--ai generates realistic data and creates it through the clone’s
REST API. For the conceptual difference, see Seeding.
Arguments
| Argument | Required | Description |
|---|---|---|
<id> | yes | The clone id, e.g. slack-a1b2. |
Options
| Option | Description |
|---|---|
-f, --fixture <name> | Named fixture pack (deterministic SQL), e.g. acme-corp. |
--ai | Generate AI data using the template’s defaults. Needs ANTHROPIC_API_KEY. |
--json | Output the seed result as JSON instead of the human summary. |
Nothing to seed. Pass --fixture <name> and/or --ai. and exits 1.
Examples
Deterministic fixture:!) are best-effort — rejected records don’t fail the seed.
Up to five are shown.
AI seeding details
- Model:
claude-haiku-4-5. - Auth: reads
ANTHROPIC_API_KEYfrom your environment. - Default brief: “a small, fast-moving software startup.”
- Default volume
medium: 6 users, 4 channels, 20 messages. See the volume table. - Data is created via real signup → workspace → channels → messages, so auth and referential integrity hold.
Seed on spin
To seed at create time instead, pass--seed to spin:
Reset replays it
The last seed is recorded on the clone and re-applied automatically byreset.
Errors you might see
| Error | Cause |
|---|---|
CLONE_NOT_FOUND | No clone with that id. |
LLM_UNAVAILABLE | AI seeding failed (model error, parse error, or missing API key). Retry. |
SEED_VALIDATION | Generated records were rejected by validation. |