Kognitos vs Prismatic

Kognitos

Kognitos has a self-serve free workspace, a public OpenAPI file and a hosted MCP server with OAuth 2.1 and scoped, expiring tokens. The 21 October AI Employees and Context Graphs are in preview for existing customers only, and their REST and MCP access isn't documented, so an outside agent can reach the automation platform but not the new parts.

Prismatic

The GraphQL API covers 120 queries and 124 mutations with typed inputs, cursor pagination and Markdown documentation, and tokens follow seven user roles. No price is published, paid use runs under an agreement that is not public, and no API rate limit or idempotency key was found in the reviewed documentation.

Kognitos

1. Don't plan on Context Graph or AI Employee calls. Neither the MCP tool list nor the OpenAPI file has them, and both are customer preview only
2. Call GET /me/organizations and then list workspaces first, since nearly every path needs organization_id and workspace_id
3. Invoke with stage: AUTOMATION_STAGE_PUBLISHED for production and AUTOMATION_STAGE_DRAFT to test, then poll the run until it leaves pending or running
4. Treat a waiting run as a question for a person. Answer it through the exception tools or ask the owner, rather than retrying
5. Use OAuth with callback port 3777 for the MCP server. Another port can fail with a callback URL mismatch

Prismatic

1. Have a person run prism login once, then store the output of prism me:token --type refresh as PRISM_REFRESH_TOKEN. Access tokens last 7 days
2. Read the errors array on every mutation. A failed mutation still returns HTTP 200
3. Pass sortBy with CREATED_AT when paging. Without a sort order pages can repeat or skip records
4. Use the regional host for the tenant, such as app.eu-west-1.prismatic.io and mcp.eu-west-1.prismatic.io
5. Create a guest user for a read-only agent, because tokens have no scopes of their own