Skip to main content
Every AI Agent gambit can use a set of native capabilities. You do not connect a toolkit or write a custom action to use them. Each capability is a component on a Component gambit, and an agent gets it by linking to that gambit. One agent can read files while another cannot.

​
Where capabilities are managed

Select an AI Agent gambit in the builder, then select Manage tools in the Tools & Capabilities region of its editor. A popover opens with two tabs.
  • Connect tools lists the tool gambits, Component gambits, and Knowledge Retrieval gambits already on the builder. Selecting one links it to this agent, the same as drawing an edge to its tool handle.
  • Add tools creates a new gambit next to this agent, already linked. Pick Component under Built-in Tools for native capabilities.
Linked gambits appear as badges in the gambit editor. Which components each Component gambit offers is set on that gambit. See Component gambit.

​
Actions

Actions run on their own and return a result, with nothing for the end user to answer. Web Search is not available. It is listed under Actions as Coming soon and cannot be added. An agent that had Web Search turned on shows a Web Search badge marked Coming soon. That agent cannot search the web. Remove the badge under Built-in tools in Manage tools.

​
File Reader

An agent can read uploads when it is linked to a Component gambit that includes File Reader. With at least one upload in the conversation, the agent gains two tools, read_document and get_document_index.

​
What the agent can read

Documents are converted to text before the agent sees them. Supported formats are PDF, Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and plain text such as TXT, Markdown, JSON, XML, and YAML. An image is indexed as a description of what it shows plus any legible text in it. A scanned PDF with no text layer is transcribed the same way, and video and audio files are not read. Uploads reach the agent the same way from every entry point. The entry points are the Attach files button in the composer, a file upload input component, and a Media Upload gambit earlier in the flow. A document or image sent on WhatsApp is read the same way.

​
How a read works

The agent never receives a whole file. Each turn, its prompt lists every uploaded file with a status, a line count, and up to eight labelled sections. The agent reads only the sections it needs, up to 8,000 characters per call, and continues from a cursor when a read is cut short. For a file with more sections, get_document_index returns the full list. Two uploads with the same name are told apart by a number. A second photo.jpg is listed as photo (2).jpg, so a read always lands on the intended file. When Show tool calls to visitors is on, each read appears in the chat like any other tool call.

​
Status and limits

A file is listed as still being read, ready, could not be read, or unsupported. A read of a file that is still being read waits up to 20 seconds. After that, the agent is told the file is still being read and to ask the end user for a moment.

​
Interface components

Interactions show a card and wait for the end user, such as a form, a date picker, or a booking card. Display components show a card the end user only reads, such as a table, a chart, or a timeline. Both come from a Component gambit, like the actions. See Component gambit for the full list.

​
Legacy capabilities

Before they became components, these capabilities were switches on the AI Agent gambit itself. An agent that still has one turned on shows it as a badge, with the tooltip Now a component. Manage it under Legacy capabilities in Manage tools. A legacy capability keeps working. Open Manage tools on the AI Agent gambit to find it under Legacy capabilities. The legacy Output components (render_ui) and Input components (request_user_input) have a Migrate to components button. It opens Migrate to components?. Select Migrate to move the selected components to a Component gambit linked to the agent. The legacy tools then turn off, and a toast confirms Migrated to components. When a component cannot move, the toast names it after Not migrated. Migrate to components is disabled while the agent has unsaved changes. Save your changes first. An agent that is live on WhatsApp cannot migrate, because components do not show there. Keep the legacy tools on that agent. To move one capability by hand instead, turn the legacy capability off, then add the matching component to a Component gambit linked to the agent.

​
Knowledge citations

When an agent answers from an attached knowledge base, the sources behind the answer can be shown to end users as citations. See Attach knowledge to an agent for how knowledge reaches the agent.

​
What end users see

Visibility of all this activity is controlled per agent, under Debug in the Settings list on the Configure page, not in the builder. Hiding activity changes only the presentation, not the agent’s behavior. For the three switches and their defaults, see Test your agent. For what reasoning, tool calls, and citations look like in the chat, see End-user experience.