Show HN:具備人類審核的 AI 輔助功能導入(n8n 工作流程)

Show HN:具備人類審核的 AI 輔助功能導入(n8n 工作流程)

Hacker News·

此專案展示了一個 AI 驅動的引擎,能將原始產品構想轉化為結構化、可直接導入 Jira 的票證,並包含一個由人類參與的審核步驟,以提升產品開發效率。

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

To see all available qualifiers, see our documentation.

This project is an AI-powered Feature Intake Engine that converts raw product ideas into reviewable, structured Jira-ready tickets, with a human-in-the-loop approval step. It is designed for Product, Engineering, and TPM teams who want speed without losing control.

Uh oh!

There was an error while loading. Please reload this page.

kavishsekhri/AI-Feature-Intake-Engine

Folders and files

Latest commit

History

Repository files navigation

🚀 AI Feature Intake Engine

Turn raw product requests into Jira-ready stories in under 1 minute, with humans in control

❌ The Problem

Great product ideas fail every day. Not because they’re bad, but because they arrive too late, too vague, or lose context before reaching the backlog.

Typical intake issues:

Speed without control is dangerous.
Control without speed is expensive.

✅ The Solution

The AI Feature Intake Engine accelerates product request review without removing human judgment.

In under 60 seconds, it:

AI does the heavy lifting.
Humans make the decision.

🧠 How It Works (High Level)

Request arrives
From Google Sheets, form, or intake source

AI enrichment
Gemini studies internal product features and architecture and converts raw input into:

Human-in-the-loop review
Reviewer:

Outcome

All of this happens before backlog pollution.

Architecture

The system is intentionally split into three independent workflows for clarity, safety, and scale.

1. Main Intake Flow (AI Generation)

Google Sheets → Filter → Google Drive Files → Gemini → Code → Email

2. Review Draft Flow (Human-in-the-loop)

GET Webhook → HTML Review Form → Respond to Webhook

This step prevents deterministic AI behavior from pushing bad specs downstream.

3. Submission Flow (Decision Engine)

POST Webhook → IF → Jira / Rejection Email

No brittle automation.
No blind Jira creation.
No black-box AI behavior.

🎯 Why This Matters (TPM / Technical PM Perspective)

From a delivery standpoint:

This engine pulls quality forward:

This is decision acceleration, not task automation.

⏱️ Real Impact

🛠️ Built With

Demo

🎥 Watch the full workflow demo on Youtube:
👉 https://youtu.be/bt-PUd4Po6g

🎥 The walkthrough shows:

👤 Who This Is For

💼 Need Help Getting Started?

Setting up the AI-Feature-Intake-Engine can be complex. I offer personalized setup sessions to help you get up and running quickly.

📅 Book a Setup Session

30-Minute Quick Help — $50
Perfect for quick questions, troubleshooting, or guidance on specific features.
👉 https://cal.com/kavish-sekhri/30min

60-Minute Deep Dive — $100
Comprehensive setup assistance, configuration, and Q&A.
👉 https://cal.com/kavish-sekhri/60min

What’s Included

About

This project is an AI-powered Feature Intake Engine that converts raw product ideas into reviewable, structured Jira-ready tickets, with a human-in-the-loop approval step. It is designed for Product, Engineering, and TPM teams who want speed without losing control.

Resources

Uh oh!

There was an error while loading. Please reload this page.

Stars

Watchers

Forks

Releases

Packages

  0

Footer

Footer navigation

Hacker News

相關文章

  1. Show HN:用於高轉換率社群媒體影片的開源 AI 工作流程

    3 個月前

  2. Show HN:Afelyon – 將 Jira 任務單轉化為 GitHub PR 的 AI 代理

    3 個月前

  3. 利用人工智慧快速驗證產品概念

    4 個月前

  4. Show HN:AI 控制框架 – 阻止 AI 編碼助手交付虛假程式碼

    3 個月前

  5. Show HN:Jinna - AI 發票工具,加速收款

    6 個月前