Skip to main content

Detailed Project Quotation · Solution Challenge 2026

JanSamadhan — Citizen Resolution Platform

AI-assisted autonomous civic grievance management system for Indian urban local bodies. Built for 4,000+ ULBs, piloting in Delhi across 9 zones and 42+ complaint categories.

DOC-JS-2026-Q1

97% Complete · MVP Live

Team 404MVP LiveSDG 11 · SDG 169 months development19 April 2026

Basic Details

Project Identity

Team NameTeam 404
Project TitleJanSamadhan — AI-Assisted Autonomous Civic System
Live URLjansamadhan.perkkk.dev
CategorySmart Resource Allocation
SDG TargetsSDG 11 (Sustainable Cities), SDG 16 (Accountable Institutions)

Platform at a Glance

Routes

39

Citizen + Authority + Admin

DB Tables

19

28 RLS policies

API Endpoints

56+

FastAPI + Next.js

Languages

10

Sarvam STT voice input

Scope of Work & Deliverables

All modules are production-complete and live. The platform covers every stakeholder — citizens, field workers, authorities, and administrators.

Frontend Modules

  • 01

    Citizen Portal9 routes. Seva AI chatbot complaint filing, geo-pin with DIGIPIN, real-time tracking, heatmap, upvoting, gamification, SLA escalation, closure confirmation.

    Live
  • 02

    Authority Dashboard8 routes. Department-scoped view (RLS enforced), worker assignment, material request review, map visualization, performance reports.

    Live
  • 03

    Worker Mobile Web3 routes. Task list with SLA countdown, proof photo upload, Google Maps navigation to 4m² DIGIPIN coordinates.

    Live
  • 04

    Admin Control Panel11 routes. Platform-wide analytics, user management, CCTV surveillance dashboard, complaint moderation, wallet sync.

    Live
  • 05

    Public Routes8 routes. Landing page, public heatmap, leaderboard, legal pages. No login required.

    Live

Backend & AI Modules

  • 06

    FastAPI Backend35+ endpoints. Complaint intake, authority ops, worker ops, admin dashboard, CCTV proxy, WhatsApp webhook, notifications.

    Live
  • 07

    AI Service6 endpoints. YOLO v8 inference, CCTV multi-frame reliability engine, citizen corroboration, auto-ticket creation, geocoding proxy.

    Live
  • 08

    Database StackSupabase (Postgres 15 + PostGIS 3.4). 19 tables, 28 RLS policies, 14 RPC functions, 8 triggers, spatial GIST indexes, immutable audit trail.

    Live
  • 09

    IntegrationsGemini LLM, Mappls geocoding, Sarvam STT (10 languages), Meta WhatsApp Bot, Resend email, reCAPTCHA v2, Redis. All operational.

    Live
  • 10

    GCP Deployment3 Cloud Run services (Web, API, AI) with Cloud Build CI/CD pipeline, Artifact Registry, GCP Secret Manager.

    Live

Third-Party Integrations — All Operational

Google Gemini

Seva chatbot · Classification

Live

Mappls API

Geocoding · Map visualization

Live

Sarvam STT

Voice input · 10 languages

Live

WhatsApp (Meta)

Bot intake · Notifications

Live

Resend

Transactional email

Live

reCAPTCHA v2

Spam prevention

Live

Redis (Upstash)

Cache · Sessions

Live

Supabase

DB · Auth · Storage

Live

Technical Specifications

Four-layer architecture designed for Indian civic infrastructure — no proprietary hardware required, and portable to government data centres.

Presentation

Next.js 15 · React 19

Desktop + mobile web interface. Hindi & English UI. No installation required. Tailwind CSS v4, Leaflet.js + Mappls maps.

Backend API

FastAPI (Python 3.10+)

35+ REST endpoints on GCP Cloud Run. Auto-scaling, zero-downtime, 99.9% uptime SLA. JWT auth + reCAPTCHA on all public endpoints.

