AI Developer • Solutions Engineer • Reasoning Engine Architect

"Building Reasoning Engines that move beyond simple scripts."

I am an AI Developer and former Solutions Engineer focused on architecting production-grade ML systems and autonomous agent frameworks. I specialize in building Python-driven agents that plan and execute complex tasks with strict validation layers to eliminate "hallucination" and ensure data integrity.

An orchestration layer for autonomous financial intelligence.

FinSurf is a decentralized network of specialized AI agents designed to navigate the complexities of financial data. It functions as a high-integrity research team, gathering and validating market data in real-time.

• The Goal: Transform raw financial data into professional-grade reports using a multi-agent network.
• Technical Edge: Implemented strict Python validation layers and automated RAG (Retrieval-Augmented Generation) to ensure high-fidelity outputs.
• Tech Stack: Python, Pandas, LangChain, React 19, Tailwind CSS 4, Express.

• 🔭 Current Project: FinSurf - Expanding the Profit Navigator for historical price retrieval and projected exit strategies.
• 🌱 Learning Path: Deep-diving into ML/LLM fundamentals, Cloud Infrastructure (AWS/Docker), and Higher Mathematics.
• 🤔 Seeking Input: Exploring advanced architectures for handling massive project data dumps and optimizing multi-agent communication.

I’m looking to partner with other builders focused on automating repetitive and mentally taxing tasks.

• Ask Me Anything: I'm happy to learn from your expertise or help debug your agentic workflows!
• Reach Out: sachin.nediyanchath@gmail.com
• Fun Fact: I love pandas (the library and the animal) and enjoy racing down dirt roads at a blistering 1 m/s. 🤠

Building FinSurf was an exercise in bridging cutting-edge AI orchestration with professional-grade document engineering. Here is a summary of the core engineering achievements and lessons learned:

The project demonstrated that complex tasks (like stock analysis) are best handled by a collaborative network of specialists.

• Isolation of Concerns: By separating Research, Tax, Dividend, and Sentiment logic, we reduced "prompt drift" and improved output accuracy.
• Strict Validation: Implementing mathematical precision for the Dividend Agent taught the importance of "Python-first" validation layers—calculating fractional shares and cumulative totals programmatically rather than relying on LLM arithmetic.

A significant technical challenge was generating PDFs from a modern Tailwind CSS 4 environment.

• Color Conversion: Since libraries like html2canvas do not natively support oklch or CSS variables, I developed a custom color-conversion utility to ensure high-fidelity rendering.
• Adaptive Pagination: Developed logic to dynamically switch between "Single Page if Fits" and "Multi-page" layouts, optimizing the reading experience for digital reports.

• Dynamic Grid Compression: Implemented a "Unified Report Look" where the UI automatically shifts from a standard loading grid to a dense, gapless "Analysis Block" upon completion. This required tight synchronization between React state management and Tailwind's utility-first classes.
• Dual-Density Reporting: Learning that different users prefer different data densities led to the Standard vs HD View toggle, providing flexibility between a balanced document and a high-density summary.

• Real-Time Data Flow: Integrating Perplexity for live web-search and Gemini/OpenAI for reasoning provided a robust template for RAG (Retrieval-Augmented Generation) applications that move beyond static data.

• Building the Accessibility Mode (High-Contrast/Neobrutalist) emphasized that financial tools must be legible and functional for all users, teaching that design accessibility is an architectural requirement, not an afterthought.

This summary captures the essence of FinSurf—a tool that combines sophisticated backend reasoning with a polished, user-centric frontend.