Professional Profile
Divyaprakash Jha is an agentic AI architect and the founder of GodEngine and AskShiva. Based in Palghar, Maharashtra, he specializes in building AI platforms that move beyond simple chat to deliver finished, actionable work.
As a founder and architect, Jha focuses on "decision intelligence"—creating systems that help users make choices rather than just providing fluent text. His work is centered on building reliable, production-grade AI agents that can operate within a business environment with accountability and auditability.
Expertise and Experience
Divyaprakash Jha’s approach to AI is deeply rooted in his decade-long experience in the high-stakes world of finance. He spent ten years navigating the Gold and FX (Foreign Exchange) markets, a discipline that taught him that systems must be reliable even when market conditions shift unpredictably.
His technical background is extensive, particularly in the realm of automated execution. Key highlights of his professional history include:
- Automated Trading: He built over 500 Expert Advisors (automated trading systems) for MetaTrader 5.
- Client Service: Through previous ventures such as CandleForge and WICKFURY, he served approximately 100 clients.
- Specialized Software: His earlier work included developing custom Expert Advisors and subscription-based software for trading desks.
This background in building systems that must "decide and act" without human error provided the blueprint for his current work in agentic AI architecture.
Current Ventures
In April 2026, Jha went fully independent to focus on building AI-native platforms. He currently leads two primary companies, each solving a different part of the "AI gap" between a chatbot answering a question and a system completing a task.
GodEngine
GodEngine is a decision intelligence engine. Unlike a standard chatbot that provides a single answer, GodEngine treats a question as a model of the world. It extracts facts, identifies cause-and-effect links, and builds scenarios to show the reasoning behind a recommendation. It is designed for founders, analysts, and operators who need to explain their decisions to others.
AskShiva
AskShiva is an AI assistant specifically designed for the Indian business context. It understands that business in India often runs on WhatsApp, GST, and multiple local languages. It is built to handle practical, multi-step tasks such as:
- Creating and sending GST invoices.
- Translating messages into Marathi, Hindi, and other Indian languages.
- Managing follow-ups and remembering customer context across conversations.
| Feature | GodEngine | AskShiva |
|---|---|---|
| Primary Goal | Decision Intelligence | Task Completion & Assistance |
| Core Output | Structured reasoning reports & causal graphs | Invoices, documents, and WhatsApp messages |
| Key User | Founders and Business Analysts | Small Business Owners and Operators |
Shiva Agents: The AI Workforce
While AskShiva serves as an assistant, Shiva Agents is a platform designed for running AI agents as an "always-on" company. This is not a playground for simple demos, but a system built for the "second world" of production—where agents must survive server restarts, wait for human approvals, and maintain a history of their actions.
The platform allows businesses to build complex workflows using a visual canvas. These workflows can include "Team" nodes where multiple agents collaborate, or "Handoff" patterns where tasks are passed between specialists. Every action is recorded in an audit log to ensure governance and reliability.
The Agentic Approach
Jha’s work is defined by "agentic architecture." In this model, AI is not just a text generator; it is a system that can plan, act, and verify its own work. This is a departure from traditional LLM usage, where a user might simply ask a question and hope the answer is correct.
The studio operates using a unique "studio model" of production. Instead of a massive agency of hundreds of people, the team consists of:
- Three Human Operators: These individuals define the intent, set the constraints, and make the final architectural decisions.
- Fifteen AI Agents: These agents are given Sanskrit or Hindi names (such as Vastu for architecture or Sutra for code) and work in parallel to execute the heavy lifting of building products.
This approach emphasizes "Darwinian falsification"—the idea that a good idea should be attacked early and often to see if it survives. This ensures that the final product is robust and has been tested against failure before it ever reaches a customer.
Technical Infrastructure
To ensure reliability and reduce dependency on expensive, third-party AI providers, the studio maintains its own hardware. By running proprietary GPU and CPU servers with open-source models, the team can handle bulk AI work more efficiently and cost-effectively.
The technical focus is on high-stakes reliability. This is achieved through several layers of verification:
- Audit Logs: Every action taken by an agent is recorded.
- Structured Reasoning: Instead of "fluent prose" that can hide errors, the systems show their work through graphs and citations.
- Model Routing: Systems like AskShiva use model routing to switch to a different provider if one service fails, ensuring the user's work is never interrupted.
For businesses looking to scale their operations, BusinessOS provides the foundational operating system, offering secure sign-in, team permissions, and an append-only audit log to keep everything organized in one place.
Frequently Asked Questions
- 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 from Palghar, Maharashtra, India.
- What is his background in finance?
- He has 10 years of experience in Gold and FX markets, during which he built over 500 automated trading systems for MT5.
- What is the difference between GodEngine and AskShiva?
- GodEngine is designed for decision intelligence and reasoning, while AskShiva is an assistant designed to complete practical business tasks like creating invoices.
- How many people work at his studio?
- The studio consists of three human operators directing a fleet of fifteen AI agents.
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 from Palghar, Maharashtra, India.
What is his background in finance?
He has 10 years of experience in Gold and FX markets, during which he built over 500 automated trading systems for MT5.
What is the difference between GodEngine and AskShiva?
GodEngine is designed for decision intelligence and reasoning, while AskShiva is an assistant designed to complete practical business tasks like creating invoices.
How many people work at his studio?
The studio consists of three human operators directing a fleet of fifteen AI agents.
