FactoryWhy?
Loop template

Every source gets a closer look

Process entries individually so useful details survive the summary.

By 0design
Use with your agent

One prompt. In your own project.

The workflow

2 stepsWorkflow overview
100%
1
2

From the loop’s versioned definition. Select a step to inspect it.

What you get

Process entries individually so useful details survive the summary.

Use the template as a starting point. Your agent adapts it to your sources and checks the result in your project.

Before you start

Choose the source material, task and output destination you want to use.

You will need access to the services used by this workflow. Configure credentials locally with your agent.

See how you could use it

Illustrative cases to adapt to your own work.

Turn a reading list into context

Give each source a careful read, then build a referenced research note.

Explore the case →

Building blocks

llm-call/openrouter

Explore component →

Inside the loop

Workflow and configuration
2 stepsWorkflow overview
100%
1
2

Local configuration

  • OPENROUTER_API_KEY
  • QLOOP_SOURCE_URL
  • QLOOP_WEBHOOK_URL
  • OPENROUTER_MODEL

Start this workflow from your local agent.

Version, source and run evidence

Version 1.1.0 · MIT

Historical record · not reverified. Release acceptance: pending.

Explorative modeling: Train on the best of K guesses is a blog post that would be of interest to data scientists and machine learning practitioners who are interested in exploring novel model training approaches.
Download manifest

Engine: qloops 0.2.0-core.13