One voice note, three requests: how we built an LLM router

Description and use

The system automatically splits a voice note containing multiple requests into separate tasks and routes them to the appropriate agents, asking for clarification only when needed.

Problem

Users record a single voice note that contains multiple requests, but the system must separate and route each request to the appropriate agent without requiring the user to issue them separately.

Outcome

The system enables field workers to issue complex multi‑action voice notes in a single utterance, automatically routing each request to the correct agent and only prompting for clarification when necessary, thereby reducing interruptions and improving workflow efficiency.

Workflow

• 1. Receive the raw voice note and transcribe it.
• 2. The router parses the transcription, splitting it by distinct requests rather than sentences.
• 3. Each request is passed to the agent that declares responsibility for that type of work.
• 4. The model receives the original wording and contextual project data (timestamps, current time, card contents).
• 5. The model selects the relevant card(s) based on the search results provided by code.
• 6. If the model cannot disambiguate (e.g., multiple matching cards), the router asks the user a clarifying question; otherwise it proceeds without confirmation.
• 7. The agent executes the action and logs the change in the card’s history.

Evidence

The router splits a message by the things asked, not by sentences.

Source

The router splits a message by the things asked, not by sentences.

Source

In practice, users accept 93% of permission prompts anyway.

Source