Tools¶

Configure tools that extend your agents' capabilities — from knowledge retrieval and CRM integrations to human handoff and custom API calls.

Overview¶

Tools are actions and integrations that agents can invoke during conversations. They allow your agent to go beyond simple text responses — retrieving documents, calling external APIs, handing off to human agents, creating CRM leads, and more.

Tools are configured at the workspace level under Settings > Processors > Tools, then assigned to individual agents under the agent's Tools & Artifacts module.

Available Tool Types¶

Click Create Tool, search for a type, and select it. Complete the form and review Advanced parameters before saving.

Core Tools¶

Playbook¶

Playbook (previously called Static Text) stores a verbatim block of text that the agent can fetch on demand. No vectors, no chunking — the configured body is returned as-is.

Why use it over a Knowledge Base:

• Verbatim return — no retrieval, no embedding, no chunking, and nothing lost to a similarity threshold
• Keeps the system prompt lean — large instruction sets stay out of the system prompt
• No repository overhead — nothing to ingest, vectorise or re-index when the text changes. Edit the tool and the next call returns the new body

How to configure:

1. Navigate to Settings → Processors → Tools → Create Tool and select Playbook
2. Give the tool a Name and a tool-selection Description that tells the LLM when to fetch it
3. Paste the static text body and save
4. Add the tool to any agent that needs it

End Twilio Call¶

The platform holds the Twilio Call SID internally and can end a live voice call from the agent side. Attach this built-in tool to a voice agent — when the agent invokes it, the active call is ended.

Context¶

The Context tool provides the agent with background information to work with. There are two primary types:

Static Context — fixed information that does not change:

Dynamic Context — obtained from the webpage the agent is operating on (Floating Widget/Sidebar only):

• Enable "Use Dynamic Context from the Webpage for Floating Widget/Sidebar Agent"
• Configure the Get Contents Code — a JavaScript snippet that extracts content from the page
• Default: return document.body.innerText; (uses all page content)

Retrieval¶

The Retrieval tool performs vector search against a knowledge repository to find and return the most relevant document chunks for each user query. This is the core tool for RAG (Retrieval-Augmented Generation) workflows.

Chat with User Selected Documents¶

Enables end users to select specific documents from search results within a Search Type agent and initiate a focused chat conversation using only those documents as context.

Setup requires two agents:

1. Search Agent — enable "Enable Chat with Selected Documents" in Behavior settings and designate a Chat Type agent
2. Chat Type Agent — must be configured with the "Chat with User Selected Documents" tool, which inherits the parent Search Agent's knowledge repository

End-user flow:

1. User searches in Non-AI mode and selects up to 10 documents
2. Clicks "Start Chat" to open a new chat session with those documents as context — opens in the same browser tab (browser back button returns to the Search Agent view). Works consistently across Chrome, Firefox, Edge and Safari
3. Can toggle between Full Documents and Relevant Chunks modes
4. A real-time capacity visualization bar tracks token usage
5. System automatically falls back to Retrieval Mode if documents exceed 100% context capacity

Human Agent¶

Hands off the conversation from the AI to a human agent. Includes queue management, timeout configuration, and end-of-session rating.

Key configuration fields:

Agent to Agent¶

Communicate with another agent using API calls. Useful for specialized workflows where different agents handle different types of tasks. Cyclic loops are automatically prevented.

User Memory¶

Persists user-specific information across all conversations for a specific user. The agent can store and recall facts about the user (preferences, past interactions, account details) between sessions.

Tool Configuration Fields¶

User Memory tool configuration with the Merge Instructions field — rule-based merge logic (conflict_resolution, deduplication, …) is editable at the tool level; click Default to restore the built-in rules

Context Memory¶

Stores and retrieves contextual data with smart merging logic. Supports multiple persistence scopes:

Advanced configuration:

Integration Tools¶

Custom¶

A generic tool that executes a custom JavaScript function to perform any logic — calculations, data transformations, API calls, or custom business rules.

Example — validating calculation inputs:

Schema properties: operation, left, right. This JavaScript illustrates input validation and arithmetic; adapt the result handling to the Custom tool runtime before use.

function calculate(operation, left, right) {
  if (typeof left !== "number" || typeof right !== "number" ||
      !Number.isFinite(left) || !Number.isFinite(right)) {
    throw new Error("left and right must be finite numbers");
  }
  switch (operation) {
    case "add": return left + right;
    case "subtract": return left - right;
    case "multiply": return left * right;
    case "divide":
      if (right === 0) throw new Error("Cannot divide by zero");
      return left / right;
    default: throw new Error("Unsupported operation");
  }
}
const result = calculate(schema.operation, schema.left, schema.right);

Webhook¶

An HTTP tool for calling external APIs. The API must respond within 10 seconds.

Available placeholders in URL, Body, and Headers:

Body Format — JSON or Multipart form-data¶

In Multipart form-data mode, set a key's value to {{data.chatTranscriptPdf}} to attach the conversation transcript as a PDF file part under that key.

The PDF placeholder can sit alongside the existing ones in the same body — for example the PDF attachment plus the markdown transcript and an LLM-set schema property.

Additional Parameters:

Multi-Step Custom¶

A specialized tool that executes a series of steps in order — like a purchase journey or multi-stage workflow. Each step is a separate API call or action that can use outputs from previous steps.

Click "Add Step" to add more steps to the sequence. Each step executes in order, and outputs from earlier steps can be referenced by later ones.

