> ## Documentation Index
> Fetch the complete documentation index at: https://help.statisfy.com/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Agents Overview

> Build intelligent AI agents that can reason, use tools, and automate complex tasks

# AI Agents

AI Agents are intelligent assistants that go beyond simple automations. Powered by large language models, they can understand context, reason through problems, use tools to gather information, and take actions autonomously.

## What Makes Agents Different?

<Columns cols={2}>
  <Card title="Traditional Automations" icon="diagram-project">
    * Follow predefined paths
    * Execute fixed sequences
    * Rule-based decisions
    * Predictable outcomes
  </Card>

  <Card title="AI Agents" icon="robot">
    * Reason about tasks
    * Dynamic decision-making
    * Use tools intelligently
    * Adapt to context
  </Card>
</Columns>

## Agent Capabilities

### Contextual Understanding

Agents understand natural language instructions and can interpret ambiguous requests based on context:

```
"Prepare me for my call with Acme Corp tomorrow"
```

The agent will:

* Look up the Acme Corp account
* Review recent activities and conversations
* Check health scores and open tasks
* Summarize key points for the call

### Tool Usage

Agents can use tools to:

* **Fetch data** from Statisfy and integrated systems
* **Take actions** like sending emails or creating tasks
* **Search** through documents and knowledge bases
* **Calculate** metrics and analyze trends

### Multi-Step Reasoning

Agents break complex tasks into steps:

```
Task: "Find accounts at risk of churning and draft outreach emails"

Agent reasoning:
1. Query accounts with declining health scores
2. For each account:
   a. Analyze recent activity patterns
   b. Identify key risks
   c. Draft personalized outreach
3. Compile results
```

***

## Agent Configuration

When creating an agent, you configure:

### Instructions (System Prompt)

Define the agent's role, expertise, and behavior:

```
You are a customer success analyst specializing in account health.
Your role is to:
- Identify early warning signs of churn
- Provide actionable recommendations
- Communicate findings clearly and concisely

Always base your analysis on data, not assumptions.
```

### Model Selection

Choose the AI model that powers your agent:

| Model                | Characteristics                     | Best For         |
| -------------------- | ----------------------------------- | ---------------- |
| **Gemini Auto**      | Automatically selects based on task | General use      |
| **Gemini 3 Pro**     | Advanced reasoning, higher accuracy | Complex analysis |
| **Gemini 3 Flash**   | Fast responses                      | Simple tasks     |
| **Gemini 2.5 Flash** | Balanced speed and capability       | Most use cases   |

### Reasoning Level

Control how deeply the agent thinks:

| Level      | Description                            |
| ---------- | -------------------------------------- |
| **Auto**   | Model decides based on task complexity |
| **Low**    | Quick responses for simple tasks       |
| **Medium** | Balanced thinking for standard tasks   |
| **High**   | Deep reasoning for complex analysis    |

### Toolkits

Enable groups of tools the agent can use:

| Toolkit             | Tools Included                                              |
| ------------------- | ----------------------------------------------------------- |
| **Account Data**    | Get account details, health history, contacts               |
| **Activity Data**   | Fetch activities, meetings, emails                          |
| **Task Management** | Create tasks, add comments, update status                   |
| **Communication**   | Send emails, Slack messages                                 |
| **CRM**             | Salesforce operations, opportunity updates                  |
| **Data Analysis**   | Run Python code for counting, aggregation, and calculations |

### Scope

Define what data the agent can access:

| Scope       | Description                         |
| ----------- | ----------------------------------- |
| **Global**  | Access all organization data        |
| **Account** | Limited to specific account context |

***

## Creating an Agent

### Step 1: Define the Agent's Purpose

Start with a clear goal:

* What problems will this agent solve?
* Who will use it?
* What actions should it take?

### Step 2: Write Instructions

Craft detailed instructions that cover:

```markdown theme={null}
# Role
You are a [specific role] that helps [target users] with [main task].

# Capabilities
You can:
- [Capability 1]
- [Capability 2]
- [Capability 3]

# Guidelines
- [Guideline 1]
- [Guideline 2]

# Constraints
- Never [limitation 1]
- Always [requirement 1]
```

### Step 3: Select Tools

Enable only the tools the agent needs:

* More tools = more capability but slower responses
* Fewer tools = faster but more limited

### Step 4: Configure Model Settings

Choose based on your needs:

* Complex analysis → Higher reasoning, Pro model
* Quick answers → Lower reasoning, Flash model

### Step 5: Test Thoroughly

Test with various scenarios:

* Typical use cases
* Edge cases
* Unclear or ambiguous requests

***

## Prebuilt Agents

Every Statisfy workspace comes with **25 prebuilt agents** ready to use out of the box. These cover the most common customer success, sales, and account management tasks.

