Get a free book•Principles of Building AI AgentsGet a free book•Principles of Building AI Agents

Get a free bookPrinciples of Building AI Agents
Pricing
Customers
Docs

Open Source

Platform

FrameworkBuild agents and workflows

ObservabilityMetrics, logs, traces

StudioCollaborate, evaluate, iterate

Agent BuilderCollaborate, evaluate, iterate

ServerCloud deployment for agents

By Use Case

Internal AgentsAgents in Slack and internal systems

Customer-facing AgentsAgents that act inside your product

Developer Platform AgentsAgents other product teams build on

Get Started

Latest

Books

Workshops

QuickstartBuild your first agent TemplatesAgent projects CourseVideo course on agents

BlogLatest from Mastra team ResearchResearch and benchmarks ChangelogUpdates and fixes

1 • PrinciplesPrinciples of Building AI Agents 2 • PatternsPatterns of Building AI Agents

WorkshopsLive sessions with the team Podcast • Agents HourWeekly livestreams and guests

27.4k
Login Sign Up

product
solutions
resources
Get Started
Latest
Books
- 1 • PrinciplesPrinciples of Building AI Agents
- 2 • PatternsPatterns of Building AI Agents
Workshops
- WorkshopsLive sessions with the team
- Podcast • Agents HourWeekly livestreams and guests
more

27.4k
Login Sign Up

This is not the page
you were looking for.

/docs/08-running-evals doesn't exist.

Popular paths

running-experimentsDocs
built-in-scorersDocs
custom-scorersDocs
evals-with-memoryDocs
gates-and-verdictsDocs
multi-turnDocs

Browse the docs →

Get weekly updates:

Framework

Agents
RAG
Workflows
Observability

Product

Framework
Observability
Studio
Agent Builder
Server

Developers

Docs
Changelog
Templates
Course

Resources

Blog
Research
Guides
Book · Principles
Book · Patterns
Podcast · Agents Hour

Company

About
Customers
Careers
Contact Us
Newsletter

Connect

Contact Us
GitHub
Discord
YouTube
X (Twitter)

Security
Checking status

Privacy
Terms
DPA
llms.txt