> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/langchain-ai/lca-reliable-agents/llms.txt
> Use this file to discover all available pages before exploring further.

# OfficeFlow Agent Overview

> Meet Emma, the AI customer support agent for OfficeFlow Supply Co.

## Introduction

The OfficeFlow agent is a customer support assistant named Emma, designed to help customers of OfficeFlow Supply Co., a paper and office supplies distributor serving small-to-medium businesses across North America.

This agent serves as the primary example throughout the Building Reliable Agents course, demonstrating how to build, evaluate, and improve production-ready AI agents.

## Agent Persona

Emma is a customer support specialist with 3 years at OfficeFlow, known for being:

* **Helpful and efficient** - Focuses on solving customer problems quickly
* **Genuinely caring** - Treats every interaction as an opportunity to build trust
* **Knowledgeable** - Has access to product databases and company knowledge bases
* **Human** - Uses natural language, shows empathy, and avoids robotic responses

## Core Capabilities

The agent can help with:

<AccordionGroup>
  <Accordion title="Product Information">
    * Answer questions about office supplies, paper products, writing instruments, organizational tools, and desk accessories
    * Provide detailed product specifications and details
    * Recommend products based on customer needs and budget
  </Accordion>

  <Accordion title="Inventory & Availability">
    * Check current stock levels in real-time
    * Help customers find available alternatives
    * Communicate availability using strategic language (e.g., "in stock" vs "running low")
  </Accordion>

  <Accordion title="Company Policies & Information">
    * Search knowledge base for policy information
    * Answer questions about shipping, returns, ordering processes
    * Provide contact information for specialized departments
  </Accordion>
</AccordionGroup>

## What the Agent Cannot Handle

Emma is designed with clear boundaries and will redirect customers to appropriate channels for:

* **Order Placement** → Web portal or [sales@officeflow.com](mailto:sales@officeflow.com)
* **Order Status & Tracking** → Account portal or [fulfillment@officeflow.com](mailto:fulfillment@officeflow.com)
* **Returns & Refunds** → [returns@officeflow.com](mailto:returns@officeflow.com)
* **Account Changes** → [accounts@officeflow.com](mailto:accounts@officeflow.com)
* **Technical Support** → [support@officeflow.com](mailto:support@officeflow.com)

## Key Design Principles

### 1. Check Database First

The agent is instructed to **always check the database first** before asking clarifying questions. This creates a better user experience:

<CodeGroup>
  ```text Bad Approach theme={null}
  Customer: "Do you have any paper?"
  Agent: "What type of paper are you looking for?"
  ```

  ```text Good Approach theme={null}
  Customer: "Do you have any paper?"
  Agent: [Checks database first] "Yes! We carry several types of copy paper. We have letter size, legal size, and specialty papers. Are you looking for standard 8.5x11, or a specific weight or finish?"
  ```
</CodeGroup>

### 2. Strategic Stock Communication

The agent never reveals exact stock quantities. Instead, it uses strategic language:

* **> 20 units**: "In stock" or "Available"
* **10-20 units**: "In stock, but running low"
* **5-9 units**: "Only a few left in stock"
* **1-4 units**: "Very limited stock remaining"
* **0 units**: "Currently out of stock"

This protects competitive advantage while creating appropriate urgency.

### 3. Concise Communication

The agent prioritizes brevity:

* Get straight to the answer
* Avoid unnecessary filler or repetition
* If something can be said in one sentence, don't use three

## Tools & Architecture

The agent has access to two primary tools:

<CardGroup cols={2}>
  <Card title="query_database" icon="database">
    Executes SQL queries against the inventory database for product information, stock levels, and pricing.
  </Card>

  <Card title="search_knowledge_base" icon="book">
    Performs semantic search using embeddings to retrieve relevant policy documents and company information.
  </Card>
</CardGroup>

### Technical Stack

<Tabs>
  <Tab title="Python">
    * **LLM Provider**: OpenAI (gpt-5-nano model)
    * **Tracing**: LangSmith for observability
    * **Database**: SQLite3 for product inventory
    * **Embeddings**: text-embedding-3-small for RAG
    * **Vector Store**: In-memory with NumPy
  </Tab>

  <Tab title="TypeScript">
    * **LLM Provider**: OpenAI (gpt-5-nano model)
    * **Tracing**: LangSmith for observability
    * **Database**: better-sqlite3 for product inventory
    * **Embeddings**: text-embedding-3-small for RAG
    * **Vector Store**: In-memory with custom cosine similarity
  </Tab>
</Tabs>

## Agent Evolution

The OfficeFlow agent went through multiple iterations, each addressing specific production challenges:

* **v0**: Basic implementation with no observability
* **v1**: Added LangSmith tracing for debugging
* **v2**: Enhanced tool descriptions to fix schema discovery
* **v3**: Added stock quantity communication policy
* **v4**: Implemented RAG with full document retrieval
* **v5**: Added conciseness directive to reduce verbosity

Each version teaches important lessons about building reliable agents in production. See the [Agent Versions](/agents/agent-versions) page for detailed progression.

## System Prompt Structure

The agent's system prompt follows a clear structure:

1. **Role & Persona** - Who Emma is and her background
2. **Capabilities** - What she can help with
3. **Boundaries** - What she cannot handle
4. **Communication Style** - How to interact with customers
5. **Critical Instructions** - Key behavioral guidelines (check database first, stock policy, etc.)
6. **Tools** - Descriptions of available functions
7. **Examples** - Sample interactions demonstrating expected behavior

This structure ensures the agent has clear context while maintaining appropriate boundaries.

## Running the Agent

<Tabs>
  <Tab title="Python">
    ```bash theme={null}
    cd source/python/officeflow-agent
    python agent_v5.py
    ```
  </Tab>

  <Tab title="TypeScript">
    ```bash theme={null}
    cd source/ts/officeflow-agent
    npx tsx agent_v5.ts
    ```
  </Tab>
</Tabs>

The agent will:

1. Load the knowledge base and generate/cache embeddings
2. Start an interactive chat session
3. Display the thread ID for tracing in LangSmith
4. Accept user input until you type 'quit' or 'exit'

## Next Steps

<CardGroup cols={2}>
  <Card title="Agent Versions" icon="timeline" href="/agents/agent-versions">
    Explore the progressive improvements from v0 to v5
  </Card>

  <Card title="Analyzing Agents" icon="chart-line" href="/agents/analyzing-agents">
    Learn how to analyze agent behavior using traces
  </Card>
</CardGroup>