Salesforce Operations¶

Use Salesforce Operations for record lookup and updates beyond lead creation. Configure Account Connection Mode, then choose Auto for AI-planned operations or Script for an admin-authored JavaScript function.

In Auto mode, Access Level defaults to Read only. Confirm Before Writes is enabled by default; the form describes a preview and confirmation before create, update or delete. Objects the Tool Can Use starts with Account, Contact, Lead, Opportunity, Task and Event. Removing all object restrictions allows all objects, so keep an explicit list when you need a limited scope.

Fetch Documents by ID¶

This tool retrieves documents referenced by ID or title in the conversation. Configure Document Selection Model, Query Schema Prompt, optional response instructions and Context Token Limit (the form documents a 2048-token default). Use User Input as Query to Query the Knowledge Base controls use of the user's query.

Salesforce Create Lead¶

Tool for interacting with Salesforce APIs, focusing on lead management. Creates leads directly in Salesforce from conversation data.

Hubspot Create Lead¶

Tool for interacting with HubSpot APIs, focusing on lead management. Works identically to the Salesforce tool but maps to HubSpot's API structure.

Account Connection Mode — Global vs User¶

Both Salesforce and HubSpot lead creation tools support a per-tool Account Connection Mode, letting admins choose how authentication is handled:

Salesforce Create Lead tool with Account Connection Mode set to Global — the connection is shared across users once configured. The blank form shown is disconnected. Helper text below the toggle summarizes both modes

Salesforce in User mode — no shared admin credentials. An Instance URL field is required so each user's credentials resolve to the correct Salesforce org (e.g., mycompany.my.salesforce.com)

HubSpot in User mode — no Instance URL required; the form goes straight from the mode toggle to the Schema

User Mode — End-User Connection Persistence

Users can review their saved connections under Account menu > Account > Connected applications. Each application card shows its status, tool/account details, an instance address when applicable, and a Disconnect action. A card can show Reconnect required when its connection needs attention.

Connected application cards with profile, account and instance details blurred.

Calendly¶

Tool for scheduling meetings directly within agent conversations. When invoked, the agent displays a Calendly scheduling interface (inline or popup) to the user.

Additional Parameters:

Data Visualization¶

A built-in tool type that renders interactive HTML visualizations directly in the chat. When invoked, the LLM authors a complete HTML document for the requested visualization (charts, diagrams, dashboards) and it renders inline in the chat inside a sandboxed iframe — supporting Tailwind CSS and external visualization libraries (Chart.js, Mermaid, D3, Plotly) loaded via CDN.

The in-product tool description reads: "Renders an interactive HTML visualization in the chat. Provide a description and data — the tool generates the HTML automatically using available libraries (Chart.js, Mermaid, D3, Plotly, etc.)."

Settings → Processors → Tools → Create Tool — Data Visualization appears in the Add Tool list alongside User Memory, Context Memory, Agent to Agent, and other built-in types

Data Visualization configuration — instructions, output-token limit, temperature and Brand Logo upload.

Inline bar chart using invented documentation data: Group A = 12, Group B = 18 and Group C = 9 sample units.

Check generated charts against the supplied values, labels and source. The model may introduce unsupported descriptions or attributions; correct them before sharing the visualization.

Key Capabilities¶

• Built-in tool type — Data Visualization appears as a new entry in the Add Tool list alongside Agent to Agent, User Memory, Context Memory, Human Agent, Salesforce / HubSpot Create Lead, etc.
• Sandboxed rendering — Generated HTML renders inside an iframe in the chat, free to use external CDN libraries and Tailwind CSS without affecting the host page.
• Author-controlled defaults — Visualization Instructions are appended to the system prompt for the generation call, so admins can lock in brand colors, chart defaults, and styling preferences without re-stating them on every query.

Configuration Fields¶

How to Configure & Use¶

1. Create the tool — Navigate to Settings > Processors > Tools > Create Tool and select Data Visualization from the Add Tool list.
2. Configure parameters — Fill in Tool Name, Description, optional Visualization Instructions, and tune Max Output Tokens / Temperature if needed, then Save.
3. Add to an agent — Open the target agent's Tools & Artifacts section → Add, search for the tool by name, and select it from the picker.
4. Generate visualizations — The agent now renders visualizations inline in chat based on the user's prompt — e.g., a product pricing analysis card showing per-product original price, discount, final price and status, with totals.

Available Libraries¶

Brand Logo on AI-Generated Visualizations¶

Upload a Brand Logo in the Data Visualization tool form. The form recommends a single PNG/WebP with transparency or an SVG for sharp scaling, with top-right placement by default.

Use Visualization Instructions to specify placement, size and styling; these instructions take precedence over the built-in defaults. Configure the logo on the workspace tool or the agent's tool configuration as appropriate. Workspace tool changes do not automatically update existing agent copies.

Rules for AI-Generated Visualizations¶

• Use only Tailwind CSS classes for styling (loaded automatically)
• Only request libraries actually used
• Write clean, self-contained HTML with inline <script> tags
• Content renders inside an iframe — no external navigation or form submissions
• Keep visualizations responsive and accessible

Assigning Tools to Agents¶

1. Navigate to the agent's Tools & Artifacts module
2. Click "Add Tool"
3. Select a configured tool from the list
4. Configure tool-specific settings for this agent
5. Click "Save"

Related Topics¶

• Pre-Processors — Process user input before the agent responds
• Post-Processors — Process conversations after responses
• Agent Builder — Advanced Configuration — Assign tools to agents
• Knowledge Overview — Set up knowledge repositories for Context and Retrieval tools
• Back to Settings