ai
Add AI features to Glide apps using AI columns like Generate Text, Image to Text, Audio to Text. Use when adding AI-powered functionality, text generation, OCR, transcription, or auto-categorization.
What this skill does
# Glide AI
Glide has powerful AI columns that run inference on your data. These can add significant value to apps with minimal effort.
## AI Column Types
| Column | Input | Output | Use Case |
|--------|-------|--------|----------|
| **Generate Text** | Text/template | AI-generated text | Summaries, descriptions, recommendations |
| **Image to Text** | Image URL | Extracted text | Receipt scanning, document OCR, product analysis |
| **Document to Text** | Document URL | Extracted/summarized text | PDF parsing, document processing |
| **Audio to Text** | Audio URL | Transcription | Voice notes, meeting recordings |
| **Text to Boolean** | Text | true/false | Sentiment analysis, spam detection |
| **Text to Choice** | Text + options | Selected option | Auto-categorization, priority assignment |
| **Text to JSON** | Text | Structured JSON | Entity extraction, form parsing |
## AI Techniques
### Detail Screen Summary with Hint Component
A powerful pattern: show an AI-generated summary at the top of detail screens.
How it works:
1. **Aggregate data** - Create a Template column or JSON Object column that combines relevant fields
- Template: `Name: {Name}, Status: {Status}, Due: {Due Date}, Notes: {Notes}`
- Or use JSON Object to structure the data
2. **Generate summary** - Create a Generate Text column that takes the aggregated data
- Prompt: "Summarize this task in 1-2 sentences, highlighting priority and next steps"
3. **Display with Hint** - Add a Hint component at the top of the detail screen
- Bind it to the Generate Text column
- Users see an instant AI summary of the item
Example prompts:
- Task: "Summarize this task, noting urgency and blockers"
- Customer: "Provide a brief profile of this customer based on their activity"
- Order: "Summarize this order status and any issues"
- Project: "Give a quick health check of this project"
This gives users instant context without reading through all fields.
### Auto-Categorization with Text to Choice
Automatically categorize items as they're added:
1. Create a Text to Choice column
2. Define the categories (e.g., "Bug", "Feature", "Question", "Other")
3. Point it at the text field to analyze (e.g., ticket description)
4. New items get auto-categorized
Great for:
- Support tickets → category
- Feedback → sentiment (Positive, Negative, Neutral)
- Expenses → expense type
- Leads → qualification level
### Smart Descriptions from Basic Info
Generate rich descriptions from minimal input:
1. User enters basic info (name, a few keywords)
2. Template column combines the inputs
3. Generate Text creates a full description
Example for products:
- Input: "Blue widget, small, outdoor use"
- Generate Text prompt: "Write a compelling 2-sentence product description"
- Output: "Introducing our compact Blue Widget, perfectly sized for any outdoor adventure. Built to withstand the elements while delivering reliable performance wherever you go."
### Receipt/Document Scanning
Extract structured data from images:
1. User uploads a receipt photo
2. Image to Text extracts the content
3. Text to JSON parses into structured fields (vendor, amount, date)
4. Display parsed data in the UI
Works for:
- Receipts → expense tracking
- Business cards → contact creation
- Documents → data entry
- Product photos → inventory details
### Sentiment Analysis
Detect sentiment in text:
1. Create a Text to Boolean column
2. Prompt: "Is this feedback positive?"
3. Use result to show 😊 or 😞 emoji via If-Then-Else
4. Or use Text to Choice for Positive/Neutral/Negative
Apply to:
- Customer feedback
- Support ticket tone
- Review analysis
- Survey responses
## Best Practices
- **Aggregate before generating** - Combine relevant data into one input for better AI results
- **Be specific in prompts** - Tell the AI exactly what format and length you want
- **Use for summaries** - AI excels at condensing information
- **Cache results** - AI columns compute once and store the result
- **Consider cost** - AI columns use Glide AI credits; use strategically
## When to Add AI
Look for opportunities where:
- Users need to quickly understand complex data
- Manual categorization is tedious
- Text input could be richer/more helpful
- Images contain data that should be structured
- Summaries would save users time
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.