Nice Looking Reports

If I ask say Claude to run a report or create a chart of the data in say an airtable, it will create something nice.

If I do the same in Pickaxe, you just get text back.

Is there a way or an action that can make the output better ?

2 Likes

Hi,
Great question!

When you use Claude on their own platform, they have hidden system prompts and formatting instructions running behind the scenes that help produce more polished outputs like nicely formatted reports and charts. Unfortunately, these hidden prompts are not included when you access the model through API keys or third-party tools like Pickaxe.

However, you can still achieve similar results in Pickaxe. You can instruct your bot to generate responses in Markdown or HTML so you have more control over formatting and layout. You can also use the Chart Generator to create visual charts directly from your data. Additionally, the PDF Generator can help you build downloadable reports in a more structured format.

1 Like

Hey @ihmunro, long time. Hope you’re well!

Great question. What you’re noticing is a key difference in how most LLM-based tools (like ChatGPT/Claude) handle output versus how Pickaxe works when connected to external data like Airtable.

By default, Pickaxe returns text because the core LLMs themselves are text-in, text-out systems. However, Pickaxe is designed to go beyond this with Actions. Here’s the strategic angle:

  • Why Pickaxe returns “just text”: The LLM generates a response based on your prompt and training data. Unless explicitly told to format or visualize, it outputs plain text.
  • How to improve the output with Actions: Pickaxe’s Actions let you connect your tool to external services. While there isn’t a built-in “chart” or “report” visualizer for Airtable data out of the box, you can extend Pickaxe’s capabilities using Make (formerly Integromat), Zapier, or custom API-based Actions. For example:
    • Send data to a visualization service: Use an Action to send Airtable data to a tool like Google Sheets, Google Data Studio, or even a charting API (like QuickChart).
    • Return images or formatted tables: Configure your Action to process the data externally (e.g., generate a chart as an image URL) and then return that image or a nicely formatted table back into Pickaxe’s chat output.
    • Embedding outputs: You can also prompt Pickaxe to output in Markdown, which will render tables more cleanly inside chat, or to show links to externally generated charts.
  • Strategic advantage: The beauty of Pickaxe is in its flexibility. While you have to set up these integrations, you’re not boxed into a single vendor’s visualization system. This allows you to tailor your workflow—automate reporting, embed live dashboards, or format outputs exactly how you want.

Next steps:

  • Explore the Actions tab and consider integrating with Make.
  • Use an Action to move your Airtable data to a visualization platform, then return the result (image, table, or link) back to your Pickaxe.