AI employees · automation · operating systems
JDM builds AI employees and automations that take defined work off your team, run it around the clock, and show you every decision they made.
Free · 20 minutes · French, English, Arabic or Darija
The constraint
Messages arrive faster than anyone can answer them. The follow-ups that would have closed the sale are the ones nobody got to. The owner becomes the bottleneck, and the only lever on offer is to hire, which is slow and expensive.
Illustrative moments.
What an AI Employee is
An AI Employee is a role that runs on the JDM Core: what it knows, which channels it works in, which rules it follows and the exact moment it hands the work to a person.
A single capability, built to do one job with clear inputs, outputs and limits.
Identity, knowledge, memory, tools, channels, guardrails, logging and metering. Built once, shared by every role.
Assembled, they become the Core. A new AI Employee is a new configuration, not a new codebase.
The roster
Agents are named by role, never with a human first name. The code and the cut corner tell you the function class at a glance. Status is stated plainly.
SUP · Service
Holds: First-line answers, order status, returns, escalation with context.
Message in
Answer from your knowledge
Capture the request
Escalate with context
Machine step Handed to a personDemo: works in our prototype, not yet installed for a client. Planned: specified, built on the same core.
The trail
Every automated action leaves a record a non-technical owner can read: what arrived, which source was used, which rule applied, what was done and who approved it.
Machine steps run on the blue spine. The moment a person takes over, the trail turns ochre and leaves the spine at 45°. You can always tell who did what.
WhatsApp message received
« Bonsoir, une chambre double du 12 au 14 mars ? »
Availability checked
Calendar · 12 to 14 March · 2 rooms free
Rate rule applied
Weekend rate · breakfast included
Reply sent with two options
French · 46 words
Airport transfer needs a person
Rule: transfers are confirmed by reception
Reception confirmed the transfer
Booking request created · guest notified
Dar Lagune is a fictional establishment used for demonstration.
Proof
We publish what is real. Radd, our first AI Employee, works as a demonstration and is being deployed with our first establishments in Dakhla. It is not yet installed for a client. You would be among the first five.
The first JDM AI Employee, built for hotels, riads, guesthouses and surf camps in Dakhla, where guest messages arrive at hours when reception is closed. Radd means reply in Arabic and Darija.
Configuration-driven and channel-agnostic, so a new AI Employee is a new configuration rather than a new codebase.
Dar Lagune · today
Needs a person first
Airport transfer for 5 guests
Concept interface. Dar Lagune is a fictional establishment used for demonstration; every figure is illustrative.
Pricing
Radd · Support AI for hotels, riads, guesthouses and surf camps. Monthly subscription, operated by us. Every price is a starting point stated in full.
à partir de1 500DH / month
300 conversations / month
Setup 2 500 DH, once
Talk about Essentielà partir de3 500DH / month
800 conversations / month
Setup 4 900 DH, once
Talk about Professionnelfrom10 000DH / month
2 500 conversations / month
Setup from 12 000 DH, once
Talk about Business3 DH per conversation above the allowanceAnnual prepayment: 10% off
It does not guess. Below a confidence threshold, or on a trigger word you choose, it hands the conversation to a named person on your team with the full history attached.
Yes. Every conversation and every action is in the trail, in plain language: what arrived, which source was used, which rule applied, what was sent and who approved it.
French, Darija, Arabic and English, including when a customer switches language in the middle of a conversation.
No. We operate what we build. Monitoring, fixes and knowledge updates are part of the subscription.
Discover how work flows today. Design what the system does and where a person stays in the loop. Build and test against real conversations. Integrate with your tools. Then optimise from the trail, month after month.
Not yet. Radd works as a demonstration and is being deployed with our first establishments in Dakhla. What we show you is the working system; it is not yet installed for you. You would be among the first five.
