> ## Documentation Index
> Fetch the complete documentation index at: https://docs.b-bot.space/llms.txt
> Use this file to discover all available pages before exploring further.

# Customer Support

> Plan a customer support AI Agent with grounded answers, clear boundaries, and human escalation.

# Customer Support

A customer support AI Agent can help users find documented information, follow troubleshooting steps, and prepare a handoff to a person. Design it as part of a support process, not as a replacement for policy, account controls, or human judgment.

## Define the Scope

Start with a limited set of supported tasks, such as:

* Answering questions from approved help content
* Guiding users through reversible troubleshooting steps
* Collecting details needed for a support request
* Summarizing a conversation for a human agent
* Drafting replies for human review

List tasks the Agent must not complete without an approved tool and appropriate authorization. Examples include changing account access, issuing refunds, or making legal commitments.

## Configure the Agent

<Steps>
  <Step title="Define the Role">
    Describe the products, users, languages, and issue types the Agent supports. State when it must say that it does not know.
  </Step>

  <Step title="Add Maintained Knowledge">
    Connect current help articles, policies, and troubleshooting guides. Assign an owner and review date to each source.
  </Step>

  <Step title="Set Response Rules">
    Require concise steps, distinguish confirmed facts from suggestions, and ask for missing context before diagnosing a problem.
  </Step>

  <Step title="Design Escalation">
    Specify when to involve a person and which details should be included in the handoff.
  </Step>

  <Step title="Test the Experience">
    Test both the Agent and its intended Distribution Channel with common questions, outdated assumptions, unsupported requests, and sensitive cases.
  </Step>
</Steps>

## Example System Prompt

```text theme={null}
You are a customer support Agent for [organization].

Use only the approved support information available to you.
If the answer is not supported, say what is missing and offer a human handoff.
Ask for the minimum information needed to understand the issue.
Give reversible troubleshooting steps one at a time.
Do not claim that an account change, refund, or ticket update was completed
unless an authorized tool confirms it.
Do not request passwords, full payment details, or other unnecessary secrets.
```

Adapt this example to your policies and available capabilities.

## Escalation Design

Escalate when:

* The user asks for a person
* The request requires identity verification or restricted account access
* A policy exception or financial decision is required
* The available knowledge does not support an answer
* Troubleshooting could cause data loss or another irreversible outcome
* The conversation involves safety, legal, or compliance concerns

An escalation summary should separate user-provided facts, actions already attempted, relevant source material, and the unresolved question.

## Evaluation

Build a repeatable test set and review:

* **Grounding:** Is the answer supported by current source material?
* **Resolution path:** Are the next steps clear and appropriate?
* **Boundary handling:** Does the Agent avoid unsupported actions and claims?
* **Escalation:** Does it hand off at the correct point with useful context?
* **Privacy:** Does it avoid collecting unnecessary sensitive data?
* **Tone:** Is the response respectful without hiding uncertainty?

Track results from your own workflow. Do not assume a specific automation rate, response time, or cost saving before measurement.

<Warning>
  Review privacy, security, retention, and access requirements before connecting customer records or support systems. A connected app should receive only the permissions needed for the approved workflow.
</Warning>

## Related Guides

<CardGroup cols={2}>
  <Card title="Create an Agent" icon="plus" href="/essentials/create-expert">
    Create the initial customer support Agent.
  </Card>

  <Card title="Craft a System Prompt" icon="message" href="/concepts/best_practices/crafting-a-system-prompt">
    Write testable behavior and escalation instructions.
  </Card>

  <Card title="Training Concepts" icon="brain-circuit" href="/concepts/fine-tuning/introduction">
    Choose between maintained knowledge, examples, and fine-tuning.
  </Card>

  <Card title="Distribution Channels" icon="share-nodes" href="/essentials/distribution-channels">
    Configure how users reach the support experience.
  </Card>
</CardGroup>