# Plavaga

> Product engineers since 2010. We ship AI systems and optimize what's already live -- agentic commerce, RAG pipelines, document intelligence, conversational AI. Built on AWS.

Plavaga Software Solutions is an AI implementation and diagnostics studio based in Bengaluru, India. Most of our AI work is for Indian companies, and we have delivered for clients across the US, UK, and Middle East since 2010. We serve mid-market CTOs and technical decision-makers. Over a decade on AWS.

Last updated: 2026-08-10

## Services

- [AI Readiness Assessment](https://www.plavaga.com/services/ai-readiness): Honest evaluation of your data, infrastructure, use cases, and team readiness for AI. Actionable report, $4K-$8K.
- [Production AI Feature Delivery](https://www.plavaga.com/services/production-ai): From architecture to production in 6 weeks. One scoped AI feature, one team, one invoice.
- [AI Security Readiness](https://www.plavaga.com/services/ai-security): The AI security summary your enterprise prospects are asking for. Prompt injection testing, data leakage assessment, agent security review.
- [RAG Quality Recovery](https://www.plavaga.com/services/rag-recovery): Your RAG is returning wrong answers. We audit the pipeline, find the root cause, and fix production RAG.
- [AI Feature Monetization](https://www.plavaga.com/services/ai-monetization): Your AI features are live but your billing hasn't kept up. We wire metering, entitlements, and usage-based pricing.
- [AI Margin Intelligence](https://www.plavaga.com/services/ai-margin-intelligence): Which customers are you subsidizing with AI features? We produce the per-customer P&L that changes pricing decisions.
- [AWS Cloud Architecture & Modernization](https://www.plavaga.com/services/aws-infrastructure): Cloud architecture, legacy modernization, cost optimization, DevOps. The foundation everything else runs on.

## Track Record

- [Track Record](https://www.plavaga.com/track-record): Production AI systems and client engagements since 2010
- [Agentic Commerce Platform](https://www.plavaga.com/track-record/agentic-commerce): The production subsystem where every AI operational gap now diagnosed for clients was first encountered
- [Conversational AI for Hospitality](https://www.plavaga.com/track-record/conversational-ai-hospitality): Where production AI problems at scale first surfaced -- cost surprises, retrieval failures, and PII handling
- [Document Intelligence for Real Estate](https://www.plavaga.com/track-record/document-intelligence-real-estate): Where we learned that OCR is the real bottleneck, hybrid search is non-negotiable, and title verification is fundamentally a graph problem
- [Aarca Research -- Technical Advisory for Non-Invasive Health Diagnostics](https://www.plavaga.com/track-record/aarca-research): End-to-end technical leadership across cloud, AI, and compliance for a health-tech company building non-invasive diagnostic devices
- [Architecture Consulting -- National-Scale Examination System](https://www.plavaga.com/track-record/edtech-examination): Architecture consulting and team enablement for computer-based testing
- [Enterprise Blueprints -- Legacy Unification for Global Network](https://www.plavaga.com/track-record/enterprise-blueprints): Replacing three legacy systems with one global platform for 200,000 members
- [Redbriq -- Real Estate Inventory Management Platform](https://www.plavaga.com/track-record/redbriq): Full-stack product development from concept to production
- [Satmetrix -- Modernizing Enterprise Analytics](https://www.plavaga.com/track-record/satmetrix): Rebuilding the analytics module of a leading Customer Experience Management platform
- [Taglr -- Distributed Product Catalog Platform](https://www.plavaga.com/track-record/taglr): Cloud-native platform cataloging 80 million products with real-time search and analytics

