JDM System
The JDM intelligence architecture.
Business in, outcome out. Between them, one core that turns AI, data and automation into agents, knowledge and workflows you can inspect.
The intelligence stack
Seven layers. Each one engineered.
From the conversation your customer sees to the infrastructure underneath. Select a layer and the Core draws it out of the stack.
Where customers and staff meet the system: WhatsApp, web, portals and review queues.
- Conversation design
- Portals
- Review queues
Radd Core
One engine. Eight components.
Every AI Employee is a configuration of the same engine, so every improvement to the engine improves every role.
- IdentityRole, tone and boundaries
- KnowledgeYour facts, searchable
- MemoryConversation state
- ToolsBookings, leads, handoff
- ChannelsWhatsApp, web, more
- GuardrailsConfidence and escalation
- LoggingEvery decision recorded
- MeteringUsage and cost tracked
Knowledge layer
Your business knowledge. Made operational.
A model knows the world. It does not know your rates, your policies or what you promised a customer last week. The knowledge layer connects the information your people already use, keeps it current, and lets every answer be traced to its source.
AI = model + context + knowledge + tools + workflow + controls
- Documents
- Website
- CRM
- FAQs
- Policies
- Products
- Databases
- Emails
- Internal notes
Agent runtime
From prompt to action.
An AI Employee is a system, not a prompt. Nine steps run for every request, and the last one is always available: hand the work to a person.
A message, an email, a form or an event from another system.
Observability
Every action has a trace.
A chat log tells you what was said. The trace tells you why: which source, which rule, which tool and which person. This is the record an owner reads to audit a conversation in a minute.
- Received WhatsApp messageFrench · booking enquiry
- Retrieved room availabilityCalendar · 12 to 14 March
- Applied rate ruleWeekend rate · breakfast included
- Generated replyTwo options · 46 words
- Booking request createdStatus: awaiting guest
- Transfer flagged for receptionRule: transfers confirmed by a person
Running
- Execution
- 6 steps
- Latency
- 2.3 s
- Tools used
- Calendar, booking
- Human intervention
- 1 handoff
- Outcome
- Completed
Illustrative trace for a fictional guesthouse. It shows what the system records; it is not a client measurement.
Evaluation
AI that gets better, on purpose.
Every failure becomes a test case. Every change is re-evaluated before it reaches a customer. We publish the numbers only when they come from real deployments.
- Task success
- Did the work get done as specified?
- Response quality
- Correct, complete, in the right language and tone.
- Escalation rate
- How often a person was needed, and whether they should have been.
- Tool success
- Calls that ran and returned what was expected.
- Error rate
- Wrong facts, invented answers or rule breaks.
- Latency
- Time from request to useful answer.
- Cost
- Model and infrastructure cost per task.
- Customer outcome
- What happened next for the person on the other side.