Execution Modes
Every agent run uses one of two execution modes: Standard or Advanced.
Standard mode
Standard is optimized for speed. It’s ideal for:
- Short Q&A conversations
- Simple lookups and retrievals
- Quick summaries
- Customer-facing chat where response time matters
- High-volume interactions
Responses are typically returned in a few seconds. Standard mode uses fewer credits per run.
Advanced mode
Advanced is optimized for depth and accuracy. It’s ideal for:
- Complex, multi-step tasks (“write a full test suite for this module”)
- Long-form research and synthesis
- Tasks that require planning and multiple tool calls
- Code generation, debugging, architecture review
- Anything where quality matters more than speed
The agent spends more time reasoning before and during the task. Advanced mode uses more credits but produces significantly better results for complex work.
How mode is selected
| Scenario | Mode used |
|---|---|
| Agent type is Customer-Facing | Always Standard |
| Agent type is Collaboration | Always Standard |
| Agent type is Internal + task is simple | Standard (auto-selected) |
| Agent type is Internal + task is complex | Advanced (auto-selected) |
| You set it manually in agent settings | Your override |
For Internal agents, Auteryn automatically classifies incoming tasks and selects the appropriate mode. You can override this in Agent → Settings → Execution Mode.
When to override
| I want… | Use |
|---|---|
| Fast, snappy responses for end users | Standard |
| The best possible answer for a hard problem | Advanced |
| Lower costs on a high-traffic agent | Standard (or set a credit limit) |
| A coding assistant that writes production-quality code | Advanced |