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

# AI Agents and automation in Fliqr AI

> Build LLM-powered AI Agents in Fliqr AI — providers, prompts, knowledge, functions, MCP, multimodal tools, handover, and best practices.

AI Agents let Fliqr AI answer questions you did not script in advance. You configure a model, a system prompt, knowledge, and tools. The agent reasons at runtime and replies in the contact’s language — then hands off to a Flow or a human when needed.

## When to use an AI Agent

| Use an AI Agent when…                  | Prefer a [Flow](/docs/core-concepts/flows) when…  |
| -------------------------------------- | -------------------------------------------- |
| Questions are open-ended               | Steps must be exact and auditable            |
| Answers come from your docs / policies | You need strict validation (payments, legal) |
| You want tool calls (orders, CRM, MCP) | The path is a fixed menu or form             |

Many workspaces combine both: a Flow for intake, an Agent for Q\&A, and [human handover](/docs/core-concepts/ai-agents/human-handover) for edge cases.

## How an Agent is built

1. **Provider + model** — OpenAI, Gemini, Claude, DeepSeek, xAI
2. **System prompt** — role, constraints, output format
3. **Knowledge / files** — grounded answers from your content
4. **Functions & MCP** — live actions and external systems
5. **Fallback** — Default Reply Flow, keyword rules, or human inbox

Deep conceptual model: [AI Agent concepts](/docs/core-concepts/ai-agents/concepts).

## Start here

<CardGroup cols={2}>
  <Card title="Connect providers" icon="microchip" href="/docs/core-concepts/ai-agents/ai-providers">
    Bring your own API keys or use included quota.
  </Card>

  <Card title="Create an Agent" icon="robot" href="/docs/core-concepts/ai-agents/create-agent">
    Spin up an agent and attach business data.
  </Card>

  <Card title="Prompt engineering" icon="pen-nib" href="/docs/core-concepts/ai-agents/prompt-engineering">
    Write prompts that stay on-brand and reliable.
  </Card>

  <Card title="Knowledge sources" icon="book" href="/docs/core-concepts/ai-agents/knowledge-sources">
    Ground answers in URLs, docs, and transcripts.
  </Card>

  <Card title="Functions & actions" icon="bolt" href="/docs/core-concepts/ai-agents/functions-actions">
    Call APIs and trigger Flows from the model.
  </Card>

  <Card title="Human handover" icon="headset" href="/docs/core-concepts/ai-agents/human-handover">
    Route to your team when AI should stop.
  </Card>
</CardGroup>

## Capabilities map

| Area           | Guides                                                                                                                                                                                                                                                                  |
| -------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Setup**      | [Providers](/docs/core-concepts/ai-agents/ai-providers) · [Create agent](/docs/core-concepts/ai-agents/create-agent) · [Prompts](/docs/core-concepts/ai-agents/prompt-engineering) · [Knowledge](/docs/core-concepts/ai-agents/knowledge-sources) · [Files](/docs/core-concepts/ai-agents/files) |
| **Tools**      | [Functions](/docs/core-concepts/ai-agents/functions-actions) · [MCP servers](/docs/core-concepts/ai-agents/mcp-servers) · [Rich responses](/docs/core-concepts/ai-agents/rich-responses)                                                                                               |
| **Multimodal** | [Vision](/docs/core-concepts/ai-agents/vision) · [Image generation](/docs/core-concepts/ai-agents/image-generation) · [Speech to text](/docs/core-concepts/ai-agents/speech-to-text) · [Read documents](/docs/core-concepts/ai-agents/read-documents)                                       |
| **Use cases**  | [Appointments](/docs/core-concepts/ai-agents/appointment-scheduling) · [Handover](/docs/core-concepts/ai-agents/human-handover) · [Keywords & priority](/docs/core-concepts/ai-agents/keywords-and-priority)                                                                           |
| **Reference**  | [Best practices](/docs/core-concepts/ai-agents/best-practices) · [Limits](/docs/core-concepts/ai-agents/limits)                                                                                                                                                                   |

## Related

<CardGroup cols={2}>
  <Card title="AI Agent concepts" icon="lightbulb" href="/docs/core-concepts/ai-agents/concepts">
    Components, models, and Agent vs Flow.
  </Card>

  <Card title="Flows" icon="diagram-project" href="/docs/core-concepts/flows">
    Scripted paths and AI Action blocks.
  </Card>
</CardGroup>