Rhesis AI Demo - Open-source testing for LLM & agentic applications
See how Rhesis AI brings collaborative testing directly into your development workflow. Your legal, marketing, and domain experts know what can actually go wrong - now they can help define the tests that matter.
This demo shows:
How teams generate comprehensive test scenarios automatically from domain expertise
Running evaluations that check what actually matters: compliance, safety, business rules, edge cases
Getting clear, actionable insights before users see your Gen AI
Integrating testing into your IDE without jumping between tools
Agenda:
00:00 Welcome
00:18 Dashboard
00:37 Projects
00:50 Endpoints
01:17 Invite your team
01:31 Knowledge
02:07 Tests
03:15 Test generation
05:41 Test sets
06:15 Executing test sets
06:40 Test runs & detailed test results
10:35 Aggregated test results
11:01 Tasks overview and creation
11:27 Metrics (directory)
12:35 Models and connectors
13:14 API tokens
Rhesis AI works with your existing stack - from simple chatbots to agent architectures. Open source, MIT licensed, built for teams who want testing as sophisticated as their development process.
Get started:
⭐ GitHub: www.github.com/rhesis-ai/rhesis
📖 Docs: docs.rhesis.ai
💬 Discord: discord.rhesis.ai
Top comments (0)