Disclosure:I created this piece of content for the purposes of entering the Google All Things Agentic Hackathon on Devpost.
Millions of small merchants, home bakers, and neighbourhood store owners across India run their daily business through WhatsApp and UPI.
While messaging works for basic conversations, scaling a business through chat breaks down quickly:
We built ** mathondu** (เฒฎเฒคเณเฒคเณเฒเฒฆเณ โ
Our goal was simple:
Build an agent that doesn't just talk about opening a store, but actually creates the digital shop, photographs products, compiles an installable Android app, and automates WhatsApp orders end-to-end.
Rather than building a single monolithic prompt, we leveraged the Google Agent Development Kit (ADK) to coordinate a fleet of specialized sub-agents with strict domain boundaries.
โโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ Merchant Photos / โ
โ WhatsApp Text โ
โโโโโโโโโโโโโโฌโโโโโโโโโโโโโโ
โ
โผ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ onboard_orchestrator โ
โ (Google ADK) โ
โโโโโโโโโโโโโโฌโโโโโโโโโโโโโโ
โ
โโโโโโโโโโโโโโโโโโโโโโผโโโโโโโโโโโโโโโโโโโโโ
โ โ โ
โผ โผ โผ
โโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโ
โ store_extract_ โ โ product_data_ โ โ missing_fields_โ
โ agent โ โ agent โ โ agent โ
โโโโโโโโโฌโโโโโโโโโ โโโโโโโโโฌโโโโโโโโโ โโโโโโโโโฌโโโโโโโโโ
โ โ โ
โผ โผ โผ
Gemini 3.5 Flash Lite Gemini 3.5 Flash Lite Gemini 3.5 Flash Lite
โ
โผ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ catalog_image_agent โ
โ Gemini 3.1 Flash Lite โ
โ Image โ
โโโโโโโโโโโโโโฌโโโโโโโโโโโโโโ
โ
โผ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ Firebase Storage + Firestore โ
โโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโ
โ
โโโโโโโโโโโโโโโโโโโโดโโโโโโโโโโโโโโโโโโโ
โ โ
โผ โผ
โโโโโโโโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโโโโโโโ
โ Cloud Run APK Worker โ โ WhatsApp Cloud API โ
โ โ โ โ
โ Bubblewrap TWA Builder โ โ Inbound Webhooks โ
โ Android SDK โ โ Orders & Alerts โ
โโโโโโโโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโโโโโโโ
@google/adk
) When a merchant sends messy photos of handwritten paper menus or shelf items, our pipeline executes in specialized stages.
onboard_orchestrator
The top-level ADK agent coordinates sub-agent execution and commits the verified state to Cloud Firestore.
store_extract_agent
Extracts:
using Gemini 3.5 Flash Lite.
product_data_agent
Parses:
into typed schemas.
missing_fields_agent
Analyzes missing critical fields and generates targeted follow-up prompts without overwhelming the merchant.
catalog_image_agent
Synthesizes high-resolution, square product catalog photography using Gemini 3.1 Flash Lite Image.
Most AI prototypes stop at returning text.
mathondu compiles real-world deliverables.
Indian merchants frequently ask for "their own app on the customer's phone."
We built an asynchronous compilation worker running on Google Cloud Run.
The workflow is:
Merchant clicks "Get Android APK"
โ
โผ
Firestore apkJobs
โ
โผ
Cloud Run Worker
โ
โผ
Bubblewrap + Android SDK
โ
โผ
Custom TWA APK
โ
โผ
Firebase Storage
โ
โผ
Secure download link
+ install QR
Each build produces a tenant-specific Trusted Web Activity (TWA) binary such as:
com.mathondu.s.{slug}
The signed .apk
is uploaded directly to Firebase Storage, generating a secure 7-day download link and installable QR code.
Customers can message:
+91 94621 46133
with:
Hi, shop {slug}
A state machine backed by Firestore handles:
Real-time order events then alert the seller with direct links to the admin console.
The result is a complete commerce loop:
$$
\text{Browse}
\rightarrow
\text{Add to Cart}
\rightarrow
\text{Place Order}
\rightarrow
\text{Merchant Alert}
$$
โall without requiring the customer to install another shopping application.
To prevent silent catalog corruption, our admin_manager_agent
follows a strict:
$$
\text{Proposal}
\rightarrow
\text{Review}
\rightarrow
\text{Accept}
$$
pattern.
For example, if an owner asks:
"Discount all bakery items by 10%."
The agent does not immediately modify the database.
Instead, it:
This gives merchants the speed of an AI agent while preserving human control over critical business data.
| Layer | Technology |
|---|---|
| AI Framework | |
| Google ADK 2.x | |
| AI Models | |
| Gemini 3.5 Flash Lite, Gemini 3.1 Flash Lite Image, Gemma fallback | |
| Frontend / PWA | |
| Next.js 15, App Router, React, Tailwind CSS | |
| Backend / Hosting | |
| Firebase App Hosting, Cloud Run | |
| Secrets | |
| Google Cloud Secret Manager | |
| Database | |
| Cloud Firestore | |
| Storage | |
| Firebase Storage | |
| APK Worker | |
| Docker, Cloud Run, Node.js, Android SDK, Bubblewrap | |
| Messaging | |
| WhatsApp Cloud API (Meta) |
Isolating extraction, validation, and image synthesis into separate ADK agents drastically reduced hallucination and improved reliability when processing regional languages such as Kannada and Hindi.
Instead of asking one agent to do everything, each agent has a narrow responsibility and a structured output contract.
Compute-heavy tasks such as:
should not block the primary user experience.
Off these workloads to background Cloud Run workers allowed the UI to remain responsive while longer-running tasks executed asynchronously.
The biggest lesson was that agentic AI becomes much more useful when it produces something tangible.
An installable:
.apk
.pdf
menuhas significantly more operational value than a conversational answer explaining how to create one.
Don't just make the agent answer. Make the agent ship.
Message:
+91 94621 46133
Try:
Hi, shop {slug}
mathondu turns a merchant's messy input into a complete digital commerce business โ powered by autonomous agents.
๐ธ Photos / Voice / Text
โ
๐ค Google ADK Multi-Agent Pipeline
โ
๐ Storefront + Catalog + APK
โ
๐ฌ WhatsApp Commerce
โ
๐๏ธ Real Orders
If a merchant can send a photo or a voice note, mathondu should be able to build the store.