Balancing model cost and agent quality at scale
10 December 202610:00 AM PT
Chris MunnSolutions Engineer
Doug GuthrieSolutions Engineer
Every engineer and PM now needs to be cost conscious with their token spend. A cheaper model can cost more if it leads to more retries, longer workflows, or lower-quality results. Evals help you figure out and compare trade offs.
In this live workshop, Braintrust will walk through several strategies to make your agent more efficient, and to lower your LLM and coding agent spend.
What you'll learn
- How to compare models, including open-source, on cost and quality side by side
- How to use Jev as a lower-cost first pass for lower-risk or less complex correctness checks
- How to use coding agent insights to find and resolve recurring issues that are driving up costs
- How and when to run batch evals at 50% the cost
Recent on-demand workshops
Eval foundations: Answering questions about your agent
4 November 202610:00 AM PT
In this live workshop, Jess will share example evals developed at Braintrust for three different use cases. Testing an agent workflow, choosing a model judge, and comparing models.
Eval foundations
7 October 202610:00 AM PT
Designed for new Braintrust users, this workshop will cover the core foundations of evals and how to get started with Braintrust.
Put the workshop into practice
Start using Braintrust to trace what ships, score it against real data, and turn every regression into an eval you can rerun.