|
Production Systems SaaS platforms serving real customers |
Applied AI LLM pipelines, RAG, multi-tenant inference |
Full Stack FastAPI · Next.js · Supabase · Celery |
We design and ship production-grade software where applied AI meets real-world business operations. Our work spans distributed backends, vector retrieval pipelines, secure multi-tenant SaaS, and high-fidelity mobile clients.
We are not interested in demos. We ship.
An autonomous AI agent that handles WhatsApp & Email for small and medium businesses, 24/7. rehxa.com
RehXa is a multi-tenant B2B SaaS platform that ingests business knowledge (RAG), connects to customer messaging channels, and deploys AI agents capable of replying with full conversational context, brand-accurate tone, and confidence-gated escalation.
Architecture & Engineering Decisions
| Layer | Stack | Rationale |
|---|---|---|
| API | FastAPI (Python 3.11+) | Async-first, Pydantic validation, OpenAPI by default |
| Database | Supabase Postgres + pgvector | Row-level multi-tenant isolation by org_id; vector search co-located with |
| relational data | ||
| Background Jobs | Celery + Redis | Knowledge ingestion, embedding generation, follow-up scheduling — never blocks the |
| request path | ||
| AI Inference | OpenAI (primary) + Anthropic Claude (fallback) | Provider-redundant; per-org system prompts; confidence |
| scoring on every response | ||
| OAuth & Email | Composio | Bypasses 6-week Google OAuth verification cycle; unified Gmail / Outlook surface |
| Meta Cloud API (Embedded Signup) | Per-org access tokens; webhook-driven ingestion | |
| Billing | Lemon Squeezy | Merchant-of-record; handles global VAT and trials |
| Frontend | Next.js 14 App Router · Tailwind · shadcn/ui | Server components for dashboard, edge runtime for marketing |
Engineering principles applied:
- Strict per-org data isolation enforced at the query layer, not just the API layer
- All long-running operations (document ingestion, batch follow-ups) offloaded to Celery
- Confidence-gated AI: every response carries a 0.0–1.0 score, sub-threshold replies escalate to a human
- Pre-launch security audit completed; load tested with Locust (50 concurrent users sustained)
Live System Capabilities
- Unified inbox across WhatsApp + Email with real-time conversation threading
- RAG over uploaded business documents (up to 500MB per tenant)
- Per-tenant tone and personality calibration from sample writing
- Automatic multilingual handling (language detected from inbound message)
- Follow-up engine running on cron-driven Celery beat
- Team accounts with role-based assignment
- GDPR-compliant data export and deletion
Source code is private. Architecture documentation, system design diagrams, and a video walkthrough are available in the linked architecture repo.
|
RehXa — Live
Multi-tenant AI customer-message platform.
|
DevScope
AI developer assistant — debugging, doc generation, OCR-driven context capture.
|
| Project | Surface Area |
|---|---|
| Excel AI Insights | Tabular ingestion → automated summarization & chart generation |
| Resume Optimizer | Embedding-based JD-to-resume alignment scoring |
| YouTube Summarizer | Transcript chunking, chapter generation, semantic compression |
| Website Chatbot | Site-scoped RAG with custom embeddings |
| Feedback Analyzer | Review clustering, pain-point extraction, sentiment trend analysis |
| App | Surface Area |
|---|---|
| Habity | Habit tracking — streaks, 2FA, cloud sync, in-app help center |
| MoneyMate | Real-time FX conversion across 150+ currencies |
| OilHub | UI prototype — Pakistan-first engine oil marketplace |
- Production-first. Every project is built to ship, scale, and survive real users.
- Security on day one. Pre-launch audits, RLS, encryption at rest and in transit — not as afterthoughts.
- Observability by default. Structured logging, load testing, error budgets.
- Lean architecture. No premature abstraction. No frameworks chosen for résumé reasons.
We work with founders, engineering teams, and organizations on:
- Production AI systems — RAG pipelines, agentic workflows, LLM cost optimization
- Multi-tenant SaaS architecture — from schema design to billing integration
- Mobile applications — React Native, App Store / Play Store delivery
- Technical due diligence — architecture review for investors and acquirers
