AI platform
AI accounts and shared defaults
AI accounts hold the model connection and shared defaults used by your AI features.
AI model catalogue
Website model records let Powerfront offer the AI models your accounts can use, with catalogue information to help selection.
AI model provider selection
Provider selection connects AI features to the model service that processes their requests.
OpenAI API connection options
OpenAI accounts can use Responses API or Chat Completions and pass incremental replies to AI features that support streaming.
Google AI Studio model connection
Google AI Studio connects supported Gemini models to your AI features.
AWS Bedrock model connection
AWS Bedrock connects supported Bedrock models to your AI features using the configured AWS region.
Cloudflare AI Gateway connection
Cloudflare AI Gateway routes supported model requests through a configured gateway connection.
Embedding models for knowledge search
Embedding options turn a knowledge search into numeric values for matching by meaning, separately from the chat model.
Knowledge Base connections for AI
A Knowledge Base function retrieves external information for an AI feature to use in its answers.
Algolia Search for AI knowledge
Connect an AI function to an Algolia index so it can search your existing knowledge when answering questions.
Saved responses as AI knowledge
Eligible saved responses can become searchable AI knowledge, with an exclusion choice for content you do not want the AI to use.
Knowledge sources behind AI citations
Name the information behind AI answers and inspect the supporting content attached to citations.
Shared AI service connections
Reuse website connections for external AI prompts, tracing, memory and tools across the features that need them.
External AI prompts and versions
Select a versioned external prompt for an AI feature, with caching and fallback instructions when retrieval fails.
AI execution tracing with Langfuse
Send optional AI execution traces to LangFuse to review model calls, tool activity and failures alongside INSIDE usage records.
Persistent AI memory connections
Give supported AI features persistent context for a visitor or operator through an external memory service.
MCP tool connections for AI
Discover tools from a connected MCP service and make selected operations available to an AI feature.
MCP service authentication
Configure the credentials a connected MCP service requires for tool discovery and execution.
Autopilot connections through A2A
Expose an enabled Autopilot feature to another agent through discovery, messages and tracked tasks.
ACP compatibility for AI agents
ACP compatibility lets an integration discover Autopilot or Ask AI agents and submit work using alternative request formats.
Personal information masking for AI
Privacy replaces detected personal information with temporary placeholders for selected AI requests and restores it in supported replies and tool inputs.
AI guardrail policy connections
Guardrails check selected AI inputs and outputs against an external content policy and apply the configured response to an intervention.
AI usage and estimated cost
AI usage records associate model tokens with features and conversations and estimate token cost where pricing is available.
AI platform execution limits
AI execution limits bound model and function work, while specific caches and compatibility fallbacks help selected operations continue.
Voice Autopilot connection setup
Voice Autopilot connects incoming telephone calls to a realtime AI voice agent with configured instructions, tools and human hand-off.
Voice Autopilot turn detection and interruptions
Voice turn detection and playback handling control when Voice Autopilot listens, responds, accepts interruptions and completes announcements.
Salesforce Models API connection
Salesforce Models API lets AI features generate text through a Salesforce connection using a configured application or operator identity.