Babel
AI CORE FEATURES

Runners:
AI That Runs Every Time You Drop

Set up context and a prompt once. Drop new notes on it forever.

Pachinko Runners

① Select notes as context. ② Write a prompt for what the AI should do.
③ Create a runner from context + prompt. ④ Drop new notes onto it - runner fires automatically.

HOW RUNNERS WORK

Context + Prompt + Drop = Automatic

A runner is a section with a brain. You select notes as context - your stock portfolio, your brand guidelines, your research, whatever the AI needs to understand. Then you write a prompt: "for each new article, tell me which positions are affected." This creates a runner section. Now, every time you drag and drop a new note onto it - an article, a tweet, a YouTube transcript - the runner fires automatically. Your context and prompt run against the new note and you get results without lifting a finger.

  • step 1 Select notes as context (your portfolio, guidelines, research)
  • step 2 Write a prompt ("for each new article, tell me...")
  • step 3 This creates a runner section
  • step 4 Drop new notes onto it-articles, tweets, transcripts
  • step 5 The runner fires automatically every time you drop
  • the point Set it up once. Use it forever.

    • RUNNER SETTINGS

    Fine-Tune How Your Runner Processes Notes

    Runners have toggles that change how they process what you drop on them. These let you control whether the AI searches the web, processes notes individually or as a group, thinks harder, or cleans up after itself.

    Map vs Reduce

  • reduce (default) Processes all dropped notes together - good for finding connections
  • map Processes each dropped note individually - good for targeted analysis or batch processing
  • reduce example "What do these 5 articles agree on?"
  • map example "Summarize each article in one sentence"
  • the choice Together for connections. Individually for transformations.

    • Additional Toggles

  • web search AI searches the web during each drop for current data
  • extended thinking AI reasons more deeply before responding - slower but better for complex prompts
  • auto-delete Trashes the dropped note after processing to keep things tidy
  • combine them Web search + extended thinking + auto-delete = fully automated pipeline

    • GETTING GOOD RESULTS

    Refine Your Prompt, Catch Bad Outputs

    Your first prompt won't be your best prompt. The point is to watch what your runner produces and iterate. Hover over the runner icon in your runner section and an edit button appears - click it to refine the prompt. Drop a new note, see what comes back, adjust, repeat.

    AI gets things wrong. It hallucinates facts, misses obvious points, and sometimes ignores your instructions entirely. Since every runner output lands as a note in your workspace, you can read them like any other note - spot check a few, delete the ones that are wrong, and tighten your prompt if you see a pattern of bad output.

  • iterate the prompt Hover the runner icon → edit button → refine
  • spot check outputs Runner results are notes - review them like any other note
  • bad output pattern? Tighten the prompt, add examples, or add a reference that clarifies
  • try extended thinking For complex prompts, extended thinking often produces much better results

    • WHAT PEOPLE BUILD WITH RUNNERS

    Set Up Once, Use Forever

  • stock tracking Context: your portfolio. Prompt: "which positions are affected?" Drop: market articles.
  • design evolution Context: your portfolio. Prompt: "how should I evolve my style?" Drop: design trend articles.
  • competitive intel Context: your competitors. Prompt: "what are they missing that we could own?" Drop: industry news.
  • health tracking Context: your blood work. Prompt: "transform this into something healthier for me." Drop: recipes.
  • newsletter Context: your voice and style. Prompt: "write me a newsletter draft." Drop: batches of saved tweets.
  • job hunting Context: your resume. Prompt: "write a tailored cover letter." Drop: job postings.

    • SHARE YOUR RUNNERS

    Export, Import, Swap

    Built a runner that works? Export it and send it to someone. Got a friend's runner? Import it and run it on your own notes. Runners are portable - the context + prompt combo travels as a single file.

  • export Right-click the runner → Export Runner
  • import File → Import Runner...
  • what travels The prompt and the context notes, together
  • the point Good runners are worth sharing - and stealing
    • ← Back to Tutorials