Contact usENعربي

Case studyPilgrim health

HAJI: Pilgrim Guidance in Their Own Language, Through the Peak of Hajj 2025

≈14,000users during Hajj 2025 (1446H)

Built and backed by Ting

Pilgrims' questions about rituals, routes and health arrive at once, in many languages. HAJI, built and backed by Ting, answers them on WhatsApp from approved knowledge. In 2025 it ran as part of the Hajj with Health initiative, within the Makkah Health Cluster ecosystem.

Industry
Healthcare and pilgrim services
Location
Makkah, Saudi Arabia
Challenge
Pilgrim support that has to hold at peak demand

By the Ting teamUpdated

How HAJI is designed for the peakSchematic, not to scale

Design intent: questions over the Hajj days, against fixed capacity

Hajj days

  • Pilgrim questions
  • Hotline and field-team capacity
  • Beyond fixed capacityThe load HAJI is built to take

Where HAJI's job ends

  1. A message in the pilgrim's language
  2. Approved knowledge
  3. An answer in the same language
  1. A health signal
  2. An awareness prompt
  3. Escalation to a field team

Never diagnosis

Operator dashboard: the campaign team sees every flow

Schematic of the system's design; no figures implied.

The challenge

Pilgrim support is tested in the most compressed week of the year. Demand peaks in days, not months, and it arrives in many languages at once. A pilgrim with a question about the next ritual, the right route or a health worry rarely gets an answer in their own language, and hotlines and field teams cannot grow with the crowd.

Health is where the gap matters most. Heat, crowds and long distances on foot put real strain on pilgrims, and those with chronic conditions are the most exposed. Most support is reactive: it waits for the pilgrim to ask, often when the moment has already passed.

The task was to reach pilgrims where they already are, answer in their language from approved knowledge, and know exactly where the assistant's job ends.

Our approach

  1. Approved knowledge, not improvisation. Answers on rituals, logistics and health awareness draw on a curated knowledge base, not on whatever a model improvises. Behind it sit campaign logic that decides what to send and when, escalation paths to the teams on the ground, and an operator dashboard for the people running the campaign.

  2. Multilingual by design. HAJI replies in the language the pilgrim writes in, which matters in a gathering where Arabic or English reaches only part of the crowd.

  3. Health awareness, carefully bounded. HAJI sends timely awareness prompts, such as reminders about hydration and medication timing, and escalates where a person is needed. It never diagnoses.

  4. Delivered on WhatsApp. WhatsApp is the channel, not the product: the pilgrim sends a message from the app already in their pocket, and the system behind it does the work.

Outcomes and impact

Kept apart on purpose: what was handed over, what has been proven, and what is still to be measured.

  1. DeliveredHajj 2025

    A live system, not a demo: the WhatsApp channel, the curated knowledge base, campaign logic, escalation paths and the operator dashboard, running through the season.

  2. Proven

    Pilgrims will use a support channel they do not have to install, at the busiest time of the year.

  • ≈14,000users during Hajj 2025 (1446H), through the peak days

We publish usage only. Satisfaction and health-outcome figures are not published because we do not hold verified data for them, and Ting's internal capacity models are not reported as results.

Why this matters

Large events expose something true of every service organisation. You cannot hire for the peak week, and you cannot ask people in a crowd to download an app first.

HAJI shows what operational AI looks like when it is built for that pressure: it meets people in the channel they already use, answers from approved knowledge, and knows where its job ends. In health, that boundary is the product.

The same pattern runs through Saudi groups with many branches, service centres and fleets: seasonal peaks, a fixed team, and demand that is not fixed. Healthcare is one example. An AI Transformational Audit shows whether the pattern pays off in your own workflows.

More case studies

All case studies

Sound like your operation?
Let's map yours.

Contact usSee Custom Implementation