> ## Documentation Index
> Fetch the complete documentation index at: https://docs.plaisolutions.com/llms.txt
> Use this file to discover all available pages before exploring further.
# What is an Agent?
> Understand agents and the two ways to use them in PLai Framework
An **Agent** is an AI assistant you create and configure to perform specific tasks. Agents can chat with users, use tools, access knowledge bases, and integrate into workflows.
***
## Core Concept
**Agent = AI Model + Configuration + Tools + Datasources + Safety Rules**
Your agent is made up of:
* LLM Model (Claude, GPT-4)
* System Instructions
* Tools & Integrations
* Knowledge Bases
* Safety Guardrails
***
## Agent Capabilities
Every agent can:
Process natural language and context
Call APIs, search web, execute code
Query datasources and knowledge bases
Apply guardrails and safety filters
***
## Two Ways to Use Agents
Agents can be used in two fundamentally different ways:
### 1. Streaming Enabled: Conversational Chat
Use case: Chat interface, interactive conversations.
**Chat Conversational**:
* Real-time streaming
* Interactive chat UI
* Conversation history
* Multiple agent tabs
* Best for: User interaction
Flow:
1. User types question
2. Agent streams response
3. User sees real-time answer
**When to use:** Customer support chatbots, conversational assistants, interactive Q\&A
🔗 **Read more:** [Conversational Chat](./conversational-chat.mdx)
***
### 2. Streaming Disabled: Structured Output
Use case: Structured responses, integrations, automation.
**Structured Output**:
* Complete JSON response
* As tools in other agents
* In workflows
* Via API calls
* Best for: Automation
Flow:
1. Invoke agent (tool/workflow/API)
2. Agent processes
3. Returns complete response
**When to use:** Data processing, API integrations, workflow automation, batch processing
🔗 **Read more:** [Structured Output](./structured-output.mdx)
***
## Quick Comparison
| Aspect | Chat Conversational | Structured Output |
| ------------------------ | ------------------- | ------------------ |
| **Streaming** | ✅ Enabled | ❌ Disabled |
| **Interface** | Chat UI in PLai | Programmatic |
| **Response** | Streamed tokens | Complete JSON |
| **Use in Chat** | ✅ Direct chat | ❌ Not interactive |
| **Use as Tool** | ❌ Can't use as tool | ✅ Yes, as tool |
| **Use in Workflows** | ❌ No | ✅ Yes |
| **Use via API** | ❌ No (UI only) | ✅ Yes |
| **Conversation History** | ✅ Stored | ❌ Per-request only |
| **Multiple Tabs** | ✅ Agent tabs | N/A (not in chat) |
***
## How Agents Work
### Step-by-Step Process
You set up the agent with instructions, model, tools, and datasources
User or system calls the agent (via chat, API, workflow, or as a tool)
Agent receives input, accesses knowledge, calls tools if needed
Agent returns streamed (chat) or structured (output) response
### Example: Customer Support Agent
* **Configuration**:
* Name: "Support Bot"
* Model: Claude 3.5 Sonnet
* System Instructions: "Help customers with product issues"
* Datasources: FAQ database, product docs
* Tools: Help desk API, email
* Guardrails: No sensitive data exposure
* **Invocation (via Chat)**:
* Customer: "How do I reset my password?"
* Agent: (Searches FAQ) "Found answer..."
* Agent: (Streams response) "You can reset by..."
* Result: Customer sees real-time answer
* **Invocation (as Tool in Workflow)**:
* Workflow receives customer message
* Calls Support Bot as tool
* Gets complete response (JSON)
* Workflow routes to escalation if needed
***
## Key Concepts
### Agent Versions
Agents can have multiple versions. Switch between versions to:
* Test new configurations
* A/B test different prompts
* Roll back to previous behavior
* Maintain history
### Agent Slug
A unique, URL-friendly identifier for your agent (e.g., `support_bot`). Used in:
* API calls: `/agents/{slug}`
* Workflows: Reference the agent
* Tools: Invoke agent by slug
### Prompt/System Instructions
The base personality and behavior of your agent. Example:
```
"You are a friendly customer support specialist.
Be concise and helpful. If you don't know something,
offer to escalate to a human specialist."
```
### Datasources & Tools
* **Datasources** - Knowledge the agent can search (FAQs, docs, databases)
* **Tools** - Actions the agent can take (send email, call API, etc.)
***
## Agent Lifecycle
The agent lifecycle moves through five stages: Create, Configure, Deploy, Monitor, Improve.
1. **Create** — set up agent basics (name, description)
2. **Configure**
* Add system instructions
* Select model
* Connect datasources
* Add tools
* Set guardrails
3. **Deploy**
* If streaming: Enable chat in PLai
* If non-streaming: Use in workflows/API
4. **Monitor**
* View conversations (streaming)
* Track performance metrics
* Review analytics
5. **Improve**
* Optimize prompts
* Update datasources
* Adjust configuration
***
## Common Use Cases
Streaming chat agent to handle customer inquiries 24/7
Non-streaming agent in workflow to transform data
Streaming agent to generate marketing content interactively
Non-streaming agent to fetch and process external data
Streaming agent to explain and review code snippets
Non-streaming agent in workflow to process 1000s of records
***
## Next Steps
**Ready to create an agent?**
1. **[Configure an Agent](./configuration.mdx)** - Learn all configuration options
2. **[Understand Chat Mode](./conversational-chat.mdx)** - Interactive conversations
3. **[Understand Structured Output](./structured-output.mdx)** - Automation & integration
4. **[View Agent Analytics](./analytics.mdx)** - Monitor performance
Or jump to:
* **[Create Your First Agent](../../guides/first-agent.mdx)** - Step-by-step tutorial
* **[Agent Analytics](./analytics.mdx)** - Track conversations and performance
* **[Use Tools & Datasources](../concepts/agents-datasources-and-tools.mdx)** - Extend capabilities