AI assistants that convert browsing into basket growth

Client

Hilal

Hilal uses grounded AI for retail communication — product questions, recommendations, and customer conversations that convert browsing into basket growth without inventing inventory.

Project

Tasks

• Catalog and policy grounding via RAG over product and FAQ corpora
• Recommendation flows tied to live inventory and promotions
• Human escalation when confidence or sentiment thresholds trip
• Analytics dashboard for conversation quality and conversion

KPIs

1. 1. 70%+ AI resolution — without human agent for tier-1 product questions
2. 2. Measurable basket lift — on assisted sessions vs. unassisted browse
3. 3. Sub-3s response — p95 latency during campaign traffic
4. 4. Zero policy violations — grounded answers only from approved sources

Project journey

1. 1. PoC sprint

   Two-week grounded assistant on a subset of SKUs with manual eval rubric.

2. 2. Production integration

   Connected to commerce APIs, CRM, and escalation queues.

3. 3. Optimize & scale

   Prompt tuning, caching, and A/B tests on recommendation strategies.

Challenges

Retail support and sales chat could not scale personalized product answers. Agents repeated catalog questions while recommendations ignored live stock and brand voice constraints.

• Repetitive product questions consumed agents who should focus on complex sales and exceptions.
• Ungrounded recommendations risked suggesting products that were out of stock or off-brand.
• Channel fragmentation split customer communication across tools without shared context.
• Weak escalation left hard cases stuck with bots or dumped without context to humans.

Results

Testimonial

“Customers get answers instantly — and we finally see which questions drive revenue.”