AI Service

Gemini Flash · YOLO v8

Gemini classifies 42 complaint categories and 4 severity levels. YOLO v8 runs a multi-frame CCTV reliability engine with citizen corroboration.

Database

PostgreSQL 15 + PostGIS 3.4

19 tables, 28 Row-Level Security policies, 14 stored RPC functions, and GIST spatial indexes.

Location

DIGIPIN (India Post)

Official 10-character location code with 4m² precision. Works offline and helps prevent duplicate filings.

Deployment

GCP Cloud Run · Cloud Build

3 services (Web, API, AI), CI/CD on push, secrets in GCP Secret Manager, and portable container deployment.

Security

JWT · RLS · reCAPTCHA

Google OAuth + email/password with PostgreSQL RLS and controlled workflow transitions via ENUM state machine.

Voice Input

Sarvam STT — 10 Languages

Hindi, English, Tamil, Telugu, Kannada, Malayalam, Bengali, Marathi, Gujarati, and Punjabi.

Project Timeline

9-month development cycle from prototype to full Delhi deployment and DPCC handover.

Months 1–2.5 · Complete

Prototype & MVP Build

Core architecture, all 4 portals, Seva chatbot, DIGIPIN integration, Supabase schema, and GCP Cloud Run deployment.

Months 2.5–5.5 · Current

Pilot Deployment

1–5 ward pilot with real complaints, field worker onboarding, authority training, WhatsApp bot activation, and CCTV reliability tuning.

Months 5.5–8 · Planned

Full Delhi Deployment

Scale to 20+ wards across 1–2 zones, onboard all 9 zones, and expand multi-department authority operations.

Month 9 · Planned

DPCC / MCD Handover

Documentation, admin training, infra transfer readiness, SLA finalization, and support transition.

Resource Requirements

Government Permissions Required

  • R1

    Server deployment accessPermission to deploy on NIC/MeghRaj infrastructure, or approval to continue on existing GCP setup.

  • R2

    CCTV network integrationPermission to integrate YOLO v8 model workflows against existing Delhi CCTV streams managed by relevant departments.

  • R3

    Department onboardingDesignation of authority accounts for participating departments with verified government email IDs.

Infrastructure & Hardware

No proprietary hardware is required. JanSamadhan runs fully on standard cloud infrastructure, and containers can migrate to NIC/MeghRaj with minimal configuration changes.

Cost Allocation

Primary quotation values are presented for a 1-ward pilot baseline using a 2% monthly complaint filing rate (1,860 complaints/ward/month).

Primary baseline: This quotation uses 1 ward as the professional baseline for Year 1. Scale-up projections can be applied from the same software/cloud model without altering the quoted line item basis.

SOFTWARE / CLOUD COST MODEL — PRIMARY 1-WARD PILOT BASELINE

ServiceBilling basisReference modelAmount (₹)
Software / Cloud CostsYear-1 BaselinePrimary 1-ward quotation baselineIncludes GCP Cloud Run, Supabase, Redis, Mappls, Gemini, Sarvam STT, WhatsApp Cloud API, and email operations.₹19,750 / month × 12 months₹2,37,000
Software/cloud reference — 1 ward / month₹19,750
Software/cloud reference — 1 ward / year₹2,37,000

FULL YEAR-1 QUOTATION — PRIMARY 1-WARD PILOT (EXCL. GST)

