Skip to main content

Quick start

Submit an evaluation task via email or API and start testing your AI agents.

Email submission (easiest)

Send an email to test your first evaluation:
What happens next:
  1. System creates an agent to solve the task
  2. AI automatically detects verification checkpoints
  3. Agent executes and pauses at checkpoint
  4. You receive email notification
  5. Reply “approve” to continue
  6. Get results email when complete
No API key needed - Just send an email!

Test modes explained

Choose the right mode for your evaluation:
You specify exact verification points.Use when:
  • You know exactly where verification should happen
  • Testing specific decision points
  • Task has well-defined stages
Example:
Agent runs autonomously without human oversight.Use when:
  • Speed benchmarking
  • Comparing with/without human
  • Low-risk tasks
Example:

Verification workflow

When using verification mode, here’s what to expect:
1

Checkpoint reached

Agent pauses execution and sends email notification
2

Review agent's work

Open chat or check email to see what agent plans to do
3

Respond

  • Type “approve” - Agent continues - Type “reject” - Agent stops - Type “hint: [guidance]” - Agent adjusts approach
4

Agent continues

After approval, agent proceeds to next step or completes task

Example: Complete flow

Here’s a complete example from start to finish:

1. Submit via email

2. Confirmation received

3. Checkpoint notification

4. You approve

Reply to email: approve

5. Second checkpoint

6. You approve again

Reply: approve

7. Completion notification


Where to track evaluations

Dashboard

Visual overview of all evaluations

Chat Interface

See full conversation and agent work

API Status

Programmatic status checks

Email Notifications

Receive updates via email

Tips for success

Write clear task descriptionsGood: “Calculate 15% commission on a $50,000 sale and send result via email to manager@company.comBad: “Do commission stuff”
Start with auto-detect modeLet AI determine checkpoints until you understand the system better.
Test simple tasks firstStart with calculations or research before complex multi-step workflows.
Use baseline mode for comparisonsRun same task with and without verification to measure impact.

Next steps

Task Preparation

Learn how to write effective evaluation tasks

Examples

See 10+ ready-to-use example tasks

API Reference

Complete API documentation

Best Practices

Tips for getting the most from evaluations

Common questions

No! Email submissions don’t require an API key. Just send to agent@mixus.com with subject starting “Eval:”
Depends on task complexity and verification time. Simple tasks: 2-5 minutes. Complex tasks: 10-30 minutes.
Yes! Via API you can submit multiple tasks. They’ll run in parallel.
The evaluation will wait for your response. You can respond anytime via email or chat.
Yes, reply “reject” at any checkpoint or stop it from the dashboard.

Need help?