Tutorial
Set up a multi-step workflow in The Loom
Chain multiple steps into a durable workflow that runs in the background and can pause for human review. This is where LLMWeave goes past a single prompt.
Before you start
- An LLMWeave account
- Comfort running single weaves
Open The Loom
The Loom is where multi-step workflows live. A workflow strings several layers together, each of which can call one or more models.
Lay out your layers
Add layers for each stage of the task, for example draft, critique, then synthesize. Each layer can fan out across models and pass its result to the next.
Add a human-review pause if you need one
For anything high-stakes, add a human-review step. The workflow pauses durably, waits for your input, then resumes from exactly where it stopped.
Run it durably
Start the workflow. It runs in the background with each step checkpointed, so it survives interruptions and you can come back to the result. Cost is tracked per model across the whole run.
Keep going
Rank and fuse multiple model outputs
Generate several candidate answers, rank them, and fuse the best parts into one result. Useful when quality matters more than speed.
Intermediate · 4 minGround a weave in current sources with web search
Turn on web search so models answer from current sources rather than training memory. Essential for anything recent or fact-sensitive.