Automated our team's weekly report with 2 bash scripts. GraphQL API fetches PRs across the org, jq handles stats, and claude -p groups them by theme into markdown. The "judgment" part is the only thing the LLM does — data collection stays deterministic.
Automated our team's weekly report with 2 bash scripts. GraphQL API fetches PRs across the org, j...
Dev.to / 3/12/2026
💬 OpinionDeveloper Stack & InfrastructureTools & Practical Usage
Key Points
- The team automated their weekly reporting workflow using two Bash scripts, reducing manual effort and potential for human error.
- They fetch PR data across the organization via a GraphQL API and use jq to compute and format statistics.
- An LLM (Claude -p) groups the collected data by theme and outputs Markdown, while the data collection process remains deterministic.
- The LLM handles only the judgment/interpretation step, keeping data gathering strictly deterministic.
- This approach demonstrates a practical, script-driven DevOps workflow for team reporting that can be adapted across organizations.
Related Articles
Manus、AIエージェントをデスクトップ化 ローカルPC上でファイルやアプリを直接操作可能にのサムネイル画像
Ledge.ai
The programming passion is melting
Dev.to
Best AI Tools for Property Managers in 2026
Dev.to
Building “The Sentinel” – AI Parametric Insurance at Guidewire DEVTrails
Dev.to
Maximize Developer Revenue with Monetzly's Innovative API for AI Conversations
Dev.to