Line itemCalculation basisAmount (₹)
Prototype & Testing CostMVP development + QA cycleFull-stack implementation across web, API, and AI services, including end-to-end user-role integration testing.₹4,50,000
Machinery / HardwareNo proprietary hardware requiredCloud infrastructure provided by government data centres or GCP₹0
Team Stipends5 member implementation team5 members × 9 months × ₹22,000 / month₹9,90,000
Execution & DeploymentDeployment readiness and field executionFixed execution allocation covering survey, commissioning, deployment configuration, and handover readiness activities.₹50,000
Cloud & Connectivity (Year 1)Primary 1-ward pilot software/cloud model₹19,750 / month × 12 months × 1 ward₹2,37,000
Dashboard & App DevAPI toolkit + third-party development costsGemini, Sarvam STT, WhatsApp API, Mappls, and developer toolkit allocation₹60,000
Contingency Fund (10%)Risk reserve for internal implementation and scale-up contingenciesApproved contingency reserve aligned to internal project-cost coverage in the quotation sheet.₹1,42,700
Total Estimated Cost — Year 1 · 1-Ward Pilot (Excl. GST)₹19,29,700
Per-grievance infrastructure cost (1-ward, software/cloud only)₹10.62
Per-grievance full-project cost (1-ward, Excl. GST)₹86.46
Complaint volume basis (1 ward × 12 months)22,320
GST is excluded from totals above and applied separately at invoicing as per applicable tax rules.

Scale Cost Model — Interactive

Drag the slider to project Year-1 software/cloud cost from the same 1-ward baseline used in this quotation.

Wards:
1
single ward

Monthly infra cost

₹19,750

1 ward

Annual infra cost

₹2.37 L

cloud services only

Complaints / year

22K

at 2% filing rate

Per-grievance cost

₹10.62

infrastructure only

Annual Maintenance Cost

ItemScopeWhat's includedAnnual Cost (₹)
Cloud Infrastructure1-ward scale (expandable up to 7 wards)GCP Cloud Run, Supabase Pro, Redis, domain renewal, and SSL baseline operations.₹1,60,000
Developer SupportPart-time retainer (3 days/week)Security patches, dependency updates, bug fixes, and admin support.₹1,20,000
API RenewalsThird-party service continuityGemini, Sarvam STT, WhatsApp Cloud API, Mappls, and transactional email stack.₹36,000
Annual Maintenance Total (Post Year-1)₹3,16,000
Annual maintenance cloud baseline corresponds to approximately ₹13,333 per month.

Maintenance Inclusions

  • M1

    Cloud infrastructure operationsMonitoring, uptime management, and auto-scaling configuration.

  • M2

    Security and dependenciesSecurity patches, dependency upgrades, and Supabase schema migrations.

  • M3

    AI lifecycle managementGemini version upgrades and YOLO retraining for Delhi-specific CCTV patterns.

  • M4

    WhatsApp policy complianceMeta policy alignment and integration maintenance.

  • M5

    Dedicated support retainerOne dedicated developer for fixes, requests, and SLA reporting.

Competitive Benchmark

JanSamadhan is purpose-built for urban local bodies that central systems and generic CRM vendors underserve, with a strong per-grievance cost advantage.

CPGRAMS cost / grievance

₹83–250

National scale estimate · DARPG budget

JanSamadhan infra-only / grievance

₹10.62

1-ward Year-1 software/cloud baseline

Cost advantage

8–24×

Based on infra-only per-grievance baseline

Traditional-vendor delta

60–70%

Lower estimated cost vs conventional builds

CapabilityCPGRAMSSalesforce Gov CloudJanSamadhan
AI complaint classificationNoPartialYes — 42 categories, 4 severity levels
Spatial deduplicationNoNoYes — PostGIS 20m radius
Field worker dispatch + DIGIPIN navigationNoNoYes — 4m² precision
WhatsApp bot intakeNoNoYes — full flow
CCTV auto-detectionNoNoYes — YOLO v8 + reliability engine
Community severity escalationNoNoYes — upvote to severity bump
Indian language voice inputNoNoYes — 10 languages (Sarvam STT)
Per-grievance cost basis₹83–250Typically license-heavy₹10.62 infra-only · ₹86.46 full-project

All costs exclude GST · USD at ₹83.40 · GCP billed on actual CPU/memory seconds consumed
Ward population: 93,000 (Census 2011 interpolated) · Filing rate: 2% = 1,860 complaints/ward/month

Team 404 · JanSamadhan · 2026