CommunityHire an ExpertSign Up
ActionsAsk AI
Actions

Ask AI

Let users ask an in-app AI chat assistant about your data

Overview

Ask AI is Softr’s built-in chat assistant that acts like a real-time analyst, reading your live app data and answering questions instantly. Unlike other AI tools that give vague answers or require complex setup, Ask AI is embedded directly into your Softr apps with no API keys. All you need to do is toggle it on!

Here are some key features:

🔍 Reads from your app data

  • Pulls from live data inside dynamic blocks in your Softr apps
  • Gives real-time answers based on your current data

🛡️ Secure by default

  • Respects your app’s permissions and visibility rules
  • Users only see data they’re authorized to access (no accidental data exposure)

⚡ No setup required

  • Built directly into your Softr application—just toggle it on at the block level
  • No API keys or complex configurations needed

How to Add Ask AI to Your App

Step 1: In the Softr Studio, navigate to your dynamic block’s Actions section

Notion image

Step 2: Select Add Topbar button and choose Ask AI from the options.

Notion image

Step 3: From here, you can adjust the label and icon, and use the dropdown to customize messages, instructions, response style, suggested prompts, and appearance.

Notion image

Step 4: Publish your app. The chat interface will now be available to your users (depending on block permissions)

Notion image

Notion image

Security & Permissions

Ask AI only analyzes the data a user is allowed to see at the block level, always respecting your app’s permissions and visibility settings.

You can decide who sees the Ask AI button—like showing it to managers but hiding it from clients. And when users ask questions, Ask AI only analyzes the data they’re allowed to see, including filtered views (like “tasks assigned to me”).

Requirements & Limitations

✅ Supported

  • Dynamic blocks (e.g. Tables, Lists), and Vibe coding block connected to any of Softr’s supported data sources (except REST API)

❌ Not Supported

  • Static blocks or blocks connected to REST API data sources
  • Ask AI is currently only available at the block level to ensure secure, permissioned responses.
  • App-wide Ask AI implementation is coming soon!

AI Credits

Ask AI is available on all plans, including free. Every query directed to Ask AI consumes AI credits based on the complexity of the response and the amount of data analyzed. Each query counts toward your workspace’s total monthly credit usage.

FAQ

Can I use Ask AI on the free plan?

Yes. Every Softr plan (including Free) comes with a set amount of monthly AI credits to use toward Ask AI and other AI features. If you run out of AI credits in a given month, your Ask AI will pause until your credits reset with your plan or you purchase a credit add-on. Learn more about AI credits.

Use these docs with your AI tools

An AI agent can read this documentation directly. You do not need an account or an API key. Everything here is public and read-only.

Query these docs via MCP

Recommended

Add this server to Claude, Claude Code, Cursor, Mistral, or any tool that supports MCP. Your agent can then search Softr Documentation documentation and read it in full, instead of answering from memory.

https://docs.softr.io/mcp
  • searchFind the passages that answer a question.
  • fetchRead one page in full, as Markdown.
  • list_pagesSee every page in this documentation.

Query these docs over HTTP

The same tools also work as plain web requests. Use this for scripts, or for any tool that does not support MCP. There is one endpoint per tool. Arguments go in the query string, and the answer comes back as JSON.

https://docs.softr.io/api/docs/search?query=custom+domain

Read the OpenAPI description. It is built from the same definitions as the tools, so it always matches what the endpoints do.

Read these docs as Markdown

Add .md to any page URL to get its Markdown source. You can also send the headerAccept: text/markdown to the page URL itself.

To read the whole documentation in one file, open llms-full.txt. For a short index of every page, open llms.txt.