Viroop Ramagiri
Automation Specialist
Barcelona, Spain
Actions
Aiding global enterprises to scale using AI fueled by multi-cloud infrastructure (AWS/GCP/Azure).
Links
Badges
Area of Expertise
Topics
Small Talk, Big Bill - A practical look at smarter AI routing
Do you know how much your AI system spends when someone just says “Hello”?
Many AI projects start as a simple “ask me anything” bot: it greets, responds, and every interaction feels magical — until the bill arrives. This session will make the hidden cost of “Hello!” visible and show how to avoid paying the “big model price” for every small request.
We will start with a simple CLI chatbot and explore how smarter routing can decide whether a message needs a strong model, a smaller model, a predefined response, or no model at all. Along the way, we will look at guardrails, fallbacks, cost tracking, latency, and practical ways to make AI systems safer and more efficient.
Attendees will leave with a practical way to think about building AI systems that are not just smart, but also cost-aware, safer, and easier to operate.
Fat to Fit in 30 seconds: Turning AWS cloud waste into cost savings.
Many teams care about cloud costs, but cost optimization often starts too late — after a spike, a budget warning, or a painful bill through unused runtime, oversized resources, and forgotten environments.
In this session, I will share how we approached this challenge with AWS cost-optimization workflow. The idea was simple: help teams find actionable savings opportunities quickly and make cost awareness part of their normal delivery process.
We enhanced an existing aws-cost-review skill, added opening-hours automation for common AWS resources, and integrated the workflow into GitHub Actions. This allows teams to run cost checks directly in their CI/CD flow and receive a clear savings overview in under 30 seconds.
This session will cover:
- Common AWS cost leaks that many teams face
- How opening-hours automation can reduce unnecessary runtime for EC2, RDS/DocDB, and ECS
- How GitHub Actions can bring cost awareness into the developer workflow through quick, actionable savings insights
- Key learnings around configurability, holidays, wake-up behavior, and operational safety
- Real examples of monthly savings, including teams saving up to $500/month
Attendees will leave with practical ideas for making cloud cost optimization visible, repeatable, and easy to adopt — without adding heavy processes or operational overhead.
Discovering the Future of Custom AI - Build Your Own Agent
👉👉 Register here: https://og2.me/one25CustomAIAgents
Just as mobile phones have become essential tools for everyone today, the future promises a world where each of us will have our own intelligent agents by our side, revolutionizing how we interact with information.
Problem statement: Data extraction may seem straightforward when dealing with a few vendors using standardized layouts. However, the challenge multiplies when faced with over a hundred vendors, each presenting a unique format. How do we tackle this complexity? Can AI help?
In this session, Attendees will get a glimpse on how to build an Agent and its powerful AI capabilities in extracting valuable data from unstructured and semi-structured sources such as scanned copies of Invoices to effectively extract relevant information, and images to determine orientation.
We will explore insights into practical applications, best practices, and real-world examples that showcase the transformative potential of AI in data extraction.
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