PullString Platform Documentation

The PullString Platform was designed to let non-technical teams craft rich two-way conversational experiences, or bots. The resources here will let you learn more about what PullString can do for you and how you can use it to make your own chatbots and agents.

Guides    User Forums

Key Features

Here's an overview of some of the main features of PullString Author:

Content Authoring

  • Visual authoring of hierarchical conversation with an easy-to-use UI
  • Ability to define context-specific intents and rules with complex conversation flow controls
  • Categories and Activities, which help organize and structure conversational content
  • Author Scripts to programmatically manipulate content using Python scripting
  • Autocomplete, Undo/Redo, Auto Save, and Cut/Copy/Paste/Clear/Move operations
  • Optional dialog approval flows, which tracks in-progress versus final content
  • Asset management system that can integrate images and other media into conversations
  • Unicode (6.2) support for responses, intents, and synonyms in different languages

AI Dialog Engine

  • AI Dialog engine with Natural Language Processing (NLP)
  • Intent authoring, which models the user's interaction with machine-learned improvements
  • Synonym authoring, which defines related concepts with automated suggestions
  • Built-in Intent Library with many useful intents and synonyms to get you off the ground quickly
  • Powerful Pattern Matching capabilities that enable precise rule matching
  • Fallbacks, which handle cases where no intents match a user's input
  • Conditions and Priorities, which provide the best in-context responses
  • Interjections, which change conversation flow with segues back to previous contexts
  • Conversation state and logic, which can be controlled through flags, counters, labels, and lists
  • External integration with arbitrary web services or JavaScript programs
  • Generalized input events and output behaviors for greater expressivity

Analytics & Machine Learning

  • Machine learning that helps improve and surface insights about your content
  • Chat analytics that let you mine statistics for your users' interactions
  • Heat map displays that let you see which content is used more often
  • Webhooks to let you track usage metrics such as DAU/MAU, retention, and engagement
  • Metrics that monitor the efficiency of your intents

Content Testing

  • Integrated chat debugger built directly into the authoring environment
  • Drag-and-drop functionality that lets you test content at any point in the conversation
  • Ability to jump to any written line and follow the conversational path
  • Content error checker that helps identify common mistakes in content
  • Ability to inspect and alter the conversation engine's internal state while debugging

Bot Hosting

Key Features

Suggested Edits are limited on API Reference Pages

You can only suggest edits to Markdown body content, but not to the API spec.