Founder of GodEngine and AskShiva
Divyaprakash Jha is the founder of GodEngine and AskShiva, two companies dedicated to building agentic AI platforms and decision intelligence engines. Operating from Palghar, Maharashtra, he leads a specialized studio composed of three human operators and fifteen AI agents.
In April 2026, Divyaprakash Jha transitioned to working fully independent to focus on the development of AI systems full-time. His current operations are structured as a highly efficient studio that leverages a fleet of AI agents to achieve the output of a much larger agency.
This studio model uses a mix of human oversight and automated intelligence. While the humans focus on high-level architecture and intent, the AI agents handle the heavy lifting of execution. This approach allows for rapid iteration and the ability to ship complex software products efficiently.
From Financial Markets to AI Systems
The logic used to build modern AI agents is rooted in a decade of experience within the high-stakes world of financial markets. Divyaprakash Jha began trading Gold and FX markets in 2016, a period that served as a rigorous training ground for developing automated systems.
In the markets, a system must be disciplined; it cannot rely on confidence, only on whether its rules hold up when conditions change. This philosophy of "rules-based execution" is the bridge between his trading background and his current work in AI architecture. Over ten years, he developed and shipped more than 500 automated trading systems, known as Expert Advisors (EAs), for the MetaTrader 5 platform.
During this time, he established two distinct software studios to serve different market needs:
- CandleForge: Focused on custom Expert Advisors and full-stack software builds.
- WICKFURY: A subscription-based model that licenses MetaTrader 5 Expert Advisors and builds software specifically for trading desks.
This experience in building "small agents"—programs that read signals, make decisions, and manage risk without human intervention—provided the blueprint for the "large agents" he builds today.
Building Decision Intelligence with GodEngine
Most AI tools are designed to answer questions, but GodEngine is designed to help you make decisions. It is a decision intelligence engine built for founders, analysts, and operators who face high-stakes choices where a simple chat reply is not enough.
When you pose a decision question to GodEngine—such as whether to open a new retail outlet in Vasai or invest in a delivery fleet—the engine does not just guess an answer. It treats the question as a model of the real world. It extracts the facts, identifies the causes and effects, and builds a knowledge graph of the situation.
The engine performs several critical steps to ensure the output is useful for business owners:
- Breakdown: It pulls entities and causal links out of the question.
- Scenario Probing: It builds multiple plausible futures and tests them, asking "what has to be true for this to work?" and "what breaks this scenario?"
- Auditable Reasoning: Every claim in the final report is linked back to a specific source or entity in the graph, so you can verify the logic.
GodEngine is available via the web and as an Android app. It is built to provide a structured, defensible report rather than a wall of confident-sounding text, making it a tool for people who eventually have to explain their decisions to others.
Empowering SMEs with AskShiva
While GodEngine focuses on high-level strategy, AskShiva is designed for the daily execution of business tasks. It is an AI assistant built to bridge the gap between receiving an answer and actually finishing a piece of work.
For a small business owner, a "clever paragraph" about how to do something is often useless. They need the task completed. AskShiva is built to handle the specific workflows of Indian business, such as managing GST invoices, translating communications into local languages like Marathi or Hindi, and interacting via voice.
The assistant is designed with several practical features for the modern entrepreneur:
- Task Completion: It can draft invoices, create spreadsheets, write code, or prepare documents.
- Memory: It maintains context across different conversations, so you don't have to re-explain your business details every time you ask a question.
- Multi-modal Interaction: You can talk to it in the browser and hear the reply back.
- Model Routing: It automatically selects the best AI model for the specific task, ensuring efficiency and reliability.
By integrating with tools like WhatsApp and handling Indian-specific documents as "first-class" outputs, AskShiva aims to be an indispensable partner for SMEs rather than just another chatbot.
The Agentic Architecture Approach
The core technology behind these platforms is a specialized "agentic architecture." Instead of relying on a single, massive model that might "hallucinate" or make mistakes, the system uses a "plan, act, verify" loop. This structure ensures that AI actions are reliable and can be checked by humans before they cause real-world errors.
In the development studio, this architecture is personified through a fleet of AI agents. Each agent is given a persona, a specific craft, and a name derived from Sanskrit or Hindi. This is not just for show; it reflects the specialized role each agent plays in the production pipeline.
| Agent Name | Specialized Craft / Role |
|---|---|
| Vastu | Architecture and structure |
| Akshar | Lettering and text |
| Vani | Words and communication |
| Ganit | Numbers and mathematics |
| Sutra | Code and logic |
| Parakh | Testing and verification |
This approach allows the studio to maintain high quality. The process follows a strict pattern: the human writes the intent and constraints, the humans decide on the high-level architecture, the agents build the components in parallel, and then the work is measured and refined.
The Foundation: BusinessOS
The ultimate vision for these technologies is BusinessOS, an AI-native operating system designed to serve as the central nervous system for an entire company. Most small and medium enterprises (SMEs) suffer from "disconnected tools"—they use one app for WhatsApp, another for GST, a third for spreadsheets, and a fourth for email. This fragmentation makes it impossible to have a single, clear view of the business.
BusinessOS solves this by building a unified foundation first. Instead of bolting different products together, it creates a single environment where everything shares the same identity, permissions, and data. This includes:
- Secure Foundations: Using passkeys, two-factor authentication, and strict data isolation.
- Unified Data: A single source of truth so that information flows between departments without manual entry.
- Auditability: An append-only audit log that records every change, ensuring transparency in how business data is handled.
By providing a single, integrated platform, BusinessOS aims to replace the messy web of disconnected apps with a streamlined, AI-driven operating system that understands the entire lifecycle of a business.
Questions people ask
What companies did Divyaprakash Jha found?
He founded GodEngine, a decision intelligence engine, and AskShiva, an AI assistant for business tasks.
Where is Divyaprakash Jha based?
He operates his AI development studio from Palghar, Maharashtra.
What is the background of Divyaprakash Jha?
Before focusing on AI, he spent ten years in the Gold and FX markets, building over 500 automated trading systems.
What is the difference between GodEngine and AskShiva?
GodEngine is focused on decision intelligence and scenario probing, while AskShiva is an assistant designed to execute multi-step business tasks like invoicing.
How many people work in his studio?
The studio consists of three human operators directing a fleet of fifteen AI agents.
