Lotte Verheyden
Developer Relations Engineer · Langfuse
Lotte helps AI engineers trace, evaluate, and improve applications at Langfuse. She created Langfuse Academy and its open-source agent skill, and previously led product at InvestSuite.
Recorded on
Optimize Agent Costs Without Compromising Quality
Reduce your AI agent’s running costs with Lotte Verheyden from Langfuse. Learn how to use tracing and evals, run consistent experiments, and choose cost-saving changes while checking their impact on quality.
Loading session access
What you’ll explore
Know when you’re ready to optimize
Put good tracing and evals in place to set yourself up for success when starting cost optimization.
Run a structured agent optimization process
Run experiments on agent changes and measure them consistently.
Choose the right levers to reduce agent cost
Explore cheaper models, lower reasoning effort, fewer LLM calls, caching, pruning, compaction, and sub-agents.
About this session
Agents are expensive to run, so sooner or later you’ll want to bring your agent’s cost down. Doing this effectively, without compromising on quality, is an important skill. This session walks through the agent cost optimization process, from finding what drives your agent’s cost to measuring consistently whether your changes affect output quality.
Guest educator
Your educators at The Gen Academy
Learn with your assigned educators.
Aishwarya Srinivasan
AI Advisor / AI Educator
Co-Founder of The Gen Academy; AI educator with a 1.2M+ community. Former AI Developer Relations lead at Fireworks AI; built AI products at Google, Microsoft, and IBM. MS in Data Science, Columbia.
Arvind Narayanamurthy
Founder @ The Gen Academy | AI Solutions Architect | Ex - Adobe, Microsoft, IBM
Arvind brings a cross-company perspective on AI at scale, built across Microsoft, IBM, and Adobe, where he led data science teams and developed production-grade machine-learning solutions.