roles: entry map directly onto the corresponding Agent(...) kwargs when you run with framework: praisonai.
Quick Start
1
Simple — one flag on
Enable a single behaviour flag in
agents.yaml, then run it.2
All flags
Combine every behaviour flag on one agent.
3
From code
The same flags as
Agent(...) kwargs — identical behaviour, no YAML.Flag reference
Each key maps onto oneAgent(...) kwarg — follow the deep-dive link for the full option set.
How It Works
The CLI hands youragents.yaml to the adapter, which forwards each flag into the core Agent constructor.
Autonomy Levels in YAML
Theautonomy integer maps onto a core preset before it reaches Agent(autonomy=…).
bool / str preset / dict / AutonomyConfig values pass through unchanged, mirroring the Python API.
Best Practices
Start with autonomy: 3 and graduate up
Start with autonomy: 3 and graduate up
Begin at
autonomy: 3 (the suggest preset) so the agent proposes changes for your approval. Raise the level to auto_edit (4-7) or full_auto (8-10) once you trust its behaviour.Combine planning with reflection
Combine planning with reflection
Set
planning: true and reflection: true together for research-heavy tasks — the agent plans its steps, then self-reviews each result.Use guardrail names, not callables
Use guardrail names, not callables
guardrails: takes a list of registered guardrail names. YAML can’t express Python functions, so define callables in code and reference them by name here.Use the dict form for advanced autonomy
Use the dict form for advanced autonomy
For fine-grained tuning (iteration caps, doom-loop thresholds), use
autonomy: {...} dict form instead of the 0-10 int — the dict is passed through to AutonomyConfig unchanged.Related
YAML Configuration Reference — the full field table
Autonomy — deep dive into levels, doom-loop protection, and budgets