Schedule
Welcome
| Time | What |
|---|---|
| 18:00 | Doors Open — refreshments |
| 18:30 | Welcome — Vikram |
Talks (First Half)
| Time | Speaker | Topic | Slot |
|---|---|---|---|
| 18:30 | Vikram Pawar view slide |
Greetings & welcome | 10 min |
| 18:40 | Dr Chinmay Hegde view slide |
Security and Ethical Scare of Industrial AI | 15 min |
| 18:55 | Lakshmi Narayana view slide |
Architecture-as-Context: Building AI-Native Engineering Governance with Claude Code | 15 min |
| 19:10 | Nanda Kumar view slide |
When System Prompt fails — Constitutional AI by Anthropic | 15 min |
Break
| Time | What |
|---|---|
| 19:30 | Food & Refreshments Break |
Talks (Second Half)
| Time | Speaker | Topic | Slot |
|---|---|---|---|
| 20:00 | Geetansh Aditya view slide |
Agentic Prompt Injection: how-to, impact & offensive tooling | 15 min |
| 20:15 | Aranya Bandhu view slide |
Autonomous AI Agent that helps in Autonomous Payments using Harnessing and Guardrailing AI | 15 min |
| 20:30 | Rohit Madhavan view slide |
Train the Team, Not the Analyst: An RL Gym for Securing AI SOC Agents | 15 min |
Closing
| Time | What |
|---|---|
| 20:45 | Networking |
| 22:00 | Doors close |
7 speakers — 6×15-min, 1×10-min.
Speakers
- Vikram Pawar — Claude Community Ambassador · CCCL.ai Founder · RUMQ.ai Founder · Greetings & welcome
- Dr Chinmay Hegde — CEO & Managing Director · Astrikos AI · Security and Ethical Scare of Industrial AI
- Lakshmi Narayana — Director of Engineering · Capital One · Architecture-as-Context: Building AI-Native Engineering Governance with Claude Code
- Nanda Kumar — Applied AI & AI Security Leader · When System Prompt fails — Constitutional AI by Anthropic
- Geetansh Aditya — Cybersecurity Analyst · Agentic Prompt Injection: how-to, impact & offensive tooling
- Aranya Bandhu — AI Harness Engineer · Autonomous AI Agent that helps in Autonomous Payments using Harnessing and Guardrailing AI
- Rohit Madhavan — Security Analyst · Train the Team, Not the Analyst: An RL Gym for Securing AI SOC Agents
About
CCCL Bengaluru #6 — Securing AI Agents. Six talks on AI security — industrial AI, engineering governance, Constitutional AI, prompt injection, agent guardrails and RL for SOC agents — three before the break and three after, each a 15-minute slot with time for Q&A. Organised by Vikram Pawar (Claude Community Ambassador).