Deliverist AI Chatbot

Shipped

Conversational 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
  1. Problem

    Customers had to fill a 13-field form on their phone, often at the airport.

  2. What I built

    A chat that quotes, books and tracks deliveries in Arabic or English.

  3. Result

    Booking on a phone went from a long form to a short conversation.

Deliverist AI Chatbot

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

Deliverist AI Chatbot architecture

The Thinking Behind

Deliverist AI Chatbot thinking canvas

Interested in working together?