> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://poly-ai.ferndocs.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://poly-ai.ferndocs.com/_mcp/server.

# Technical considerations FAQ

> Answers on ASR/TTS independence, token limits, and context management best practices.

Answers to technical questions about automatic speech recognition (ASR), text-to-speech (TTS), token limits, and context management.

#### Can prompting affect how the agent talks or understands speech?

No. Prompts do not influence automatic speech recognition (ASR) or text-to-speech (TTS). These systems are independent.

> **Note**
>
> To customize speech recognition, use [ASR biasing](/advanced/code-driven-flows/asr-biasing) and [keyphrase boosting](/agent-studio/voice/advanced-settings#keyphrases). To customize voice output, see [voice settings](/agent-studio/voice/overview).

#### What are token and context limits?

Your agent's context is made up of global rules, retrieved topics, conversation history, and system instructions. Keeping this focused helps the agent perform at its best.

**Tips for managing context:**

* Keep global rules concise and prioritized.
* Write shorter, focused topic content – this also retrieves better.
* If you have many topics, make sure they are clearly differentiated so the retriever returns only the most relevant ones.
* Use [conversation diagnosis](/agent-studio/conversations/diagnosis) to inspect what the agent actually received if behavior seems off.