## Blog

- [Agentic Architecture Patterns: When to Use Multi-Step Agents, Tool Chains, and Orchestration Layers](https://www.plavaga.com/blog/agentic-architecture-patterns-multi-step-agents-tool-chains): Not every AI problem needs an agent. But when it does, the architecture patterns matter. Four patterns from production systems, one anti-pattern we lived through, and a decision framework.
- [How SaaS Companies Should Be Billing for AI Features: Metering, Entitlements, and the Tools That Exist](https://www.plavaga.com/blog/ai-billing-metering-entitlements-saas): Your AI features are live but billing hasn't caught up. The metering tools that exist, how to evaluate them, and patterns that work, grounded in real per-tenant economics from a production AI system.
- [Per-Customer AI Cost Attribution: Building the Margin Map That Changed Our Pricing](https://www.plavaga.com/blog/ai-cost-attribution-per-customer-margin-map): We had hundreds of hotel properties on two commercial models and no idea which ones were profitable. The per-tenant margin map - built on Langfuse, a LiteLLM-style gateway, and Stigg - was the most important tool we shipped.
- [Guardrails for Production AI: Citation Checking, Confidence Thresholds, and Human Escalation](https://www.plavaga.com/blog/ai-guardrails-citation-checking-confidence-thresholds): Guardrails are not prompt instructions. They are infrastructure. Citation checking to catch hallucinations, confidence thresholds to trigger human review, and escalation paths that keep AI reliable when the stakes are high.
- [Debugging Production AI: The Observability Stack That Tells You Why Your System Broke](https://www.plavaga.com/blog/ai-observability-debugging-production-langfuse-traces): When a production AI system returns wrong answers, traditional APM tells you the request succeeded. It did. The answer was just wrong. Here is the observability stack we built to catch quality failures before users reported them.
- [The AWS Infrastructure Checklist We Run Before Shipping AI](https://www.plavaga.com/blog/aws-infrastructure-checklist-ai-ready-architecture): Compute, storage, networking, security, observability, cost - the AWS checklist we run before an AI system ships. Some items we learned the hard way; the rest are defaults we now reach for before the failure arrives.
- [How Infrastructure Decisions Determined Our AI Margins](https://www.plavaga.com/blog/aws-infrastructure-decisions-determined-ai-margins): We did not plan infrastructure around AI economics. We built the agent, then discovered what was missing when margins we could not explain started compounding. The gateway, the PII vault, the scaling policy -- each was forced by a failure, not a checklist.
- [When Semantic Search Fails: Building Hybrid Retrieval for Production RAG](https://www.plavaga.com/blog/hybrid-search-reranking-production-rag): Pure vector similarity search works on demo datasets. In production, it returns plausible-sounding wrong answers for the queries that matter most: exact identifiers, proper nouns, reference numbers. Hybrid search with re-ranking recovers precision without sacrificing recall.
- [LangChain Agent to Production: WhatsApp Hotel Booking](https://www.plavaga.com/blog/langchain-agent-production-whatsapp-hotel-booking): A production conversational AI handling hotel bookings over WhatsApp: room availability, pricing, confirmation, and post-booking queries. Where cost surprises, retrieval failures at scale, and PII handling problems first surfaced.
- [LangChain and LangGraph in Production: What Works, What Breaks, and What We'd Change](https://www.plavaga.com/blog/langchain-langgraph-production-lessons-tradeoffs): We shipped two production systems on LangChain and LangGraph. An honest assessment: what the framework handled well, where we fought it, and the patterns that survived.
- [Anatomy of a Production RAG System: AI-Powered Title Validation for Indian Real Estate](https://www.plavaga.com/blog/production-rag-indian-real-estate-document-intelligence): We built a document intelligence system that validates property title cleanliness across over a thousand properties in Indian metros, processing sale deed chains, encumbrance certificates, and revenue records in six languages. The architecture, what broke, and what we shipped.
- [Chunking Strategy for Production RAG: What We Changed After Real Documents Broke Ours](https://www.plavaga.com/blog/rag-chunking-strategy-production-hallucinations): The most common root cause of production RAG failures is not the model. It is the chunking strategy. Fixed-size chunking that worked in demos breaks on legal documents, financial reports, and technical manuals. We learned this processing tens of thousands of Indian property documents.

## Contact

- [Start a Conversation](https://www.plavaga.com/contact): Free 30-minute discovery call

## Optional

- [About](https://www.plavaga.com/about): Company background, team, tech stack, timeline
- [Blog](https://www.plavaga.com/blog): Articles on production AI and AWS architecture