Portfolio

AI-first portfolio focused on workflow APIs, agent systems, real-time AI backends, and developer tooling. Start with the four flagship repos below, then use the rest of the page as secondary proof.

Flagship Order

If you are evaluating for AI roles, start here: EnterpriseHub, ai-workflow-api, TechNova Voice Bot, and multi-agent-demo.

Workflow APIs Agent Systems Streaming Systems FastAPI Python WebSockets 3,500+ Tests
EnterpriseHub demo

EnterpriseHub

Multi-Agent Orchestration Platform

22 Agents

Agent orchestration platform with weighted routing, cost governance, observability, prompt versioning, and eval-driven development. This is the best systems-depth repo in the portfolio.

FastAPI Streamlit PostgreSQL Redis Claude AI Docker Observability Cost Tracking
GitHub Live Demo → Benchmarks ADRs 22-agent platform | eval gates | observability

AI Workflow API

Workflow Automation Backend

FastAPI Proof

YAML-driven workflow automation backend with async job processing and SSE streaming. This is the cleanest FastAPI-first backend proof in the portfolio for AI backend and integration roles.

FastAPI ARQ Redis SSE Claude AI
GitHub YAML workflows | async workers | streaming API

TechNova Voice Bot

Real-Time Voice AI Pipeline

171 Tests

Real-time voice AI with WebSocket audio streaming, voice activity detection, Deepgram STT/TTS, and barge-in support. Strong proof for streaming and latency-sensitive AI applications.

FastAPI WebSockets Deepgram Redis Barge-In Streaming Audio
GitHub streaming pipeline | VAD | STT/TTS

Multi-Agent Demo

Planning and Routing Demo

89 Tests

Clear planning, tool use, retrieval, and conditional routing in a live demo that also runs offline with MockLLM support. Strong supporting proof for orchestration concepts.

Python LangGraph Streamlit MockLLM Routing
GitHub Live Demo 89 tests | offline demo path
Revenue-Sprint demo

Revenue-Sprint

Business Automation Pipeline

315 Tests

Upwork job scanner with 105-point scoring rubric, 4-agent proposal pipeline, prompt injection testing suite (60+ patterns), LinkedIn outreach engine.

Python Claude AI SQLite Click CLI
GitHub Benchmarks ADRs 315 tests | CI matrix 3.10-3.12
Insight Engine demo

Insight Engine

Data Analytics Platform

640 Tests

Upload CSV/Excel for auto-profiling, interactive dashboards, marketing attribution (4 models), anomaly detection (Z-score/IQR), predictive modeling with SHAP, time-series forecasting, K-means/DBSCAN clustering, feature engineering lab, model observatory (5 models), hyperparameter tuning, statistical testing, KPI framework, dimensionality reduction, advanced anomaly detection, and regression diagnostics.

Streamlit Plotly scikit-learn XGBoost SHAP Statistical Testing KPI Framework
GitHub Live Demo → API: localhost:8080/docs Benchmarks ADRs 640 tests | 3 demo datasets

Finance Analytics Portfolio

End-to-End Financial Data Pipeline

1,611 Tests

25-page interactive finance dashboard answering 17 business questions: credit risk modeling (SHAP/RF), stress testing (CCAR/DFAST), VaR analysis, A/B testing, fair lending geography (real CFPB HMDA data), causal inference, and more. Delivered as dashboard, 8-tab Excel workbook, 11 SQL query templates, 15 Jupyter notebooks, and written business memos. dbt analytics layer (DuckDB + Snowflake).

Python pandas scikit-learn DuckDB Streamlit dbt SHAP
GitHub Live Demo 1,611 tests | real HMDA data | 25 pages | 15 notebooks

Olist E-Commerce Analytics

Customer Retention and Delivery Analysis

DA Portfolio

Customer retention and delivery performance analysis on 100K+ real orders from a Brazilian e-commerce marketplace. Key findings: 93% of customers never return (vs 25-30% industry benchmark), late deliveries cost 1.2 review points, K-Means segmentation surfaces 4 actionable customer segments. Delivered as 10 SQL queries, EDA + segmentation notebooks, interactive dashboard, and written business memo.

Python pandas scikit-learn SQL Streamlit K-Means RFM
GitHub Live Demo 100K+ orders | 10 SQL queries | business memo
DocQA Engine demo

DocQA Engine

RAG Document Q and A

550 Tests

Upload PDFs/DOCX, ask questions, get cited answers. Hybrid retrieval (BM25 + vectors), cross-encoder re-ranker, query expansion, retrieval evaluation (MRR, NDCG@K), 5 chunking strategies with comparison, citation quality scoring, redundancy detection, RAGAS-style evaluation, conversation manager, document graph, batch processing, JSON/CSV export.

BM25 NumPy Streamlit PyPDF2 Re-Ranker Query Expansion Document Graph
GitHub Live Demo → Benchmarks ADRs 550 tests | mock mode

Advanced RAG System

Enterprise RAG Pipeline

Tests Passing

Enterprise-grade retrieval-augmented generation with hybrid search (BM25 + dense vectors), reciprocal rank fusion, ChromaDB vector store, FastAPI REST API with health/metrics endpoints, and Grafana observability. Designed for principal AI engineer portfolio demonstration.

FastAPI ChromaDB BM25 Docker Hybrid Retrieval Grafana
GitHub API: localhost:8000/docs FastAPI + ChromaDB | Containerizable

Multi-Agent Starter Kit

DAG Agent Orchestration

23 Tests

Production-grade DAG orchestrator with topological sort, retry/backoff, graceful degradation, BaseAgent ABC with Pydantic validation, ASCII monitoring dashboard.

