DevConf.IN 2026

India is redefining the global AI landscape by treating artificial intelligence not just as a technology, but as a sovereign Digital Public Infrastructure (DPI). This keynote explores India’s unique strategy: democratizing access to compute, data, and models to ensure AI serves the public good, mirroring the transformative success of UPI and Aadhaar. We will examine this "full-stack" approach through two critical lenses.

First, we discuss leveraging global open-source innovation. By adopting open standards and models, India is building a transparent, secure AI infrastructure that avoids vendor lock-in and fosters global collaboration while maintaining strategic autonomy.

Second, we focus on local talent. With the world's fastest-growing developer community, the mission is to pivot from consumption to creation—building "sovereign" Indian language models and high-impact applications for diverse sectors like healthcare and agriculture.

However, scaling this vision faces challenges in compute availability, high-quality datasets, and the need for deep-tech skills. As we approach the India AI Impact Summit, this session issues a direct call to action for engineers: help transition India from an AI adopter to an AI shaper. Join us to discover how open collaboration and local innovation can build a self-reliant, inclusive AI future.

Let’s be honest: Agentic AI works beautifully in 30-second demos, but often falls apart the moment you push it into production. We’ve all seen it: agents that get confused by their own context windows, use a sledgehammer (Reasoning Models) to crack a nut (simple lookups), or hallucinate tool parameters because they were overwhelmed by JSON schemas. The problem isn't usually the model's IQ but the Agentic system architecture.

In this session, we will move beyond basic Agentic patterns to explore the system architecture required for robust enterprise agents. Drawing on recent, cutting-edge research, we will dissect why a single "God Model" fails and how a Mixture-of-Agents (MoA) approach succeeds.

We will explore:

• The "When to Reason" Problem: How to use Semantic Routing to classify user intent, dynamically routing queries to the most cost-effective model (e.g., routing logic puzzles to reasoning models vs. factual lookups to standard LLMs) to slash latency and token costs.  

• The "Junk Drawer" Problem: Why dumping 90+ tools into a context window breaks agent performance. This includes using a Mixture-of-Tools strategies, where we use diverse, expert agents with specialized tool access rather than one overloaded generalist.  

• The "Inner Monologue": How to implement Metacognition and governance loops in integration with the Model Context Protocol (MCP). We will demonstrate how agents can "think about their thinking," self-correcting their plans and validating facts before presenting an answer to the user.  

Stop building black boxes. Come learn how to architect agents that are auditable, efficient, and actually know which tool to use.