HomePlatformProductsLabsBuildCompanyContactStart a Project →
Build/Cases/NammaHubballi
City Directory + AILIVE2023

NammaHubballi replaced traditional category browsing with an AI query engine powered by Google Gemini and pgvector. Users ask natural language questions, and the system retrieves grounded answers exclusively from a curated, high-quality local business database.

4,000+
Local businesses indexed
60%+
Sessions using AI query
3:2
AI query to browse ratio
Launched 2023 · Architecture replicated for AskBLR (2025)

The Context

Local business discovery in mid-sized Indian cities is broken. Google Maps shows chains and hotels. JustDial has outdated listings and aggressive ad injection. The real local economy — the specific tailor who does alterations, the diagnostic lab that opens on Sundays, the chartered accountant who handles GST returns — is invisible online. The gap was a directory that was genuinely useful for local queries, not just comprehensive in listing count.

The Approach

Built the discovery layer as an AI query engine rather than a search bar. Users type natural language questions — 'Where can I get a bike serviced near Vidyanagar?' — and the system returns grounded answers from the local business database using Gemini with pgvector RAG. The business listings themselves are structured with opening hours, service categories, and verified contact information — curated manually for quality, not scraped for quantity.

CRITICAL ENGINEERING CHALLENGE

Grounding AI to prevent hallucinated business info.

Grounding Gemini responses to only the local database — preventing hallucinated business details while still allowing natural language flexibility. The solution was a strict RAG architecture: Gemini only generates from retrieved context, never from training data, with a fallback 'not found in directory' response for out-of-database queries.

THE OUTCOME

4,000+ businesses indexed. The AI query layer handles 60%+ of all discovery sessions — users prefer the natural language interface over the category browse by a 3:2 margin. Architecture replicated for AskBLR in 2025.

Engagement Meta

ClientInternal Product
Year2023
CategoryCity Directory + AI
Status● LIVE

Technology Context

Next.js 15Node.jsPostgreSQLGoogle Geminipgvectorn8nCloudflarePM2

Quick Navigation

NAMMAHUBBALLI ARCHITECTURE
01

FRONTEND

Next.js 15Frontend + query layer
02

API LAYER

Node.jsAPI + Orchestration
03

SERVICES

Google GeminiGrounded AI responses
pgvectorRAG similarity search
n8nData ingestion pipeline
04

DATABASE

PostgreSQLBusiness database + pgvector
05

INFRA

CloudflareEdge CDN + Workers
PM2Cluster management

Architectural Decisions

Why this specific stack was chosen over standard defaults for this build.

IF YOU WANT A CITY AI PRODUCT

The AI is only as good as the data underneath it.

A city AI product built on scraped or low-quality data will confidently give wrong answers. Curated data at lower volume outperforms scraped data at high volume every time.

ON GROUNDING AI RESPONSES

Hallucination prevention is architecture — not prompting.

Prompt instructions to 'only use provided data' are not reliable at scale. A strict RAG architecture where the model cannot generate outside the retrieved context is the only production-safe approach.

ON DIRECTORY BUSINESS MODEL

Discovery quality beats listing quantity.

A directory with 500 well-curated, accurate listings is more valuable than one with 10,000 outdated or duplicate entries. The quality of each listing determines whether the user comes back — not the count.

MEASURABLE OUTCOMES
4,000+
Local businesses indexed
All manually curated and verified
60%+
Sessions using AI query
vs category browse
3:2
AI query to browse ratio
Users prefer natural language

The Final Result

4,000+ businesses indexed. The AI query layer handles 60%+ of all discovery sessions — users prefer the natural language interface over the category browse by a 3:2 margin. Architecture replicated for AskBLR in 2025.

WHAT THIS MEANS FOR YOU
IF YOU WANT A CITY AI PRODUCT

The AI is only as good as the data underneath it.

A city AI product built on scraped or low-quality data will confidently give wrong answers. Curated data at lower volume outperforms scraped data at high volume every time.

ON GROUNDING AI RESPONSES

Hallucination prevention is architecture — not prompting.

Prompt instructions to 'only use provided data' are not reliable at scale. A strict RAG architecture where the model cannot generate outside the retrieved context is the only production-safe approach.

ON DIRECTORY BUSINESS MODEL

Discovery quality beats listing quantity.

A directory with 500 well-curated, accurate listings is more valuable than one with 10,000 outdated or duplicate entries. The quality of each listing determines whether the user comes back — not the count.