Kong/BENGALURU

NOTE: LUMA Registration is Mandatory for attending the event.
LUMA Link: https://luma.com/qrta10hr

As AI-powered systems move from experimentation into core production workflows, the edge is rapidly becoming the new failure and attack surface where traffic, identity, policy, and AI-driven decisions converge.

This meetup is a joint collaboration between Kong and Harness, bringing together engineers to explore how edge security, reliability, and delivery must evolve in the era of AI.

Kong operates at the heart of modern platforms as the API gateway and connectivity layer, enabling secure, observable, and reliable traffic flow across distributed systems.

Harness is the AI Software Delivery Platform for everything after code embedding intelligence across testing, deployment, security, governance, and optimisation to help teams ship systems faster, safer, and at scale.

Together, we’ll explore what fundamentally changes when AI workloads meet real-world production systems and why many of today’s reliability and security assumptions no longer hold.

Rather than focusing on theory, the sessions and discussions will draw from practical engineering experience, examining why AI pushes complexity to the edge, where traditional security models break down, and how reliability, delivery, and security are now deeply intertwined. The goal is to leave attendees with clear mental models and actionable takeaways for building and operating AI-enabled systems in 2026.

This meetup is designed for SREs, Platform Engineers, Security Engineers, API practitioners, and anyone responsible for running AI-powered systems in production.

📆 Date: 28 February 2026, Saturday
📍 Location: Harness.io R&D Labs, Bengaluru
Maps: Harness Office

🏗 Agenda
10:00 – 10:25 AM
• Introductions
• Kong × Harness collaboration overview

10:30 – 11:00 AM
• Topic: From Requests to Reasoning: Rethinking Edge Defence
• Speaker: Roshan Piyush | Head of Security Research @ Harness
• Description: Edge security was designed for predictable request–response traffic and well-defined trust boundaries. AI-powered systems fundamentally break those assumptions. As reasoning models and agents move into production, the edge must govern autonomous behavior, multi-step execution, and dynamic decision-making—introducing entirely new failure modes.
In this session, Roshan will share insights from real-world security research to explain how AI reshapes the threat model at the edge and why traditional, request-based controls are no longer sufficient.
Takeaway:
A clear mental model for designing modern edge defence when AI sits directly in the request path.

11:10 – 11:40 AM
• Topic: Governing centralised AI & MCP access for companies building agentic systems
• Speaker: Suprit Kulkarni | Senior LLM Platform Engineer @ Kong
• Description: As teams move from simple chatbots to autonomous agentic systems, governing model access, tool usage, and cost becomes increasingly complex. Without the right controls, agents can trigger runaway execution, expose sensitive data, or access systems they were never meant to touch.
This session explores how Kong approaches agent-aware governance using the Kong AI Gateway and the Model Context Protocol (MCP), showing how centralized control can bring safety, visibility, and cost guardrails to agentic workflows in production.
Takeaway:
How to decouple agent logic from governance, enabling faster development without compromising security or control.

11:50 – 12:40 PM
• Panel Discussion
Edge Security, Reliability & Incident Response in the AI Era
(Featuring Kong + Harness + Industry SRE perspectives)
• Members
TBA
• Description: When AI becomes part of the critical request path, failures no longer look like traditional outages. Incidents can involve autonomous agents, unexpected execution paths, and subtle policy breakdowns that are difficult to detect and diagnose.
This panel brings together security, platform, and SRE leaders to discuss how teams are adapting their reliability and incident response practices for AI-enabled systems, sharing lessons learned from real production environments.
Takeaway:
Practical insights into operating, securing, and responding to failures in AI-powered systems at scale in 2026.

12:30 PM onwards
• Networking & Hallway Conversations
• Coffee + Lunch
• Community Connect

👥 Who Should Attend

• Site Reliability Engineers (SREs)
• Platform & Infrastructure Engineers
• Security & Edge Engineers
• API Gateway & Traffic Engineers
• Engineers building or operating AI-powered systems

📣 Community
This is a community-first, engineer-led Meetup focused on real systems, real failures, and real learnings.
Follow Kong on LinkedIN: Kong
Follow Harness on LinkedIN: Harness

✅ Registration
Limited seats. Please RSVP on Luma to help us plan logistics and food.
LUMA Link: https://luma.com/qrta10hr