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

# Use cases

> Six pre-built workflows you can fork in chat: voice agents, AI assistants, embeddings, RAG search, document AI, and transcription. Each ships with its own model stack, optimization recipe, and benchmark targets.

Every use case is a starting point you can fork in [the dashboard](https://runinfra.ai/~). The agent loads the recommended models, the GPU profile, and the optimization recipe that ships with each blueprint, then optimizes against the priority you set (latency, throughput, cost, or quality).

<Columns cols={2}>
  <Card title="Voice agents" icon="mic" href="/use-cases/voice-agent">
    Streaming STT, LLM, and TTS on one open stack. Sub-600ms turn-taking on a single L40S.
  </Card>

  <Card title="AI assistants" icon="sparkles" href="/use-cases/ai-assistant">
    Hermes, Llama, Qwen with tool use, policy, and streaming on a single GPU.
  </Card>

  <Card title="Embeddings + rerank" icon="search" href="/use-cases/embeddings">
    BGE encoders plus a cross-encoder reranker fused on one GPU, one round-trip.
  </Card>

  <Card title="RAG search" icon="library" href="/use-cases/rag-search">
    Hybrid retrieval, grounded generation, citation spans you can audit.
  </Card>

  <Card title="Document AI" icon="file-text" href="/use-cases/document-ai">
    Qwen2.5-VL and Llama 3.2 Vision parsing PDFs, forms, and tables to JSON.
  </Card>

  <Card title="Transcription" icon="audio-lines" href="/use-cases/transcription">
    Open Whisper speech-to-text on an OpenAI-compatible endpoint, with long-form srt/vtt export.
  </Card>
</Columns>

## How to use these

1. Open [the dashboard](https://runinfra.ai/~) and start a chat.
2. Reference the use case by name ("build a voice agent pipeline") or paste one of the example prompts from the detail page.
3. The agent loads the canonical model stack, profiles GPUs, runs the optimization recipe, and produces a deployable pipeline.
4. Review the receipt and deploy. Every parameter (model, quantization, kernel, GPU, batch size, max tokens) is editable.

Each detail page also links to its full marketing page at `runinfra.ai/use-cases/<slug>`, which carries the latest benchmarks, model list, and pricing math for that workload.

## Pick a starting point

<Columns cols={2}>
  <Card title="I have a clear use case" icon="rocket" href="/use-cases/voice-agent">
    Jump straight to the matching detail page above.
  </Card>

  <Card title="I want to compare models first" icon="compass" href="/features/models">
    Browse the catalog by modality, license, and parameter count.
  </Card>
</Columns>