Connector · AI models

Anthropic, in every client’s workflows.

Ask Claude, with the client’s own Anthropic account.

Do it in Anthropic

A step with its own fields: values from the run go in by name, and what Anthropic answers is there for the next step.

Ask ClaudeOne prompt, one reply: the output’s Reply, the text block wherever it lands (after a thinking block when there is one).

On the client’s page in Thrum: Add credential, type Anthropic API key.

platform.claude.com → Settings → API keys → Create key, in the workspace that bills this client.

The key is stored encrypted and bound to that client: another client’s workflow cannot use it, and no template or pack copies it.

When Anthropic stops answering or refuses the client’s key, you hear about it, and your client does not.

A failing request: Tried 3 times, 5 seconds apart and doubling, only for errors a retry can fix
A service that asks for a pause: Given it, up to an hour
Requests at once, per account: 2, per worker; the rest wait their turn
Timeout: 15 seconds, unless the step sets its own
Private and internal addresses: Refused, on every redirect too
The client’s key: Encrypted, bound to the client, and kept out of every run record
A step that keeps failing: Marks the workflow Degraded and alerts you, not the client

Anthropic and its logo are trademarks of their owner, used here only to say what Thrum works with; no endorsement is implied.

Get early access and you’ll be among the first in. Early members get a launch perk.