cd /news/artificial-intelligence/building-mathondu-how-we-built-an-auโ€ฆ ยท home โ€บ topics โ€บ artificial-intelligence โ€บ article
[ARTICLE ยท art-114244] src=dev.to โ†— pub= topic=artificial-intelligence verified=true sentiment=โ†‘ positive

Building Mathondu: How We Built an Autonomous AI Merchant & Store Factory with Google ADK, Gemini 3.5, and Cloud Run

A developer built mathondu, an autonomous AI merchant and store factory that uses Google's Agent Development Kit (ADK) and Gemini models to create digital shops, photograph products, compile Android apps, and automate WhatsApp orders for small merchants in India. The system orchestrates specialized sub-agents to extract store and product data from messy photos, generate catalog images, and deploy real-world deliverables via Cloud Run and Firebase.

read4 min views2 publishedAug 28, 2026

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** (เฒฎเฒคเณเฒคเณŠเฒ‚เฒฆเณ 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.

                         โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                         โ”‚ Merchant Photos /        โ”‚
                         โ”‚ WhatsApp Text            โ”‚
                         โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                      โ”‚
                                      โ–ผ
                         โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                         โ”‚ onboard_orchestrator     โ”‚
                         โ”‚      (Google ADK)        โ”‚
                         โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                      โ”‚
                 โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                 โ”‚                    โ”‚                    โ”‚
                 โ–ผ                    โ–ผ                    โ–ผ
        โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”   โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”   โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
        โ”‚ store_extract_ โ”‚   โ”‚ product_data_  โ”‚   โ”‚ missing_fields_โ”‚
        โ”‚ agent          โ”‚   โ”‚ agent          โ”‚   โ”‚ agent          โ”‚
        โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜   โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜   โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                โ”‚                    โ”‚                    โ”‚
                โ–ผ                    โ–ผ                    โ–ผ
        Gemini 3.5 Flash Lite  Gemini 3.5 Flash Lite  Gemini 3.5 Flash Lite

                                      โ”‚
                                      โ–ผ
                         โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                         โ”‚ catalog_image_agent      โ”‚
                         โ”‚ Gemini 3.1 Flash Lite    โ”‚
                         โ”‚ Image                    โ”‚
                         โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                      โ”‚
                                      โ–ผ
                    โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                    โ”‚ Firebase Storage + Firestore    โ”‚
                    โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                    โ”‚
                 โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                 โ”‚                                     โ”‚
                 โ–ผ                                     โ–ผ
      โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”          โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
      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”‚
      โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜          โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

@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”‚
              โ–ผ
       Firestore apkJobs
              โ”‚
              โ–ผ
      Cloud Run Worker
              โ”‚
              โ–ผ
   Bubblewrap + Android SDK
              โ”‚
              โ–ผ
      Custom TWA APK
              โ”‚
              โ–ผ
      Firebase Storage
              โ”‚
              โ–ผ
   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}

$$

โ€”all 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.

๐Ÿ“ธ Photos / Voice / Text

โ†“

๐Ÿค– Google ADK Multi-Agent Pipeline

โ†“

๐ŸŒ Storefront + Catalog + APK

โ†“

๐Ÿ’ฌ WhatsApp Commerce

โ†“

๐Ÿ›๏ธ Real Orders

If a merchant can send a photo or a voice note, mathondu should be able to build the store.

โ”€โ”€ more in #artificial-intelligence 4 stories ยท sorted by recency
tooldirectory.ai ยท ยท #artificial-intelligence
Google Stitch
โ”€โ”€ more on @google 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain โ€” perfect for shipping the agent you just read about.

$git push zahid main
โ†’ Live at https://your-agent.zahid.host โœ“
Get free account โ†’ Pricing
from โ‚ฌ0/mo ยท no card required
LIVE [news/building-mathondu-hoโ€ฆ] indexed:0 read:4min 2026-08-28 ยท โ€”