What can Kluff do with Replicate?
Explore models and run predictions through Replicate.
Explore models and run predictions through Replicate.
Connect for success
Explore what Replicate can do with Kluff.
Explore models and run predictions through Replicate.
The server can list available models and filter them by category.
It can retrieve model details, including its input schema and examples.
The server can create a prediction with a selected model and input parameters.
It can retrieve the status and results of a prediction by ID.
The server can list recent predictions and filter by status or date.
The server supports cancelling a running prediction.
Suggested tools to use alongside Replicate in Kluff.
Persist Replicate embedding model outputs in Pinecone when agents retrieve semantically similar content across large corpora.
Store Replicate inference metadata in Supabase tables so applications audit model versions alongside user-generated assets.
Call Replicate prediction APIs from Vercel edge functions when AI features need low-latency image or text generation.
Connect your tools, ask your first question in a project, and watch memory, spend, and visibility stay in one place—not scattered across personal chats.
$15 / user · Unlimited AI
@kluff build a launch dashboard from HubSpot and the Q4 budget sheet. Refresh it every morning.

Done. Signups come from HubSpot, spend from the Q4 budget sheet. It refreshes at 7:00 AM.
v2 adds the channel split you asked for.

Can we flag any channel over $40 per trial?

Added. Paid social is flagged.
It sends from your Gmail, as you, with the draft attached. Nothing else leaves the project.
Ana Chen confirmed net 45 at 9:18 AM. Your rule: every customer email waits for you.