Python Pydantic DAG Zero Dependencies
GitHub Benchmarks ADRs 23 tests | pip install pydantic
Scrape-and-Serve demo

Scrape-and-Serve

Web Scraping + Excel-to-Web

370 Tests

YAML-configurable web scrapers, competitor SEO analysis with gap detection, asyncio scheduler with change callbacks, backlink estimation, data validation rules engine, diff visualization, keyword extraction (TF-IDF n-grams), content scoring, data quality profiler, content intelligence, and data pipeline.

BeautifulSoup httpx SQLite Streamlit Data Pipeline Content Intelligence
GitHub Live Demo → Benchmarks ADRs 370 tests | 11 modules

Prompt Engineering Lab

Prompt Patterns and Evaluation

220 Tests

8 built-in prompt patterns (CoT, few-shot, RAG, decomposition), TF-IDF evaluation (faithfulness, relevance, completeness), z-test A/B comparison with statistical significance, reproducible benchmark runner, 7 business categories with 35 sample tasks. Prompt evaluator with ROUGE and semantic similarity, prompt versioning, and safety checker.

scikit-learn NumPy Pandas Streamlit ROUGE Evaluator Safety Checker
🚀 Live Demo GitHub Benchmarks ADRs 220 tests | 7 modules

LLM Integration Starter

Production LLM Patterns

250 Tests

Copy-pasteable LLM recipes: completion with FastAPI endpoint factory, SSE streaming, function calling with 3 demo tools, TF-IDF RAG pipeline, circuit breaker + retry hardening, per-request cost tracking, P50/P95/P99 latency measurement. Guardrails engine with injection detection, PII redaction, observability, and batch processor.

scikit-learn NumPy Pandas Streamlit Guardrails Engine PII Redaction Batch Processor
🚀 Live Demo GitHub Benchmarks ADRs 250 tests | 8 modules

Next.js AI Dashboard

Full-Stack AI Dashboard

Live

Full-stack AI dashboard with real-time metrics, chat interface, and document processing UI. Dark-mode design with Recharts analytics, shadcn/ui components, and responsive layout.

TypeScript Next.js 15 shadcn/ui Recharts Tailwind CSS
Live Demo GitHub TypeScript strict | App Router | Vercel

GHL Multi-Vertical AI Kit

YAML-Driven Bot Framework

Production

YAML-driven GHL bot framework supporting real estate, home services, and legal verticals. Configurable question flows, multi-vertical prompt templates, and GoHighLevel CRM integration.

Python FastAPI Claude AI YAML Config Multi-Vertical
GitHub 105 tests | Real estate, home services, legal

AI Workflow Automation API

Async Workflow Engine

Production

YAML-defined async workflow engine with SSE progress streaming and 3 built-in example workflows. Background task queue with ARQ, real-time status updates, and webhook notifications.

Python FastAPI ARQ Claude AI SSE Streaming YAML Workflows
GitHub 148 tests | Async pipelines | SSE progress

TechNova Voice Bot

Real-Time Voice AI Pipeline

113 Tests

Real-time voice AI pipeline: OGG to FFmpeg to VAD to STT to Claude to TTS, with sub-3s round-trip latency. WebSocket streaming, Silero-ONNX voice activity detection, Deepgram speech-to-text.

Python FastAPI WebSocket Deepgram Claude AI Silero VAD FFmpeg
GitHub 113 tests | <3s latency | PWA

Chatbot Widget SaaS

Drop-in AI Chat Widget

139 Tests

Drop-in AI chat widget with a single script tag. Full SaaS product: FastAPI + pgvector + RAG + WebSocket + Supabase JWT auth + Stripe billing. Shadow DOM isolation, streaming responses, Next.js admin dashboard. Live demo with no account required.

FastAPI pgvector Claude AI Stripe Shadow DOM RAG
GitHub Live Dashboard 139 tests | Single script tag embed

SaaS Starter Kit

Next.js 15 SaaS Boilerplate

61 Tests

Production-ready Next.js 15 SaaS boilerplate with Supabase auth, Stripe billing, TypeScript, and Tailwind. Lazy Stripe initialization for edge-compatible builds.

Next.js 15 Supabase Stripe TypeScript Tailwind CSS
View Project GitHub 61 tests | Vercel deployed

DocExtract AI

Document Extraction API

1,280 Tests

Document extraction API with async job processing, hybrid retrieval, and evaluation gates. Included here as secondary proof because it is already featured higher on the page.

FastAPI pgvector ARQ Claude AI Async Jobs Semantic Search
Live Demo 1,280 tests | Streamlit Cloud

GraphRAG Demo

Knowledge Graph-Enhanced RAG

63 Tests

Knowledge graph-enhanced RAG system. Entity extraction (spaCy + Claude), NetworkX graph traversal, BM25 + graph fusion retrieval, fact-checking, side-by-side comparison: Basic vs GraphRAG.

Streamlit NetworkX spaCy Claude AI Graph Fusion Fact-Checking
Live Demo GitHub 63 tests | 3-tab Streamlit UI

Capability Coverage

Capability Focus Key Repos
Backend and API FastAPI, PostgreSQL, Redis, Docker, CI/CD Jorge Real Estate AI, DocExtract AI
Testing and Reliability pytest, Playwright, RAGAS, bandit, mypy, GitHub Actions EnterpriseHub, Jorge Real Estate AI
Data and Analytics SQL, pandas, Tableau, Power BI, Streamlit, DuckDB Finance Analytics, Insight Engine
AI and LLM Systems Claude API, RAG, pgvector, LangChain, agentic workflows EnterpriseHub, DocExtract AI, mcp-server-toolkit