Get Started
CLI Usage
Every adapter has a CLI entry point. Pass a scenario and ARIA runs the conversation, scores it, and writes a report — no dashboard required.
Commands
Each command targets a different agent platform:
| Command | Targets |
|---|---|
npm run cli:connect | Amazon Connect (chat / voice) |
npm run cli:lex | AWS Lex V2 |
npm run cli:azure | Azure Direct Line |
npm run cli:azure-openai | Azure OpenAI Agents Runtime |
npm run cli:strands | Strands / AgentCore HTTP |
npm run cli:copilot | GitHub Copilot Chat |
npm run cli:openapi | Any OpenAPI 3.x HTTP endpoint |
npm run cli:custom | Generic HTTP / WebSocket endpoint |
Running a scenario
Pass arguments after -- so npm forwards them to the CLI:
npm run cli:openapi -- --scenarios-dir=./scenarios --scenario=banking/functional/account_queryEach judge call prints its token usage as [Xin/Yout] in the terminal, and the run writes a paired HTML + JSON report when it finishes.
Common flags
| Flag | Description |
|---|---|
--scenario, -s | Path-prefix filter for scenarios to run (relative to the scenarios dir), e.g. banking/functional/account_query. |
--scenarios-dir | Directory to load scenarios from. Use ./scenarios for the repo’s bundled packs. |
--channel, -c | chat (default) or voice. |
--transcript, -t | Re-evaluate a saved transcript JSON without re-running the conversation. |
--conversation-only / --no-eval | Run the conversation without invoking the judge. |
New to scenarios? See Scenarios for the YAML format.