industry-intelligence-radar

Industry Intelligence Radar

Core Value

Information Gap Advantage: Knowing early = Acting early = Profiting early

Data Sources

Data Source	Access Method	Configuration Required	Signal Strength
Hacker News	`scan.py` Built-in (Algolia API)	No (free)	⭐⭐⭐⭐
V2EX	`scan.py` Built-in (official trending API)	No (free)	⭐⭐⭐
36kr / Huxiu / SSPAI, etc.	`scan.py` RSS source (config.rss)	No (just fill in the RSS address)	⭐⭐⭐
X/Twitter	Agent web search / X API	Requires X API Key	⭐⭐⭐⭐⭐
Jike	Agent web search	Requires search capability	⭐⭐⭐⭐

scan.py Using only the Python standard library, you can run HN + V2EX + any RSS source with zero dependencies and no API Key. X/Jike do not have a stable public interface, so the Agent supplements them using web search capability (see Phase 1).

Keyword Matrix

User Interest Areas

AI/Agent:
  - "AI agent" OR "AI 工具" OR "LLM" OR "大模型"
  - "Claude" OR "GPT" OR "Gemini" OR "DeepSeek"
  - "MCP" OR "tool use" OR "function calling"

半导体:
  - "半导体" OR "芯片" OR "chip" OR "semiconductor"
  - "台积电" OR "TSMC" OR "英伟达" OR "NVIDIA"

航天:
  - "航天" OR "火箭" OR "卫星" OR "SpaceX"
  - "星链" OR "Starlink"

新能源:
  - "新能源" OR "电动车" OR "电池"
  - "特斯拉" OR "Tesla" OR "比亚迪"

游戏:
  - "游戏" OR "Steam" OR "Switch" OR "PS5"
  - "米哈游" OR "原神" OR "黑神话"

跨境电商:
  - "跨境电商" OR "TikTok Shop" OR "SHEIN"
  - "独立站" OR "DTC"

创业/投资:
  - "创业" OR "融资" OR "投资"
  - "YC" OR "a16z" OR "红杉"

Workflow

Phase 1: Multi-Source Scanning

① Script scanning (HN + V2EX + RSS, free, can be cron'd)

# 用内置关键词矩阵扫最近 24 小时，输出简报到文件
python3 scripts/scan.py --hours 24 --output 简报-$(date +%F).md

# 自定义关键词 / 追加 RSS 源（36kr、虎嗅、少数派等）
python3 scripts/scan.py --config keywords.json --hours 24

keywords.json Example:

{
  "keywords": {
    "AI/Agent": ["AI agent", "LLM", "Claude", "MCP"],
    "半导体": ["半导体", "NVIDIA", "TSMC"]
  },
  "high_signal": ["融资", "发布", "launch", "raise"],
  "rss": ["https://www.36kr.com/feed", "https://sspai.com/feed"]
}

② Agent web supplementation (X / Jike, requires search capability)

For real-time social signals that scripts cannot cover, the Agent supplements them using web search, then merges them into the briefing:

搜索 X/Twitter："AI agent OR LLM OR 大模型" 最近 24 小时高互动内容
搜索即刻："AI OR Agent OR 创业" 高质量讨论

Phase 2: Signal Filtering

Filtering Rules：

Deduplication: Keep only the highest-quality source for the same event
Timeliness: Keep only content within 24 hours
Signal Strength：
- 🔴 High signal: financing, launches, policy changes, major partnerships
- 🟡 Medium signal: product updates, industry discussions, clash of viewpoints
- 🟢 Low signal: routine updates, duplicate information

Phase 3: Trend Detection

Detection Dimensions：

Sudden Trend: A topic suddenly appears in large volume
Sustained Trend: A topic appears frequently for more than a week
Emerging Trend: A new concept/new tool appears for the first time

Phase 4: Generate Intelligence Briefing

Output Format：

# 📡 行业情报简报 - YYYY-MM-DD

## 🔴 高信号（必须关注）

### 1. [事件标题]
- **来源**：X/Twitter @xxx
- **时间**：2 小时前
- **摘要**：一句话概括
- **影响**：对我/行业的影响
- **行动建议**：是否需要立即响应

## 🟡 中信号（值得了解）

### 2. [事件标题]
- **来源**：即刻 @xxx
- **摘要**：一句话概括
- **关联**：与我关注的 XX 领域相关

## 📈 趋势观察

### [趋势名称]
- **热度**：⬆️ 上升 / ⬇️ 下降 / ➡️ 平稳
- **持续时间**：X 天
- **相关讨论**：[链接1] [链接2]

## 💡 机会洞察

基于今日情报，发现以下潜在机会：
1. [机会1]
2. [机会2]

## 📊 数据统计

- 扫描源：5 个
- 原始条目：150+
- 筛选后：25 条
- 高信号：3 条

Cron Configuration

# 每日早报（工作日 8:30）
schedule: "30 8 * * 1-5"
deliver: feishu

# 可选：午间快报（12:00）
schedule: "0 12 * * 1-5"
deliver: feishu

Output Targets

Feishu Group: Daily intelligence push
Knowledge Base: Store high-value intelligence in wiki/📡 外部输入/情报/
Topic Library: Good topics discovered automatically enter the topic pool

Anti-Patterns

❌ Do not pursue full coverage; signal > quantity
❌ Do not just translate; have your own judgment
❌ Do not ignore Chinese communities (Jike, V2EX)
✅ Each piece of intelligence must have a conclusion on "what use is it to me"
✅ Prioritize exclusive/first-hand information sources