poly-adk-testing
Installation
SKILL.md
Testing a PolyAI Agent
Load poly-adk-workflow first for the overall build loop these commands fit into.
Four layers of verification, catching different problems:
| Command | Catches | Runs against |
|---|---|---|
poly validate |
Invalid resources, missing values, broken references | Local files |
poly chat |
Conversational behavior, judged by reading | Last pushed state |
poly test run |
Regressions, repeatably | Last pushed state |
poly conversations |
What happened on real calls (see poly-adk-conversations) |
Live traffic |
poly chat and poly test run run against the last pushed state, not local files. Push first, or pass --push to push-and-run in one step. Both target the current branch by default; -e sandbox|pre-release|live targets a deployed environment instead.
1. Validate while editing
poly validate checks local files without contacting the platform — malformed resources, missing required values, and {{prefix:name}} references that don't resolve. Run it as you edit, not just before pushing; poly push runs the same validation and rejects anything validate rejects.