<Note>
  Prebuilt agents are fully customizable. You can modify their instructions, tools, and settings to match your team's workflow.
</Note>

### Account-Scoped Agents

These agents work in the context of a specific account:

| Agent                      | Description                                              |
| -------------------------- | -------------------------------------------------------- |
| **Account News Research**  | Researches recent news about an account using web search |
| **Account Next Best Step** | Recommends the optimal next action for an account        |
| **Account Plan**           | Generates a strategic account plan                       |
| **Account Support Review** | Summarizes recent support interactions                   |
| **Account Transition**     | Prepares handover documentation for account transfers    |
| **Account Weekly Update**  | Generates a weekly account status summary                |
| **Call Coaching Feedback** | Provides coaching feedback on recorded calls             |
| **Churn Analysis**         | Analyzes churn risk factors and suggests interventions   |
| **Customer Story**         | Drafts a customer success story with web research        |
| **Expansion / Upsell**     | Identifies expansion and upsell opportunities            |
| **Meeting Prep**           | Prepares briefing materials for upcoming meetings        |
| **Onboarding Blueprint**   | Creates a structured onboarding plan                     |
| **People News Research**   | Researches news about key contacts at an account         |
| **Product Usage**          | Analyzes product usage patterns and trends               |
| **QBR / EBR Deck**         | Prepares quarterly or executive business review content  |
| **Renewal Forecast**       | Forecasts renewal likelihood and risks                   |
| **Risk Mitigation**        | Creates a risk mitigation plan with web research         |
| **Stakeholder Mapping**    | Maps key stakeholders and their relationships            |
| **Value Delivery**         | Documents value delivered to the customer                |

### Global Agents

These agents work across your entire book of business:

| Agent                    | Description                                              |
| ------------------------ | -------------------------------------------------------- |
| **Competitive Insight**  | Researches competitors using web search                  |
| **Customer Advocate**    | Identifies top advocates for references and case studies |
| **Customer Lookalike**   | Finds accounts similar to your best customers            |
| **Feature Request**      | Aggregates and analyzes feature requests                 |
| **Weekly Priority**      | Generates a prioritized weekly task list                 |
| **Weekly User Coaching** | Provides coaching recommendations for team members       |

***

## Example Agents

### Account Health Analyst

**Purpose:** Analyze account health and provide recommendations

**Instructions:**

```
You are an account health analyst. When asked about an account:

1. Review health score history and trends
2. Analyze recent activities and engagement
3. Identify risk factors and warning signs
4. Provide specific, actionable recommendations

Always explain your reasoning and cite specific data points.
```

**Tools:** Account Data, Activity Data

***

### QBR Preparation Assistant

**Purpose:** Prepare materials for quarterly business reviews

**Instructions:**

```
You prepare comprehensive QBR materials by:

1. Summarizing key metrics and changes
2. Highlighting achievements and successes
3. Identifying challenges and proposed solutions
4. Recommending discussion topics

Format output as a structured agenda with talking points.
```

**Tools:** Account Data, Activity Data, Task Management

***

### Renewal Risk Monitor

**Purpose:** Proactively identify and address renewal risks

**Instructions:**

```
You monitor accounts for renewal risks by:

1. Tracking usage patterns and engagement trends
2. Identifying accounts with concerning signals
3. Drafting personalized outreach messages
4. Recommending specific retention actions

Prioritize accounts by risk level and ARR.
```

**Tools:** Account Data, Activity Data, Communication

***

## Using Agents in Automations

Agents can be embedded in automation flows using the **Agent V2** component:

```
Trigger → Gather Context → Agent Analysis → Take Action
```

This combines the reliability of automations with the intelligence of agents.

***

## Best Practices

### Instruction Writing

<Accordion title="Be specific about the role">
  Instead of "You are helpful", try "You are a customer success analyst with expertise in identifying churn risk signals"
</Accordion>

<Accordion title="Define output format">
  Specify how responses should be structured:

  ```
  Format your analysis as:
  ## Summary
  [1-2 sentence overview]

  ## Key Findings
  - Finding 1
  - Finding 2

  ## Recommendations
  1. Action 1
  2. Action 2
  ```
</Accordion>

<Accordion title="Set boundaries">
  Clarify what the agent should NOT do:

  ```
  Do not:
  - Make up data or statistics
  - Commit to timelines without verification
  - Share sensitive internal information
  ```
</Accordion>

### Tool Configuration

<Accordion title="Enable minimum necessary tools">
  Too many tools can confuse the agent and slow responses. Enable only what's needed for the specific task.
</Accordion>

<Accordion title="Match tools to purpose">
  An agent analyzing account health doesn't need task creation tools. An agent drafting outreach doesn't need CRM tools.
</Accordion>

### Testing

<Accordion title="Test with real scenarios">
  Use actual account data and realistic questions to validate the agent works as expected.
</Accordion>

<Accordion title="Test edge cases">
  What happens when:

  * Data is missing?
  * The question is ambiguous?
  * Multiple accounts match?
</Accordion>

***

## Monitoring and Improvement

### Track Agent Performance

* **Response quality:** Are answers accurate and helpful?
* **Tool usage:** Is the agent using tools appropriately?
* **Completion rate:** How often does the agent successfully complete tasks?

### Iterate on Instructions

Based on feedback:

* Add guidance for common failure modes
* Clarify ambiguous instructions
* Add examples for complex tasks

### Review Tool Usage

If the agent isn't using tools effectively:

* Check that needed tools are enabled
* Add explicit instructions about when to use specific tools
* Simplify by removing unnecessary tools

## Next Steps

<CardGroup cols={2}>
  <Card title="Creating Agents" icon="plus" href="/agent-studio/agents/creating-agents">
    Step-by-step guide to creating agents
  </Card>

  <Card title="AI Components in Automations" icon="robot" href="/agent-studio/automations/ai-components">
    Use agents within automation flows
  </Card>
</CardGroup>