AI & Models
The control surface for everything AI does in ThreadCloud. Parse, enrich, classify, describe — all of it routes through this configuration.
What lives here
Settings → AI & Models has four sections:
1. API key
The Anthropic API key. Stored encrypted, never echoed back in the UI after save.
To rotate:
- Get new key from console.anthropic.com
- Paste into the field
- Click Save
- Old key auto-revokes after 24h
2. Model selection
Which Claude model handles each workstream:
| Workstream | Default model | Why |
|---|---|---|
| Parse (Tier-1) | claude-haiku-4-5 | Fast, cheap, structured extraction |
| Enrich (Tier-2) | claude-haiku-4-5 | Same — accuracy-sensitive but bounded |
| Description | claude-sonnet-4-6 | Prose quality matters more than speed |
| Classify (Legacy Enrich) | claude-haiku-4-5 | Volume-sensitive, structured output |
Override per-workstream if needed. Generally don’t.
3. Brand voice + description rules
The editorial voice used for storefront descriptions:
- Brand voice — paragraph describing the tone (e.g. “Understated luxury. Inform, don’t sell. Lead with fabric and construction.”)
- Structure — what to lead with (fabric → construction → fit → COO → occasion)
- Avoid rules — words and phrases to never use (“elevate”, “timeless”, “effortless”, “perfect for any occasion”)
Changes apply to new descriptions and any re-generated descriptions. Existing descriptions stay as they were.
4. Prompt overrides (advanced)
Per-prompt overrides for specific extraction rules:
| Prompt key | What it controls |
|---|---|
description.style | Description structure rules |
description.cooFilter | Which countries get mentioned in description prose |
description.bulletPoints | Whether to use bullet points in descriptions |
extraction.fabricContent | Custom rules for fabric extraction |
extraction.occasionRule | Custom rules for occasion classification |
Edit at your own risk. Each override is a free-form prompt that gets injected at AI call time.
Sync controls
At the bottom of the page:
- Sync sell-through now — triggers an immediate Shopify Order Sync (otherwise runs every 6 hours)
- Reset AI cache — clears Anthropic prompt cache (rarely needed)
- Re-run enrichment on all draft orders — useful after changing brand voice
Common patterns
After changing brand voice
- Save new brand voice
- Click “Re-run enrichment on all draft orders” — this regenerates descriptions for any orders in DRAFT status
- Existing live products on Shopify need a per-order re-push to pick up the new voice
When AI is throwing 429s (rate limits)
Anthropic rate limit hit. Two options:
- Wait — limits reset every minute, and the retry logic handles it
- Upgrade the Anthropic plan if you’re constantly hitting the wall
Don’t switch to a smaller model — that’s a different fix and usually wrong.
Anthropic outage
If status.anthropic.com shows an incident:
- Don’t kick workers manually — they’re already retrying
- Don’t change the API key
- Don’t change the model
- Just wait
Common mistakes
Next steps
- Legacy Enrichment — bulk-classify the existing catalog
- Settings → Brands & Suppliers — brand-specific overrides