Case studiesbuilt to last.
These are engineering write-ups: the architecture decisions, trade-offs, and performance numbers behind systems we built and run, mostly our own Prism products. For client work organized by who we built it for and what we shipped, see the portfolio.
WhatsApp Cloud API console: how we built PrismWA
A shared inbox and visual flow builder for WhatsApp Business teams — with real-time messaging, role-based access, idempotent webhook processing, and a no-code automation engine built on top of Meta's Cloud API.
12+
Flow node types
<10s
Webhook-to-inbox latency
0
Duplicate messages processed
Building PrismBot: A Multi-Tenant, Multi-Agent Chat Architecture
A multi-tenant AI chatbot backend built with NestJS and TypeScript that utilizes LangGraph for a supervisor-specialist agent routing system, delivering real-time responses and autonomous CRM updates via WebSockets.
3-Stage
RAG pipeline with parallel query expansion
100%
Tenant isolation across vectors, KB, and CRM
2
Specialist agents (RAG Expert & CRM Sales)
Replacing Exotel with a Self-Hosted Voice AI Gateway — 60% Cost Reduction at 500K Calls/Day
A production-grade telephony gateway that bridges PSTN networks with AI voice applications, enabling a large social-impact foundation to cut per-minute call costs by 60% while handling half a million calls daily — with zero changes to existing AI application code.
60%
Cost reduction
500K
Calls/day capacity
<200ms
One-way audio latency
Building a Real-Time Taxi Booking App with Live Maps
A React Native taxi booking app with live driver tracking on the map. Replacing 5-second polling with WebSockets cut location delay from 4-5 seconds to under one, and API traffic by roughly 70%.
<1s
Location delay
70%
Fewer API calls
25%
Battery savings
Building a Multilingual Voice AI Pipeline with Bhashini for Public Welfare Surveys
A real-time speech pipeline on Bhashini covering 14 Indian languages, running speech recognition, translation, and synthesis end to end in under two seconds.
<2s
Pipeline latency
14
Languages supported
0
Human translators needed
PrismLMS: AI-Powered Learning, End-to-End
An LMS that generates its own supporting material. Upload a chapter and get a quiz, flashcards, a mind map, and a summary back in under a minute, streamed as they finish.
~60s
Generation time
4
AI artifacts per chapter
5
Parallel LLM executions
PrismBot RAG Implementation
A production-grade, multi-tenant AI chatbot platform enabling organizations to deploy custom, context-aware assistants across web and WhatsApp channels.
<300ms
Vector search latency
4x
Retrieval relevance improvement
10
Parallel embedding lookups
AI-Powered Interview Orchestration Platform
A multi-agent AI system that conducts structured interviews autonomously — real-time video, adaptive questioning, and objective behavioral assessment at any scale.
0
Interviewer hours per screening
100%
Structured script adherence
5
Behavioral dimensions per candidate
Ready to build something that matters?
We solve problems that don't have Stack Overflow answers. Let's talk.
Book a Discovery Call