Skip to main content
FTS integrates Anthropic Claude to accelerate knowledge capture and discovery. AI features are optional and can be disabled by workspace admins.

​
Available AI Features

​
Draft Cases from Notes

When you have rough notes or incident details scattered across emails, messages, or documents, use AI Draft to create a structured case:
  1. Paste or upload your notes
  2. Click Generate Case Draft
  3. Claude transforms notes into a case with:
    • A clear, professional title
    • Well-organized body with sections
    • Suggested tags
    • Recommended evidence types
  4. Review and edit the draft before saving
This saves hours of manual writing, especially for incident documentation.
The generated draft is a starting point. Always review and add your own insights before submitting for review.

​
Translate Cases

Need to share knowledge across multilingual teams? Use AI Translate:
  1. Open any published case
  2. Click Translate
  3. Select target language(s) (e.g., Spanish, German, Mandarin)
  4. Claude generates translations preserving technical terminology and structure
Translations appear as linked versions. Team members can switch between languages seamlessly.
Translations are reviewed by humans before publication. Admins assign translators to ensure quality.

​
Summarize Threads

If a case has extensive review comments or a long revision history, use Summarize to get the key points:
  1. Open the case’s Activity tab
  2. Click AI Summary
  3. Claude generates a concise summary of all feedback and changes
  4. Perfect for catching up before re-opening an old case

​
Answer Questions

Search can only find existing cases. Ask AI lets you ask questions and get answers grounded in your published knowledge:
  1. Click Ask AI in the dashboard
  2. Type your question in natural language (e.g., “What should we do if the hydraulic pump makes noise?”)
  3. Claude searches your published cases and provides an answer with citations
  4. Each cited case includes a link for full context
This feature is especially powerful for:
  • Troubleshooting on the production floor
  • Training new technicians
  • Quick reference during incidents
AI answers are based on your published cases only. If no cases address your question, AI will say so rather than guess.

​
How It Works Technically

All AI features use Anthropic Claude (the same model powering this documentation). Here’s what happens:
  1. Your query or content is sent to Anthropic’s servers
  2. Claude processes it and returns results
  3. Results are displayed in FTS
  4. Your data is not used to train or improve Claude
Each request is isolated—Claude doesn’t retain memory of previous interactions with your workspace.

​
Privacy & Data Security

No Training Data

Customer cases and queries are never used to train AI models.

Real-time Processing

Requests are processed immediately and not stored by Anthropic.

GDPR Compliant

Data handling meets EU data protection standards.

Admin Control

Admins can disable AI features for sensitive workspaces.

​
Enabling & Disabling AI

Workspace Admins can control AI availability:
  1. Go to Settings → AI Features
  2. Toggle each feature on/off independently:
    • Draft Cases
    • Translate Cases
    • Summarize Threads
    • Answer Questions
  3. Changes take effect immediately
If AI features are disabled, buttons won’t appear in the UI.
Disabling AI doesn’t delete existing translations or summaries—they remain accessible but can’t be regenerated.

​
Quality & Limitations

AI features work best when:
  • Case content is clear and well-written
  • Evidence is well-captioned
  • Tags accurately describe the case
  • Questions are specific and grounded in your knowledge base
AI has limitations:
  • Draft cases still require human review and editing
  • Translations need human review for specialized terminology
  • Summaries may miss nuances in long discussion threads
  • Answers can only cite published cases—they won’t extrapolate beyond your knowledge base
Admin-assigned translators review and correct translations before publication. AI is a starting point, not a final product.

​
Feedback & Improvement

If you find an AI-generated draft unhelpful or a translation inaccurate:
  1. Click Feedback on that feature
  2. Describe what could improve
  3. FTS logs your feedback (shared with Anthropic to improve future versions)
Your feedback helps refine these tools for everyone.

​
Best Practices

Don’t publish without careful review. AI can make mistakes.
“What’s best practice for motor maintenance?” works better than “Tell me about motors.”
AI translations are excellent for new-hire onboarding in multilingual teams.
The more clear, detailed cases you publish, the better AI answers become.

Search

Combine AI answers with semantic search for powerful discovery.

Cases

Improve case quality to unlock better AI assistance.