For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Login
HomeDocsAPI ReferenceMCP ServerChat SDKsRelease Notes
HomeDocsAPI ReferenceMCP ServerChat SDKsRelease Notes
  • Introduction
    • Overview
    • Getting started
    • Authentication
    • Data privacy
    • Built-in prompts
    • FAQ
    • Troubleshooting
  • Tools
    • Overview
    • get_ada_configuration
    • get_ada_metric
    • get_available_filters
    • get_conversations
    • get_conversation
    • search_knowledge
    • search_coaching
    • get_improvement_guide
    • list_entities
    • propose_change
    • get_test_cases
    • get_test_runs
    • get_test_run_quota
    • send_feedback
  • Prompt library
    • Overview
    • Improvement recommendations
    • Quick health checks
    • Create visualizations
    • Diagnose performance issues
    • Identify optimization opportunities
    • Review configuration
    • Search knowledge and coaching
    • Test agent responses
    • Deep-dive analysis
Login
LogoLogo
On this page
  • Disable model training
  • Disable individual tools
  • What data flows through MCP
Introduction

Data privacy

Was this page helpful?
Previous

Built-in prompts

Next
Built with

Some MCP tools—such as get_conversation—retrieve conversation transcripts that may contain personally identifiable information (PII). Before connecting Ada to an AI assistant, disable model training on your chat data so that customer information is not used to train AI models.

Disable model training

  • ChatGPT: Go to Settings → Data Controls → disable “Improve the model for everyone”.
  • Claude: Go to Settings → Privacy → disable “Allow training”.

If you use a company or enterprise subscription for ChatGPT or Claude, model training is typically disabled by default. Verify this with your IT administrator.

Disable individual tools

If you prefer not to share conversation transcripts with your AI assistant, Claude Desktop allows you to disable individual tools like get_conversation after connecting—you can still get value from the other available tools. ChatGPT does not currently support disabling individual tools.

What data flows through MCP

Depending on which tools you use, the following may be transmitted to your chosen MCP client (for example, Claude or ChatGPT):

  • Conversation transcripts
  • Reasoning history
  • Customer inquiry summaries
  • Automated resolution status and reasons
  • CSAT scores and feedback
  • Knowledge article content
  • Coaching content
  • Agent configuration (playbooks, actions, custom instructions)