Day 6: Festival Feedback, Automated – AI, GitHub Actions, & goose

How I tamed festival feedback chaos with AI-powered GitHub issue triage, instant labeling, and daily summaries, all thanks to goose CLI, Python, and GitHub Actions!

The Problem: Feedback Overload!

You know the feeling—hours after a festival launches, the feedback floods in: bug reports, urgent facility requests, feature dreams, a swarm of questions. Suddenly, it’s chaos in GitHub Issues!

This year, I vowed to solve it once and for all with AI, automation, and some Goose-powered magic.

Introducing: My Festival Feedback System

Turn GitHub Issues into a self-organizing, AI-triaged feedback powerhouse.

🛠️ Tech Stack

• goose CLI (by Block): My conversational AI sidekick
• GitHub Actions: For seamless issue and comment workflows
• OpenAI API & Anthropic API: LLM brains (GPT-4o-mini + Claude possible)
• Python: For custom triage, sentiment analysis, and summaries
• YAML: To glue workflows and schedule automations
• PyGithub: For easy Python <-> GitHub API integration

⚡️ What My System Does

• Issue Categorization: AI instantly classifies every issue as bug, feature, question, or urgent
• Priority Detection: From "life-or-death" (critical) to "nice-to-have" (low)
• Sentiment Analysis: Tracks vibes—positive, neutral, or negative feedback
• Automated Responses: Helpful, human-sounding replies directly on issues
• Comment Handling: Smart AI follows up on new comments, keeps the convo going
• Custom Issue Templates: Streamlined forms for bug, feature, question
• Daily Summaries: Each morning, AI posts a status update with insights/trends/urgent flags

🛠️ How I Built It (Step-by-Step)

GitHub Secrets 🔑 Set up OpenAI & Anthropic API keys securely in repo secrets. Easy, safe, and ready for YAML workflows to call. 1.

Workflows as Automation Engines ⚙️ Set up two core YAML workflows: 1.

issue-triage.yml for handling issues/comments 1.

daily-summary.yml for morning stats 1.

Python as the AI Brain 🧠 The magic: Python scripts—called by the workflows—to analyze, categorize, summarize, and reply, all with LLM-powered prompts! 1.

Testing Like a Festival Pro 🎪 Created template-based issues for urgent facility problems, feature requests, and lost+found questions to see if the system could: 1.

Assign correct labels/priority 1.

Reply in a friendly, actionable way 1.

Summarize the surge in daily feedback

Wow, it nailed all of it! 🚀

🎨 Why This is Game-Changing

• Automates triage so no critical issue goes unseen
• Turns average feedback into actionable data (sentiment, trends, priorities)
• 24/7 AI responder: No more “sorry for late reply!”
• Adapts for any project: Open source, events, support, product feedback...
• Easy to customize (edit Python prompt, labels, or templates)

Real World: Example Issue (and what happened) Issue posted:

[URGENT] Heating system not working in storytelling tent

• Labeled as 🚨 urgent, 🟠 high priority, and 😟 sentiment: negative
• Instant response with stats and next steps for staff
• Showed up in the next day’s daily summary under "urgent issues"

What I Learned

• Goose CLI is fantastic for rapid prompt and script prototyping Allow AI help design your workflow logic!
• GitHub Actions + AI = superpowers for project management
• Good prompt design = helpful (not spammy) automated replies
• Daily summaries help the team stay focused on trends, not just tasks
• Secret/config management in GitHub is easier than ever

Powered by

• Goose by Block
• OpenAI & Anthropic LLM APIs
• GitHub Actions + PyGithub

Final Thoughts Day 6’s Using goose CLI with GitHub Actions created a fast, AI‑assisted workflow where prompts, scripts, and automated summaries evolved in real time. Strong prompt design, combined with streamlined secrets management, made the entire pipeline cleaner, more reliable, and far easier to maintain. My automation project turned issue "chaos" into calm our festival team felt empowered, automation done correctly! 😊. I look forward to adapting this setup for future development and open it up for the world to use!

Day 6: Automated. Feedback: Tamed. Community: Happy!

This post is part of my Advent of AI journey - AI Engineering: Advent of AI with goose Day 6 of AI engineering challenges.

Follow along for more AI adventures with Eri!