatsApp is already open on the phone.
How it runs
How we launch one
Four stages. The Meta approval usually takes longer than the build.
-
Get the account approved first
A verified Meta Business account, a number not already on consumer WhatsApp, and a display name that survives review. Most first attempts stall here.
Before anything is built -
Write the templates for approval
Outside a 24-hour window you may only send pre-approved templates. Reminders and confirmations are written and submitted before launch, not improvised after.
Written for approval -
Publish privacy and deletion pages
Meta checks that both load publicly before approving. We build them alongside the assistant rather than scrambling at review.
Checked before submission -
Then the assistant
Connected to your calendar and records, with handover rules and tone set with your team. The straightforward part, once the account is clear.
Live in weeks
Common questions
Questions we get asked
Days to a few weeks, depending on how clean your business verification is. We start it on day one for that reason.
Only if it is not already registered on consumer WhatsApp. If it is, the usual answer is a new number that forwards.
Meta charges per conversation, not per message, and rates vary by country and category. We will model it against your actual volumes before you commit.
Messages are personal data and often health data. Who controls it, how long it is kept and how deletion is requested are written down before launch.
The other 7
Rarely bought on its own.
Most teams need two or three of these together. Take the layer you are missing, or the whole stack.
Build agents that complete real work end to end — read the case, apply your policy, take the action and record why. Not chatbots that answer questions about the work.
Read moreProve how an AI system behaves before it goes live, and keep proving it afterwards. Evaluation suites, adversarial testing and drift monitoring built from your own cases.
Read moreBuild and modernise web, mobile and internal platforms, wired into the core systems you already run rather than sitting beside them.
Read moreRelease faster with automated regression suites, API and performance coverage, and real-device mobile testing wired into your pipeline.
Read moreAutomate regulatory reporting, financial crime operations and statutory filings — behind maker-checker, with an audit trail a regulator will accept.
Read moreConnect the tools you already pay for and let agents run the steps between them — on a schedule, on a trigger, or on approval.
Read moreSmall, private AI models that make one decision well — route, classify, triage — with a confidence score your team can trust. Runs inside your network.
Read moreTell us what is slowing you down.
Half an hour, no deck. Describe the process and we will come back with whether it is worth automating, roughly what it would take, and what we would build first — or tell you plainly if it is not a job for us.