Morning Debrief Analyzer

---

name: Morning Debrief allowed-tools: Bash, Read, Write description: Transcribe morning debrief audio and analyze for engineering ideas and priorities

Morning Debrief Analyzer

This prompt transcribes morning debrief audio recordings using OpenAI Whisper and analyzes the transcript to extract and organize key engineering ideas discussed. It creates a structured summary with the current date and quarter, identifies the top 3 priorities, lists all key ideas from the debrief, and generates novel extensions based on those ideas, and generates leading questions that can guide our work today with ideas for potential answers and next steps. Then it creates a transcript section with the full transcript of the debrief with every sentence as an individual item in a bulleted list. The output follows a clear hierarchical structure that makes it easy to reference during the workday. See the `Instructions` section for the detailed process. Output your results in a new markdown file with an alphanumeric + underscore name based on the original transcript file name.

Prerequisites

• OpenAI Whisper must be installed
• If you encounter installation errors, STOP and notify the user:

  Whisper is not installed. Please run:
  uv tool install openai-whisper

Variables

AUDIO_FILE_PATH: [[FILE_PATH]] DEBRIEF_OUTPUT_DIR: agentic_drop_zone/morning_debrief_zone/debrief_output// DEBRIEF_ARCHIVE_DIR: DEBRIEF_OUTPUT_DIR/drop_zone_file_archive/

Instructions

• First, check if whisper is available by running: which whisper
• If whisper is not found, notify the user to install it with: uv tool install openai-whisper
• Create output directory: DEBRIEF_OUTPUT_DIR//
  • date_time is the current date and time in the format YYYY-MM-DD_HH-MM-SS
• Transcribe the audio file using: whisper "[[FILE_PATH]]" --model tiny --language en --output_format txt --output_dir DEBRIEF_OUTPUT_DIR/
  • The --model tiny is fast and suitable for English transcription
  • You can use --model base or --model small for better accuracy if needed
  • The transcription will generate a .txt file in the output directory
  • IMPORTANT: Run this command with a 5 minute timeout. If it doesn't finish, notify the user and stop.
• Read the generated transcript file (it will have the same base name as the audio file but with .txt extension)
• Read the generated transcript file
• Determine the current date and quarter (Q1: Jan-Mar, Q2: Apr-Jun, Q3: Jul-Sep, Q4: Oct-Dec)
• Analyze the transcript to identify all engineering ideas and priorities mentioned
• Extract the top 3 most important priorities from the discussion
• List all key ideas concisely, focusing on actionable engineering concepts
• Generate novel extensions by:
  • Combining related ideas in new ways
  • Identifying potential optimizations or improvements
  • Suggesting complementary features or approaches
  • Proposing innovative solutions based on the discussed concepts
  • Extrapolate f