Skip to main content
Prasad Kavuri

AI Platform Modules

16 Production AI Modules

Every module runs on a shared governance foundation — guardrails, rate limiting, observability, eval-gated CI, and drift monitoring. Each is tied to a real enterprise platform concern: quality, reliability, cost, retrieval, orchestration, or oversight.

Governance layer

Shared

Rate limiting

All routes

Eval gating

CI-enforced

Audit trail

Trace IDs

16 modules

Core AI Infrastructure

Foundation systems — quality, retrieval, routing, and governance

RAG Pipeline

Live
Browser WASM

Improves grounded enterprise knowledge retrieval and reduces unsupported AI answers in operational workflows

Real retrieval-augmented generation with Transformers.js embeddings and ChromaDB — runs entirely in your browser.

What this proves

Shows how enterprise knowledge can be retrieved with source traceability, relevance controls, and citation — not hallucination.

Transformers.jsChromaDBnomic-embed-text

LLM Router

Live
Server API

Balances quality, latency, and spend across model tiers for production AI request routing

Real multi-model routing across Llama 3.1 8B, 70B, and Mixtral — see live latency, cost, and quality trade-offs.

What this proves

Routes each AI request to the optimal model — from fast WASM models for simple tasks to Qwen3.6-27B for agentic reasoning — demonstrating LLM FinOps and decision intelligence at the platform level.

GroqMulti-modelLive latency

Vector Search

Live
Browser WASM

Enables semantic discovery and natural-language retrieval across enterprise content systems

Semantic search with real sentence-BERT embeddings and UMAP visualisation of the embedding space.

What this proves

High-throughput semantic search over large corpora with real-time filtering — the retrieval layer for any serious AI product.

all-MiniLM-L6-v2UMAPCosine similarity

Native Browser AI Skill

Live
On-Device AI

0ms Latency and 100% Privacy (Edge-inference) for accessibility auditing workflows

A reusable Chrome AI Skill that audits webpage accessibility using on-device Gemini Nano.

What this proves

On-device AI inference with zero server dependency — the architecture pattern for compliance-sensitive enterprise tooling.

Chrome Prompt APIGemini NanoWASM

Agentic Systems

Autonomous agents, tool-use orchestration, and enterprise control

Multi-Agent System

Live
Server API

Coordinates specialized agent workflows with approvals and auditability for high-impact enterprise decisions

CrewAI-powered agents with real LLM calls via Groq — Analyzer, Researcher, and Strategist collaborating in real time.

What this proves

Demonstrates governed agentic workflows with human-in-the-loop approval checkpoints, audit trails, and role-based orchestration — safe for enterprise deployment.

CrewAIGroqLlama 3.3Handoff Architecture+2

MCP Tool Demo

Live
Server API

Improves reliability by standardizing tool access across agent workflows

Model Context Protocol in action — watch an LLM discover and call tools to answer questions about Prasad's background.

What this proves

Shows how standardized tool protocols reduce integration overhead and make agent capabilities composable across enterprise systems.

MCPTool UseGroq API

Enterprise Control Plane

Live
Server API

Operationalizes enterprise AI oversight with RBAC, spend controls, and traceable policy enforcement

Org-wide AI governance dashboard — RBAC, group spend limits with token-cost tracking, and structured observability feed.

What this proves

Operational guardrails for enterprise AI: RBAC, spend analytics, token budgets, and structured observability in a single control surface.

EnterpriseRBACStructured ObservabilityToken Analytics

Edge Agent + Cloud Agent Collaboration

Live
Edge + Cloud

Enforces data residency at the device boundary while delivering cloud-quality reasoning — zero PII exposure to external APIs

Three-tier privacy-first AI pipeline: BERT NER redacts PII in the browser via Transformers.js ONNX, a HITL gate governs the handoff, and Groq produces an executive summary from the sanitized payload only.

What this proves

Demonstrates the governance-first agentic handoff pattern enterprises need for regulated AI workflows: edge extraction, explicit HITL approval, and auditable cloud orchestration.

edge-aibrowser-agentlocal-inferenceprivacy-first-ai+4

Agent Auth Demo

Live
Server API

Eliminates bespoke agent onboarding by implementing the emerging open standard for agent identity

Live auth.md protocol implementation — AI agents register anonymously, claim with email + OTP, then call MCP tools with a Bearer credential.

What this proves

Demonstrates agent-native authentication: anonymous registration, email claim, OTP upgrade, and authenticated tool access — the identity primitive every agentic platform needs.

auth.mdOAuthMCPBearer token+1

Real-Time Spatial AI + World Modeling Engine

Live
Three.js + API

Accelerates logistics and spatial planning with policy-aware world artifacts that are explainable, reviewable, and simulation-ready

Perception → reconstruction → agent reasoning. Precomputed 3D mesh playback with drift correction visualization and LLM spatial query layer. Controllable parametric spatial design — refine generated scenes with natural-language instructions. Changes are validated, diffed, and auditable.

What this proves

Brings LLM reasoning into spatial and operational planning — policy-aware world models that are auditable, diffable, and simulation-ready.

World GenerationSpatial AIThree.jsGLB Export+8

AI Applications

Production AI experiences across modalities

AI Portfolio Assistant

Live
Server API

Cuts expert lookup time by making organizational knowledge instantly accessible

Streaming full-context assistant over my experience with optional retrieval-enhanced grounding and cited context cues.

What this proves

Demonstrates conversational AI grounded in structured knowledge — RAG + LLM working together on a real corpus.

Vercel AI SDKStreamingRetrieval Grounding

AI Hiring Intelligence

Live
Server API

Reduces recruiting cycle time through faster candidate-role alignment

Paste a job description — get multi-dimension fit scoring, HITL-gated tailoring, and an ATS-optimized resume with drift detection.

What this proves

AI-powered resume tailoring at scale — shows LLM orchestration applied to a high-frequency, measurable business workflow.

JD parsingSkill matchingHITLEvaluation+1

Multimodal Assistant

Live
WebGPU

Lowers processing costs by running vision workflows closer to users

Florence-2 image captioning and OCR running in-browser via Transformers.js — no server, no API key.

What this proves

Edge-deployed vision AI with zero server cost — the architecture pattern for privacy-sensitive document and image workflows.

Florence-2WebGPUIn-browser

Model Quantization

Live
Browser ONNX

Reduces infrastructure overhead through smaller, faster production models

Live ONNX benchmark comparing INT8 vs FP32 inference — real file sizes, real latency, real quality diff.

What this proves

Demonstrates 4-bit MoE quantization delivering 70%+ memory reduction with minimal quality loss — the cost lever most teams overlook.

ONNXINT8 vs FP32Transformers.js