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

# Building GenerativeAgent

> Map of what building GenerativeAgent touches. Pick the areas that fit your deployment.

Getting Started left off with one Topic answering one question in the Previewer. Not every deployment goes all the way: some teams only deflect and route, others automate full workflows on top. Pick the pieces that fit.

## Deployment patterns

<CardGroup cols={2}>
  <Card title="Answer from KB and route to humans" icon="signs-post" href="#knowledge-base-and-routing">
    Use your Knowledge Base so GenerativeAgent can answer what it can. Everything else transfers to the right human queue. The first real deployment for most teams.
  </Card>

  <Card title="Automate workflows" icon="gears" href="#task-automation">
    Tasks take over work human agents used to handle, backed by API Connections. Layers on top of KB answering and routing.
  </Card>
</CardGroup>

## How GenerativeAgent works

Read this before configuring anything else. Voice and chat behave differently, and the distinction shapes how Topics, Tasks, and Functions are written.

<CardGroup>
  <Card title="How GenerativeAgent works" icon="diagram-project" href="/generativeagent/build/how-ga-works">
    Talker-Reasoner for voice, single-model for chat, and what happens on each turn.
  </Card>
</CardGroup>

## Knowledge base and routing

Ingest Sources, grow Topics beyond the first one, and configure Handoffs for transferring to human queues.

<CardGroup cols={2}>
  <Card title="Connect a knowledge base" icon="book" href="/generativeagent/configuring/connecting-your-knowledge-base">
    Ingest Sources from URLs, files, or an existing KB and keep them in sync.
  </Card>

  <Card title="Route conversations" icon="route" href="/generativeagent/build/using-ga-at-top-of-ivr">
    Configure Topics and Handoffs so GenerativeAgent answers what it can and transfers the rest.
  </Card>

  <Card title="Handoffs" icon="headset" href="/generativeagent/configuring/tasks-and-functions/handoff">
    Availability-aware routing to agent queues with context the human can use.
  </Card>
</CardGroup>

## Task automation

Replace scripted human-agent workflows with deterministic Tasks. Tasks call Functions, Functions call the APIs configured as API Connections, so the backend work is part of building a Task.

<CardGroup cols={2}>
  <Card title="Add a use case" icon="list-check" href="/generativeagent/build/adding-a-use-case">
    Design a Task, wire it to Topics, and pattern it after a real agent workflow.
  </Card>

  <Card title="API Connections" icon="plug" href="/generativeagent/configuring/connect-apis">
    Map a JSON API to an LLM-friendly interface. Works for Salesforce, Zendesk, HubSpot, and most modern APIs.
  </Card>

  <Card title="Code API Connections" icon="terminal" href="/generativeagent/configuring/connect-apis/code-api-connections">
    Chain multiple calls, handle SOAP or form posts, or run a complex workflow as one action.
  </Card>
</CardGroup>

## Testing

Validate changes before they ship. Previewer for interactive checks, Test Scenarios for scripted regressions, functional testing for the integration surface.

<CardGroup cols={2}>
  <Card title="Previewer" icon="play" href="/generativeagent/configuring/previewer">
    Interactive testing for a single Topic or Task in the Draft environment.
  </Card>

  <Card title="Test Scenarios" icon="flask" href="/generativeagent/configuring/tasks-and-functions/test-scenarios">
    Scripted multi-turn conversations that run as regression checks.
  </Card>

  <Card title="Functional testing" icon="clipboard-check" href="/generativeagent/configuring/functional-testing">
    Validate end-to-end behavior across the deployment, not just the agent.
  </Card>
</CardGroup>

## Deployment and channels

Promote Draft to Production and wire the agent into a voice or chat platform.

<CardGroup cols={2}>
  <Card title="Deploy GenerativeAgent" icon="rocket" href="/generativeagent/configuring/deploying-to-generativeagent">
    Promote Draft to Production and manage versions across environments.
  </Card>

  <Card title="Channel integrations" icon="phone" href="/generativeagent/integrate">
    Amazon Connect, Genesys, Twilio, Zendesk Talk, SIP, or the ASAPP Web SDK.
  </Card>

  <Card title="Go-live checklist" icon="circle-check" href="/generativeagent/go-live">
    The final review before production traffic hits the agent.
  </Card>
</CardGroup>

## Human oversight and safety

Human-in-the-Loop approval and data-handling controls. Configure early, not after go-live.

<CardGroup cols={2}>
  <Card title="Human-in-the-Loop Agent" icon="user-check" href="/generativeagent/human-in-the-loop">
    Require human approval on specific Tasks or Topics before the agent acts.
  </Card>

  <Card title="Data redaction" icon="eye-slash" href="/security/data-redaction">
    PII handling in transcripts, logs, and evaluators.
  </Card>
</CardGroup>

## Observation and improvement

Review transcripts, score live traffic with Evaluators, and track containment and Task completion in reports.

<CardGroup cols={2}>
  <Card title="Conversations" icon="comments" href="/generativeagent/configuring/conversations">
    Full transcript review with reasoning traces and tool calls.
  </Card>

  <Card title="Evaluators" icon="gauge" href="/generativeagent/observe/evaluators/manual-annotation">
    Manual annotation and automated scoring on live traffic.
  </Card>

  <Card title="Reporting" icon="chart-line" href="/generativeagent/reporting">
    Containment, handoff, and Task metrics across the deployment.
  </Card>
</CardGroup>