Jagan PS
Senior AI /MLEngineer
Bengaluru, India
Actions
I am working as Senior Software Development Engineer – AI/ML at Flexera with 6+ years of experience in full-stack and AI/ML development. Based in Bengaluru, I have also presented at BIACONF (IIM Bangalore), BangPypers, and RVCE on LLMs and MLOps. A FlexHack25 winner, built scalable AI systems using Go, Python, and cloud-native tools, with certified expertise in data science and full-stack engineering.
Area of Expertise
Topics
From GitOps to AgentOps
Self-service has always been at the center of Platform Engineering. Over the years, we’ve built mature ecosystems around reusable infrastructure — Helm chart repositories, Terraform module registries, internal developer portals, and API catalogs — all designed to help teams move faster without reinventing the wheel.
But as AI agents become active participants in engineering workflows, a new question starts to emerge:
Why don’t we have a marketplace for agent capabilities?
Today, most AI agents still operate with tightly coupled tool configurations, hard-coded integrations, and manually curated access lists. Every new capability often requires custom onboarding, duplicated integration logic, and platform-level coordination. As the number of agents and tools grows, this quickly becomes difficult to scale.
This talk introduces the concept of an Agent Capability Provider (ACP) Marketplace — a self-service ecosystem where platform teams can publish reusable capabilities that agents can discover and consume dynamically through standardized protocols.
At the center of this model is the ACP Protocol, which enables a plug-and-play architecture for agent tooling. Instead of every team building custom integrations, capabilities can be registered once and exposed through a governed marketplace layer connected via the MCP Gateway. This creates a standardized contract for how tools are described, discovered, authenticated, and invoked across the organization.
We’ll explore what it means to design a true capability marketplace for autonomous systems — where agents can evaluate and select tools based on factors such as reliability, latency, cost, permission scope, and operational health.
The session will also demonstrate how dynamic capability discovery changes the way agents operate. Rather than relying on static tool lists embedded into prompts or orchestration code, agents can query the marketplace in real time to understand what capabilities are available and determine the best option for a given task.
Beyond architecture, we’ll discuss the operational and business impact of this model. One of the biggest hidden problems in enterprise AI systems today is what I call “Discovery Debt” — teams repeatedly rebuilding integrations because they have no centralized understanding of what capabilities already exist.
By treating agent tools as products within a governed marketplace, platform teams gain visibility into usage patterns, effectiveness, operational cost, and adoption across the AI fleet. This creates measurable ROI for platform engineering while also helping retire unused or low-value capabilities over time.
Key takeaways include:
• Understanding the ACP Protocol and plug-and-play capability architecture
• Designing a governed marketplace for reusable agent capabilities
• Enabling dynamic capability discovery through MCP Gateway integration
• Reducing “Discovery Debt” across AI and platform teams
• Measuring platform ROI through capability usage, effectiveness, and lifecycle management
• Building scalable self-service ecosystems for autonomous engineering systems
Agent Mesh Layer
This session explores what it means to build an Agent-Ready Internal Developer Platform as AI agents become first-class engineering participants. We’ll examine an Agent-as-a-Service architecture using Kubernetes and Agent Mesh patterns to provide discoverability, orchestration, shared capabilities, and operational control.
A key focus is the MCP Gateway, a standardized and secure interface for agents to interact with enterprise systems such as Jira, GitHub, cloud APIs, CI/CD, and internal tools—without creating uncontrolled access paths.
We’ll also cover RBAC, OPA policy enforcement, auditing, approval guardrails, and observability for autonomous actions. Finally, we’ll share practical lessons and architectural trade-offs from moving beyond disconnected automation toward a governed agent ecosystem, including the balance between speed, latency, flexibility, safety, and traceability.
Engineering Intelligence: LLM Councils, Domain Context, and Agentic Control
AI agents are no longer just thinking systems — they are becoming context-rich, tool-aware, and decision-oriented collaborators.
The real shift is not better models, but how context, retrieval, tools, and governance are structured around agents.
In this talk, we explore a practical agentic framework where:
Design and scale agentic AI frameworks where multiple LLM agents, governed by councils, domain-specific context, and agentic tools, work together to augment human intelligence—while maintaining quality, security, and enterprise-grade guardrails.
LLM agents collaborate through an LLM Council (multi-agent review, validation, and arbitration)
Each agent operates with domain-specific context powered by 16 types of RAG
Traditional MCP tools evolve into Agentic Tools with intent, memory, and policy awareness
Quality, security, and jailbreak resistance are enforced at the framework level, not bolted on later
We’ll show how agentic systems move from reactive question-answering to proactive problem-solving, and how this elevates—not replaces—human intelligence in real engineering workflows.
Beyond Single Agents: LLM Councils, Agentic Tools, and the Future of Human-AI Intelligence
Design and scale agentic AI frameworks where multiple LLM agents, governed by councils, domain-specific context, and agentic tools, work together to augment human intelligence—while maintaining quality, security, and enterprise-grade guardrails.
In this talk, we explore a practical agentic framework where:
LLM agents collaborate through an LLM Council (multi-agent review, validation, and arbitration)
Each agent operates with domain-specific context powered by 16 types of RAG
Traditional MCP tools evolve into Agentic Tools with intent, memory, and policy awareness
Quality, security, and jailbreak resistance are enforced at the framework level, not bolted on later
We’ll show how agentic systems move from reactive question-answering to proactive problem-solving, and how this elevates—not replaces—human intelligence in real engineering workflows.
This is not a product demo. It’s a blueprint for how AI-native systems actually work at scale.
Beyond Single Agents: LLM Councils, Agentic Tools, and the Future of Human-AI Intelligence
AI agents are no longer just thinking systems — they are becoming context-rich, tool-aware, and decision-oriented collaborators.
The real shift is not better models, but how context, retrieval, tools, and governance are structured around agents.
In this talk, we explore a practical agentic framework where:
LLM agents collaborate through an LLM Council (multi-agent review, validation, and arbitration)
Each agent operates with domain-specific context powered by 16 types of RAG
Traditional MCP tools evolve into Agentic Tools with intent, memory, and policy awareness
Quality, security, and jailbreak resistance are enforced at the framework level, not bolted on later
We’ll show how agentic systems move from reactive question-answering to proactive problem-solving, and how this elevates—not replaces—human intelligence in real engineering workflows.
This is not a product demo. It’s a blueprint for how AI-native systems actually work at scale.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top