AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
TypeScript ai-agentai-agent-toolsai-agentsai-agents-frameworkmcpmcp-servermcp-toolsmcpsn8n-alternativeno-code-automationworkflowworkflow-automationworkflows
icon: 🧪
Testing AI Usage Locally
How to see AI calls go to Autumn and land in the usage tables on a dev box. The copy job only runs in Cloud and Enterprise, and only for platforms with Autumn credentials.
- Run with
AP_EDITION=eeandnpm run dev. - If your dev database ran an older version of migration
AddAiUsageTables1878000000000, dropai_usage_ingest_cursor,ai_usage_5mandai_usage_daily, delete that row frommigrations, and restart so the current version runs. - In the Autumn sandbox:
- create a customer with an ID. One created without an ID shows
PENDINGand can't be used; - attach the Free plan;
- create a secret key (
am_sk_test_…) under Developer → API Keys; - check that the credits feature id is
apCredits.
- create a customer with an ID. One created without an ID shows
- On your platform:
UPDATE "platform_plan" SET "autumnCustomerId" = '<id>', "autumnApiKey" = 'am_sk_test_…', "aiProvidersEnabled" = true WHERE "platformId" = '<platform id>'; - Wait for one
aiUsageCopylog line: the first run only creates the cursor. Then make calls: a chat message, a test step, a published run, and one call on your own key. - In Autumn each call is an event with
properties.usage(v1). Own-key calls in a chat turn showsource: ai_usageand value 0. Events withoutusage, such asflow_run, are skipped. - After about 3 minutes (2-minute delay + the one-minute job), check
ai_usage_5m,ai_usage_daily,ai_usage_copy_cursorandai_usage_run. A row is a total per 5-minute slot or day per series, so comparesum("calls")with the number of events, not the row count.