Webinar Agenda (30 min + 15 min Q&A):
Are you an engineer considering how to measure and observe you LLM empowered features in development
or production? Or an Enterprise AI leader willing to take your LLM empowered business process
automations finally into production? Join our webinar "Building an Optimal LLM Evaluation Stack"
to learn how to create a robust framework for evaluating and optimizing large language models.
Discover best practices, tools, and strategies to ensure your LLMs deliver optimal quality with
minimum cost and latency.
5 min
Opening Words
10 min
Why You Need EvalOps and Objectives-Driven Evaluation
• Common LLM automation failure modes
• Why LLM output evaluation is more complex than
expected
• Overview of Objectives-Driven evaluation stack
• EvalOps: Optimizing LLMs in
production
Ari Heljakka
Founder and Chief Executive Officer, PhD
10 min
Practical Evaluation Stack Building
• Building and using evaluators effectively
• Automating business processes for measurable
impact
Oguzhan (Ouz) Gencoglu
Co-founder & Head of AI
5 min
The Future of LLM Governance
Ari Heljakka
Founder and Chief Executive Officer, PhD
15 min
Q&A Session
Watch Recording
5 min
Why You Need EvalOps and Objectives-Driven Evaluation
• Common LLM automation failure modes
• Why LLM output evaluation is more complex than
expected
• Overview of Objectives-Driven evaluation stack
• EvalOps: Optimizing LLMs in
production
Ari Heljakka
Founder and Chief Executive Officer
5 min
Why You Need EvalOps and Objectives-Driven Evaluation
• Common LLM automation failure modes
• Why LLM output evaluation is more complex than
expected
• Overview of Objectives-Driven evaluation stack
• EvalOps: Optimizing LLMs
in production
Ari Heljakka
Founder and Chief Executive Officer
Ari Heljakka
Founder and Chief Executive Officer
Why You Need EvalOps and Objectives-Driven Evaluation
• Common LLM automation failure modes
• Why LLM output evaluation is more complex than
expected
• Overview of Objectives-Driven evaluation stack
• EvalOps: Optimizing LLMs in
production
Oguzhan (Ouz) Gencoglu
Co-founder & Head of AI
Practical Evaluation Stack Building
• Building and using evaluators effectively
• Automating business processes for measurable
impact
Ari Heljakka
Founder and Chief Executive Officer
The Future of LLM Governance
An overview of key trends, challenges, and strategies guiding the responsible development and governance of large language models in the future.
15 min
Q&A Session
A 15-minute Q&A where our experts will address your questions on EvalOps, LLM Evaluation, and key insights from today's session.
Ari Heljakka
Founder & CEO at Root Signals
Oguzhan (Ouz) Gencoglu
Co-founder & Head of AI at Root Signals
