Delivered engagementPropTech · $25k – $35k
ArgoFetch

Databode · Bodey AI assistant

Delivered engagement. Coralsoft designed and built this product end to end; figures below retain their evidence level.

WebBackendNext.js 16 (×2 apps)React 19Tailwind CSS v4
argofetch-ai-property-intelligence.example / dashboard
ArgoFetch Bodey AI chat answering a market trend question with an inline chart
The situation

What was in place before we started.

A production real-estate intelligence SaaS for the Sunshine Coast property market. Bodey — the on-platform AI assistant — answers natural-language questions about live sales, listings, and time-on-market data via a streaming tool-call pipeline, with Stripe billing, an operator admin panel, and an interactive property map.

ArgoFetch is a production real-estate intelligence platform built for the Sunshine Coast property market under the Databode brand. The platform serves real-estate agents and investors who need fast, reliable answers about local sales, listing volumes, price trends, and time-on-market data. The product's core is Bodey — an AI assistant that answers natural-language questions about property data using a live Supabase database, not pre-computed summaries.

Bodey is sold as a SaaS product with tiered subscription plans, usage quotas, and an operator-facing admin panel. The system had to resolve natural-language timeframes precisely, enforce strict data attribution, and handle complex multi-tool queries in a single streaming response — all on top of complete SaaS infrastructure: tiered billing, per-user monthly quotas, a configurable operator admin, an interactive property map, and a module system that lets the operator change behaviour without code changes.

Constraint

Every Bodey answer had to be grounded in a live Supabase query executed during the stream — no pre-aggregated datasets, no generic market knowledge. Natural-language timeframes like "last financial year" or "Q3 2023" had to be resolved precisely before the tool calls fired.

Timeline
6 months reconstructed
Team
5 people reconstructed
Budget
$25k – $35k reconstructed
Platforms
2
Stackrecorded
Next.js 16 (×2 apps)React 19Tailwind CSS v4TanStack Query v5Zustand v5GSAP 3Recharts 2Next.js Route HandlersEdge runtime (Bodey chat)Node.js runtimeSupabase Postgres + RLSSupabase Auth + SSR cookiesTypeScriptZod validationVercel Edge ConfigOpenAI GPT-4oVercel AI SDKStripe (tiered billing + quotas)Google Maps API
Challenges

Each constraint, and what we did about it.

Constraint

Every Bodey answer had to be grounded in a live Supabase query executed during the stream — no pre-aggregated datasets, no generic market knowledge. Natural-language timeframes like "last financial year" or "Q3 2023" had to be resolved precisely before the tool calls fired.

What we did

Two Next.js 16 applications share a single Supabase Postgres instance — the customer platform and the operator dashboard — communicating through Supabase Auth with SSR cookies and Bearer-token API access. The Bodey chat endpoint runs on Edge runtime to keep streaming latency near zero; every other Route Handler runs on Node.js, where the seven-stage pipeline (auth, session, prompt assembly, tool registry, tool execution, post-stream cleanup, accounting) lives.

Results

Outcome, with the source of every figure.

7
Pipeline stages per Bodey request, from auth to post-stream accounting
self-reported — Coralsoft's own figure for its own delivery, stated in cases.ts. No third-party attestation in the sources.
5
Zod-typed tools live-querying Supabase during a single streaming response
self-reported — Coralsoft's own figure for its own delivery, stated in cases.ts. No third-party attestation in the sources.
2
Linked Next.js apps sharing one Supabase instance — platform + operator dashboard
self-reported — Coralsoft's own figure for its own delivery, stated in cases.ts. No third-party attestation in the sources.
Showcase

How the system fits together.

4 of 5 views
argofetch-ai-property-intelligence.example
ArgoFetch interactive property map with a Peregian Springs property tooltip
argofetch-ai-property-intelligence.example
ArgoFetch operator dashboard of drag-and-drop analytics modules
argofetch-ai-property-intelligence.example
ArgoFetch — product screenshot
argofetch-ai-property-intelligence.example
ArgoFetch — product screenshot
Roadmap

How it was sequenced.

6 monthsreconstructed delivery
Weeks 1–4

Discovery & architecture

Streaming chat over OpenAI GPT-4o via the Vercel AI SDK, with five Zod-typed tools running live Supabase queries mid-response — enabling chained reasoning and multi-step analysis without leaving the stream.

  • Bodey AI assistant
Weeks 5–14

Core build

analyzeSales, analyzeListings, analyzeMatchedListings, buildChartSpec, and getDataSourceInfo — each a typed contract over the live property dataset, with a timeframe resolver mapping phrases like "las

  • Five-tool data registry
Weeks 15–20

Integrations & data

buildChartSpec returns Recharts-compatible visualisation specs that render inline after the response completes — so chart metadata is extracted from the stream and hydrated client-side without a second roundtrip.

  • Inline chart generation
Weeks 21–26

Hardening & QA

Google Maps API integration with property pins, suburb overlays, and a configurable analytics module system — operators can drag, drop and reconfigure dashboard layouts without redeployment.

  • Interactive property map
Week 27

Launch & handover

Tiered subscription plans with per-user monthly prompt quotas enforced at the auth stage of every Bodey request — immediate rejection if exhausted, no wasted tokens.

  • Stripe billing + quotas
Related

More in PropTech.

AI financial assistant for NRIs
Anar chat interface with conversation history and task tracker sidebar
Delivered engagement$25k – $35k
Anar
AI financial assistant for NRIs
webbackendFintech
3 metricsDelivered

More work like this.

Every case study is a Coralsoft delivery story, with the evidence behind each figure kept visible.