From meeting speech to task dispatch: wiring on-device ASR into an AI collaboration workflow

说明与用途

从会议语音到任务派发的端到端管道：在设备上进行语音识别，提取行动项，创建 Octo 循环，分配给代理执行，并通过反馈迭代完善交付物。

问题

Roughly 40% of verbally agreed tasks in daily meetings never made it into any tracking system, leading to missed action items.

结果

Implemented an end‑to‑end pipeline that captures spoken action items, automatically creates task Loops in Octo, assigns them to agents, and iteratively refines deliverables through feedback, significantly improving task capture and reducing manual follow‑up.

工作流

• Record audio with Octic hardware
• Run on‑device ASR to produce timestamped, speaker‑attributed JSON transcript
• Post‑meeting batch NLU extracts action items, decisions, and open questions
• Map extracted action items to Octo Loops via API, setting title, owner, acceptance criteria, and source context
• Notify assigned Agent in Octo, who executes the task and submits deliverable
• Human reviews deliverable, accepts or rejects, providing feedback stored as Preferences
• Agent revises based on feedback, iterating until acceptance

证据

Roughly 40% of verbally agreed tasks never made it into any tracking system.

来源

The output is a timestamped, speaker‑attributed transcript in JSON.

来源

We run a lightweight NLU pass over the full transcript.

来源