mitramandal.ai ep4
What is mitramandal.ai?
mitramandal.ai is an AI meetup where engineers share how they've actually integrated AI into their daily development workflows. Every developer is solving applied AI differently: some are orchestrating agentic pipelines across MCPs, others are wiring real-time RAG loops into Cursor or Claude, and more are operationalizing multimodal copilots inside CI/CD. We've seen fine-tuning flywheels, retrieval sandboxes, and autonomous evaluation harnesses that ship to prod every week.
Martin Fowler nailed it recently: "we are still figuring out how to use LLMs... what I suggest is that people experiment with them... and do share the experiences."
What you'll see
agent orchestration, RAG implementations, and tool integrations
real-world case studies from production implementations
deep dives into fine-tuning strategies, evaluation methods, and model optimization
discussions on observability, guardrails, and scaling AI systems in production
Our focus
This meetup is for AI engineers, LLMOps engineers, and developers working at the intersection of applied AI and traditional software engineering. We're talking about the application of AI and how AI is being integrated into real engineering workflows.
Upcoming: episode 4 - Jun 27, 2026
We're hosting the fourth mitramandal meetup. same vibe: builders, researchers, and tinkerers sharing real-world AI workflows.
Speaker lineup:
1. Adaptive Load Balancing for LLMs
Akshay Deo, Co-Founder & CTO @Bifrost & Maxim AI
LLM providers rarely fail cleanly, they just get slow or start rate limiting you. This talk shows how an adaptive load balancer in Bifrost watches each provider's real behavior and steers traffic away from the struggling one before users notice.
2. Running Untrusted Agent Code at Scale
Everyone's building agents, but how do you deploy them securely and keep the data with you?
Shekhar Patil, AI, Infrastructure and Partnerships @Last9
Your AI agent runs code nobody on your team wrote: generated by an LLM, pulled from a registry, or shaped by a prompt-injected webhook. The moment it can call tools and spend money, you're running a multi-tenant code-execution platform with an adversary inside it. This talk shows how we deploy untrusted agents safely by making isolation structural, not conventional: enforced by the kernel, the crypto, and the database key, never by trusting the agent to behave. You'll leave with a concrete threat model, copyable controls (kernel sandboxing, per-agent crypto, pre-call budgets, tamper-evident audit), and the one test that decides them all, does a control make the attack impossible, or just tedious? It's zero trust for agents, and we'll show where a separate-kernel micro-VM finishes the job.
3. Architecting Security-First Multi-Agent Systems: Enforcing RBAC, PBAC, and Data Sovereignty
Vivek Singh, Sr Technical Leader @Cisco
In multi-agent architectures, security and compliance cannot be treated as an afterthought or an external layer. For enterprise-grade systems, dynamic data access boundaries must be fundamentally woven into how agents discover and interact with tools and data sources. This session provides an architectural deep dive into how we enforce Role-Based Access Control (RBAC) and Permission-Based Access Control (PBAC) directly within multi-agent orchestration layers. We will explore how to leverage the Model Context Protocol (MCP) to build a governed ecosystem where agents explicitly inherit user-level and context-level permissions. Crucially, we will address a core architectural challenge: Data Sovereignty vs. Insights Synthesis. You will learn how to design systems where raw data must strictly reside within specific regional boundaries (e.g., country-specific compliance laws), yet agents can still safely cross-compile and synthesize high-level insights for global orchestration. We will map out the architectural blueprints, critical edge cases to consider, and the open engineering challenges in building fully compliant, security-aware AI systems.
Last meetup
Thank you to everyone who joined us in Bengaluru for our Episode 3 (Apr 11, 2026). Event photos are now live on the Past events page