Deliverist AI Chatbot
ShippedConversational commerce for Saudi logistics. RAG pricing, 5 AI tools, speech-to-text, bilingual.
Sole Product Engineer · OSIT / Deliverist · 2025
- Form fields to one chat
- 13 → 1
- Faster replies
- ~500ms
- AI tools
- 5
- Typed or spoken
- EN + AR
Problem
Customers had to fill a 13-field form on their phone, often at the airport.
What I built
A chat that quotes, books and tracks deliveries in Arabic or English.
Result
Booking on a phone went from a long form to a short conversation.

What it does
01
13-Step Shipment Wizard
Book a shipment without leaving the chat.
02
RAG Pricing Pipeline
Prices update when a new pricing PDF is uploaded.
03
5 AI Intent Tools
Sends each message to quote, book, track, complaint or FAQ.
04
Bilingual RTL with Speech
Arabic and English, typed or spoken.
Tech Stack
All projects- Next.js
- Vercel AI SDK
- DeepSeek
- OpenAI
- PostgreSQL
- Drizzle ORM
- Google Maps API
- Whisper
- LangChain
Read the full write-up1 min read
The problem
Deliverist moves luggage between doors and airports across Saudi Arabia. Their customer-facing product was a static form with 13 fields. Nobody wants to fill that out on their phone at an airport. They needed a single conversational interface for quoting, booking, tracking, and complaints in English and Arabic.
Highlights
- Cut response latency ~500ms by migrating from two-step intent detection API to native Vercel AI SDK tool calling
- Unblocked product launch with a RAG pricing pipeline (PDF → OpenAI embeddings → PostgreSQL vector retrieval) when the backend pricing API wasn't ready
- 13-step shipment wizard embedded in chat turned a support tool into a transaction channel
- Bilingual EN/AR with full RTL, speech-to-text via Whisper, and iframe embedding for distribution
What I built
- 13-Step Shipment Wizard
- Embedded booking flow inside chat: pickup location, destination, item type, weight, dimensions, packaging, insurance, pickup date, delivery speed, payment method, COD toggle, special instructions, and confirmation. Each step validates via tool calls.
- RAG Pricing Pipeline
- PDF pricing documents are chunked, embedded via OpenAI, and stored in PostgreSQL with pgvector. When a user asks for a quote, the system retrieves the relevant tariff rows and computes a live price. Updating prices requires uploading a new PDF, zero code changes.
- 5 AI Intent Tools
- Vercel AI SDK tool calling routes user utterances to the right handler: quote, book, track, complaint, or FAQ. Each tool has a typed Zod schema and runs in parallel where possible. Intent detection happens in a single inference pass.
- Bilingual RTL with Speech
- Full Arabic/English support with RTL layout via logical properties. Speech-to-text via Whisper handles Saudi dialects. Both languages share the same conversation state so users can switch mid-chat.
More numbers
17
API routes
6 months
Duration
Architecture

The Thinking Behind

Related Projects
Interested in working together?