Agent Capabilities

Extend your agent with tools, knowledge bases, and integrations

Capabilities give your agent the ability to do more than just chat. Connect tools to call APIs, knowledge bases to search documents, and integrations to interact with external systems.

The Capabilities Page

Open any agent and go to the Capabilities section. You’ll see:

• Added capabilities - Tools and knowledge already attached to this agent
• Add button - Opens the capability catalog
• Configure - Adjust settings for each capability

Types of Capabilities

Knowledge Bases

Connect document stores so your agent can search and retrieve information.

Type	Description
Knowledge Base	Search documents uploaded to Knowledges
File Search	Search files attached to conversations

When you add a knowledge base:

1. Click Add Capability
2. Select Knowledge category
3. Choose the knowledge base to connect
4. Save

Your agent can now search that knowledge base when answering questions.

After adding a knowledge base, update your Instructions to tell the agent when and how to use it.

Tools

Give your agent the ability to take actions and retrieve data.

Type	Description
API Tools	Call HTTP endpoints
MCP Servers	Connect to Model Context Protocol servers
System Tools	Built-in capabilities like web search
Skills	Pre-built tool bundles from the catalog

Common tools include:

• Web Search - Search the internet for current information
• Code Interpreter - Execute Python code for calculations
• Calendar - Check schedules and availability
• Email - Send and read emails

Why some tools need configuration: System tools like Web Search are pre-configured and work immediately. API tools and MCP servers connect to external services outside Prisme.ai - they need credentials (API keys, OAuth tokens) and endpoint URLs because your agent is calling systems that require authentication. The agent discovers available tools from descriptions you provide, then decides when to use each tool based on the user’s request.

Guardrails

Add safety controls to your agent:

• Input guardrails - Filter or modify user messages before processing
• Output guardrails - Check and filter agent responses before sending
• Action approval - Require confirmation for sensitive operations

Adding Capabilities

1. Click Add Capability in the Capabilities page
2. Browse or search the catalog
3. Select a capability
4. Configure required settings (if any)
5. Click Add

Some capabilities require configuration:

• Knowledge Base - Select which knowledge base to connect
• API Tool - Provide the endpoint URL and authentication
• MCP Server - Enter the server URL and any required headers

Configuring Capabilities

To change settings for an existing capability:

1. Find it in your capabilities list
2. Click the Configure button (gear icon)
3. Update the settings
4. Save

Common configuration options:

Setting	Description
Name	Display name for the tool
Description	What the tool does (helps the agent decide when to use it)
Parameters	Input fields the tool accepts
Authentication	API keys or tokens for external services

Removing Capabilities

To remove a capability:

1. Find it in your capabilities list
2. Click the Remove button (trash icon)
3. Confirm removal

Removing a capability may break your agent if the instructions reference it. Update your instructions after removing capabilities.

System Capabilities

Some capabilities are built-in based on your agent’s profile. These appear in a separate “Always On” section and cannot be removed.

Memory Types

Agents have access to different memory types depending on their profile:

Memory Type	Description	Available From
Working Memory	Information within the current conversation turn	All profiles
Session Memory	Information across the entire conversation	Light Agent+
Long-term Memory	Information persisted across conversations	Full Agent+

Working Memory is the immediate context — what the user just said and recent messages.

Session Memory lets the agent remember things you mentioned earlier in the conversation, even if it’s scrolled out of the context window.

Long-term Memory persists between sessions. If you tell the agent your preferences today, it can remember them next week.

To use long-term memory effectively, choose the Full Agent or Orchestrator profile. Simpler profiles won’t remember information between conversations.

System Tools by Profile

Depending on the agent profile, the following system tools are available:

Tool	Description	Available From
memory	Working memory (all profiles), session memory (workflow+), long-term memory (agent_full+)	All profiles
budget_get_remaining	Check remaining token/cost budget	All profiles
knowledge_search	Search the agent’s configured knowledge sources	All profiles (when knowledge configured)
todo_write	Create and manage task lists	Agent Light+
activate_skill	Activate a specialized skill for the current task	Agent Light+
planning_create_plan	Create step-by-step plans	Agent Full+
reflection_evaluate	Self-evaluate progress and quality	Agent Full+
human_request_approval	Request human approval for actions	Agent Full+
human_ask_clarification	Ask the user for clarification	Agent Full+
agent_delegate	Delegate subtasks to other agents	Orchestrator
agent_list_available	Discover available agents	Orchestrator

Planning and Reflection

Full Agents and Orchestrators have access to planning and reflection capabilities:

Planning: Before tackling a complex task, the agent creates a step-by-step plan. You’ll see this as a “Plan” block in the conversation. The agent then executes each step.

Reflection: After completing steps, the agent evaluates its progress. Did the step succeed? Is the output quality good? Should it adjust the approach?

These capabilities help agents handle complex, multi-step tasks more reliably. They’re not available in simpler profiles because they add overhead that isn’t needed for straightforward Q&A.

How agents think: Full Agents and Orchestrators use a reason-act cycle. They reason about what to do, take an action (like calling a tool), observe the result, then reason again about what to do next. This loop continues until the task is complete or the budget limit is reached. Simpler profiles respond in a single pass without this iterative reasoning, which makes them faster but less capable of handling multi-step problems.

Best Practices

Match capabilities to profile

Higher profiles support more capabilities. A Simple agent with many tools may not use them effectively.

Write clear descriptions

Tool descriptions help the agent decide when to use each capability. Be specific about what each tool does and when it’s appropriate.

Update instructions

After adding capabilities, edit your Instructions to tell the agent how to use them. Don’t assume it will figure it out.

Test incrementally

Add one capability at a time and test in the Playground before adding more. This makes it easier to identify issues.

Consider security

Tools that access external systems may expose data. Review what each tool can do before adding it to your agent.

Capability Catalog

The catalog contains pre-built capabilities organized by category:

Category	Examples
Knowledge	Knowledge bases, file search
Communication	Email, Slack, Teams
Data	Database queries, spreadsheet access
Productivity	Calendar, task management
Development	Code interpreter, GitHub
Search	Web search, internal search

Available capabilities depend on your organization’s configuration. Contact your admin to enable additional integrations.

Next Steps

Test in Playground

Try out your capabilities and see how the agent uses them

Create knowledge bases

Build document stores to connect to your agents