I build AI systems that actually do things.
AI Engineer & Full-Stack Developer building agentic systems, dynamic workflows, automation, APIs, and modern web applications.
• Celery Worker #1: Multi-Doc LLM Synthesis
• Celery Worker #2: Third-Party API Verification
What I Build
Practical software engineering bridging autonomous agent reasoning with robust production infrastructure.
AI Engineering
AI agents, multi-agent workflows, custom runtime orchestration, LangGraph, tool use, and human-in-the-loop (HITL) review architectures.
Backend Engineering
FastAPI, asynchronous Python microservices, MongoDB persistent workflow state, Redis caching/messaging, Celery background task workers, and robust APIs.
Full-Stack Development
Next.js, TypeScript, Tailwind CSS, responsive web applications, static exports for production hosting, and conversion-engineered interfaces.
Automation & SEO
Content automation, site-scale vector indexing, internal linking algorithms, WordPress REST APIs, web research agents, and data-driven crawling.
Featured Projects
Real engineering systems built around dynamic AI, multi-agent coordination, and production workflows.
ONE AI(Legacy AI)
An AI agent platform built around FastAPI, MongoDB, Redis, Celery, LangGraph, custom Python orchestration, and human-in-the-loop workflows.
Most AI applications are architected as static, single-track pipelines (Prompt → Agent → Tool → Response). This brittle approach collapses when business requirements demand multi-step reasoning, conditional routing based on dynamic intermediate states, parallel branch execution, or human sign-off before committing state changes.
RentDesk
An AI-powered WhatsApp assistant that automates rental bookkeeping, records tenant payments directly into Google Sheets, and answers tenant balance queries in real time.
Landlords and property operators waste countless hours fielding repetitive WhatsApp messages from tenants ('What is my current balance?', 'Did you get my transfer?'), while manually copying unstructured payment screenshots or text notes into spreadsheet ledgers.
MarketLens
An AI-powered product research agent that gathers product data from Daraz, OLX, and the wider web, analyzes prices, compares new versus used markets, and produces a final market intelligence report.
Conducting competitive product research across regional e-commerce platforms and classifieds (like Daraz and OLX) requires tedious manual search queries, copying price outliers, distinguishing brand-new retail items from secondhand listings, and synthesizing price elasticity by hand.
Browser-Based Product Intelligence Agent(Playwright MCP Product Research)
An AI-powered product research workflow that uses Playwright MCP to interact with websites through browser automation and gather information for product analysis.
Modern JavaScript-heavy single-page applications (SPAs), dynamic pricing filters, and interactive search modals resist standard static HTTP crawlers. Extracting product information from these platforms requires real browser execution, form interaction, pagination clicking, and handling dynamic DOM mutations.
WordPress Article Content Bot
An automated WordPress content generation and internal linking system powered by LangGraph, Groq, and Google Gemini with site-scale vector indexing and PageRank/Search Console authority signals.
Publishing authoritative, SEO-optimized articles at scale is bottlenecked by repetitive manual steps: crawling existing content to avoid topic cannibalization, generating in-depth drafts with correct semantic headings, drafting JSON-LD structured schemas, producing header visuals, uploading to WordPress, and crucially: discovering and updating legacy articles with relevant internal links.
Haywood Technologies
A modern IT consultancy website built with Next.js, TypeScript, Tailwind CSS, and a strong focus on technical SEO, responsive design, structured data, and production deployment.
Enterprise IT consultancies need an authoritative digital presence that delivers exceptional visual engagement, pristine Lighthouse performance, and exhaustive technical SEO — while remaining fully deployable to low-cost, secure static/shared hosting environments without requiring Node.js server daemons.
SEO Automation & Web Experiments
A collection of technical SEO automation scripts, internal linking algorithms, sitemap graph crawlers, and content intelligence utilities.
Technical Snapshot
Technologies and libraries applied across real projects. No exaggerated or unused tools.
AI & Agents
- ›LangGraph & Dynamic Orchestration
- ›Multi-Agent Workflows & Branching
- ›Human-in-the-Loop (HITL) Review Nodes
- ›Model Context Protocol (MCP)
- ›Structured Output Parsing (Pydantic)
Backend Systems
- ›FastAPI & Asynchronous Python
- ›MongoDB (State Graph Persistence)
- ›Redis (Idempotency Cache & Broker)
- ›Celery (Distributed Task Execution)
- ›ChromaDB Vector Embeddings
Frontend & Infrastructure
- ›Python & TypeScript / JavaScript
- ›Next.js (App Router, Static Export)
- ›Tailwind CSS & Responsive UI
- ›Playwright Browser Automation
- ›Docker, Git, Linux Administration
“The main challenge isn't calling an LLM. It's designing a workflow system that could dynamically determine what should happen next.”
Anyone can send a prompt to an API endpoint. Real engineering lies in state management, resilient tool handling, parallel execution barriers, human approval gates, and keeping asynchronous background jobs synchronized with live client interfaces.
Let's build something useful.
Have an AI, automation, backend, or full-stack problem? Let's talk about technical requirements and practical solutions.