Skip to content
All projects
Saudi enterprise groupEnterpriseSaudi Arabia2026

Fifteen HR services, answered on WhatsApp, written back to Oracle EBS

HR services delivered in the app employees already have open, with Oracle EBS still the system of record and every request auditable end to end.

The challenge

The HR platform was not the problem. Oracle EBS HRMS held employee records, organisational structure, leave, attendance and approvals correctly for around 10,000 people. Reaching it was the problem: employees moved between self-service portals and separate applications to do things that take one sentence to describe.

That fragmentation lands on the HR team as workload. A large share of their week went on repetitive inquiries — how much leave do I have left, where has my certificate got to — and on manually chasing the status of requests already in the system.

Availability was the third constraint. HR services effectively existed during office hours on a desktop, while the workforce is mobile and distributed. An employee on a site at 9pm had no route to a payslip or a leave balance.

And the answer could not be a second system of record. Anything that held its own copy of leave balances would drift from Oracle within a week and become the thing nobody trusts.

Our approach
01

Meet employees where they already are

WhatsApp rather than another portal or another app to install. Adoption is the whole point of the project, and an interface with nothing to learn and nothing to download is the only one that reaches a workforce of this size.

02

Understand the request, then resolve the person

Natural-language understanding maps a message in Arabic or English onto an HR service, extracts the parameters it needs, and identifies the employee and their reporting line from Oracle — so the assistant knows who is asking and who has to approve before it asks anything back.

03

Read and write against Oracle, not a copy

Balances, attendance records, profile and organisational data are read live from Oracle EBS, and submissions are written straight back into it. Oracle remains the authoritative record; the assistant is an interface to it, never a parallel truth.

04

Run the approval chain inside the conversation

A request raises the real workflow — direct manager, senior manager on escalation, HR officer — with each approver acting from their own WhatsApp thread and the employee notified as the request moves. Status tracking stops being a phone call.

05

Generate the documents at the end of it

Salary and employment certificates are generated from Oracle data on approval and delivered into the same conversation, rather than produced by hand and emailed later.

06

Keep the data in the Kingdom

The platform runs on public cloud inside Saudi Arabia, with employee and HR data resident in-Kingdom, logical isolation of tenant data and processing, and an AI environment scoped to the organisation — the condition on which everything else depended.

How it works

WhatsApp messages arrive at a conversation gateway, are classified and parameterised by the language layer, and resolve against an employee identity taken from Oracle. A workflow engine holds request state and the approval chain, while an integration layer performs the reads and writes against Oracle EBS. Everything runs in-Kingdom.

WhatsApp Business channel
Conversation gateway
Arabic / English understanding
Employee identity & reporting line
HR service catalogue
Approval workflow engine
Oracle EBS HRMS integration
Certificate generation
Notification & status tracking
In-Kingdom cloud, isolated tenant
What we built

The system, in specifics.

A conversational HR assistant on WhatsApp covering fifteen services: leave request and balance, salary and employment certificates, attendance inquiry, overtime, business trip, personal information and profile updates, training, internal transfer, promotion, medical insurance, payslips and request status tracking.

Arabic and English understanding and response, including mixed-language messages, with right-to-left formatting in generated documents.

Live Oracle EBS HRMS integration across employee profile, reporting structure, department data, leave balances and requests, attendance records and summaries.

Multi-step approval orchestration — direct manager, senior manager and HR officer — with escalation paths and in-conversation approval for each role.

Automated certificate generation from Oracle data, delivered as a document in the chat.

Proactive notification on every state change, so employees stop chasing status.

Role-scoped access: an employee sees their own record, a manager sees their reports, an HR officer sees the queue — enforced server-side against Oracle’s own hierarchy.

Public cloud hosting inside Saudi Arabia with in-Kingdom data residency and logical isolation of customer data and processing.

A service catalogue designed for extension, so new HR services — and later, functions beyond HR — onboard without redesigning the platform.

Full audit trail per request, covering the message that raised it, every approval, and the Oracle transaction it produced.

The product

What it looks like in use.

Leave request, approval chain and certificate, against Oracle EBS
Leave request, approval chain and certificate, against Oracle EBS
Outcome

What changed.

~10,000
Employees served
Single enterprise HR platform
15
HR services in the catalogue
Leave and certificates through to promotion requests
AR / EN
Bilingual throughout
Understanding, replies and generated documents

HR services reachable in the app employees already have open, in Arabic or English

Oracle EBS kept as the single system of record — no second copy of leave balances to drift

Approvals run end to end in the conversation, with the employee notified at each step

Repetitive balance and status inquiries taken off the HR team

Available outside office hours, from a phone, without a desktop portal

Employee and HR data resident in Saudi Arabia, with isolated processing

A service catalogue built to extend beyond HR without re-architecting

Next

Related work.

Flagship

Outcall Review Agent

Multi-client programmeEnterpriseGlobal

Automated outbound voice agent for customer feedback and reviews

An AI agent that calls customers after service, holds a natural feedback conversation, and routes happy customers to a public review.

Voice AILLMsSpeech Recognition
Read case study
AI Document System — AI feasibility analysis, extraction and document generation for Dubai Municipality
Flagship

AI Document System

Dubai MunicipalityGovernmentUAE

AI feasibility analysis, extraction and document generation for Dubai Municipality

Reads third-party and internal feasibility documents, fills the financial sheets and forms that follow, and checks the result against ISO, WHO and other international standards.

AI/LLMsPythonFastAPI
Read case study
AI Takeoff Estimator — Construction takeoff and bidding from architectural PDFs, in minutes
Flagship

AI Takeoff Estimator

Multi-client programmeConstructionGlobal

Construction takeoff and bidding from architectural PDFs, in minutes

Reads architectural PDFs, detects the scale on its own, measures only the trade you work in, and returns quantities, labour hours and a bid — then pushes the work into your CRM.

Computer VisionDocument AIDeep Learning
Read case study