news-signal-outreach

News Signal Outreach

The catch-all signal composite. Every other composite handles a specific signal type (funding, hiring, leadership change, champion move). This one handles everything else — any piece of news or public event that could create a reason to reach out.

A regulation change. A product recall. A competitor acquisition. A market expansion. A layoff. An earnings miss. A new partnership. An industry report. A conference keynote. A viral LinkedIn post. Any external event that shifts a company's priorities, creates urgency, or opens a window for your product.

Why this composite exists: The world generates an infinite stream of potential outreach triggers. The four structured signal composites handle the most common patterns. This composite handles the long tail — the unpredictable, opportunistic moments that often produce the best outreach because nobody else is sending a templated sequence about them.

When to Auto-Load

Load this composite when ANY of these are true:

• User shares ANY URL (LinkedIn post, article, tweet, blog, news) and asks about a company or person mentioned in it
• User says "came across", "saw this post", "found this article", "check this out", "is this relevant", "is this company a fit", "should we reach out"
• User mentions a company or person they discovered from an external source (social media, news, conference, podcast, newsletter) and asks about relevance or fit
• User asks "can we reach out to anyone based on this?"
• User says "check if this news is relevant to our prospects", "news-based outreach", "trigger-based outreach"
• User has a list of companies and wants to check recent news for outreach angles
• The news doesn't fit neatly into funding, hiring, leadership change, or champion move categories
• An upstream workflow surfaces a news item that needs evaluation

Key principle: If the user shares an external signal (URL, post, article, mention) and asks ANY question about the companies/people in it — load this composite. Don't wait for the word "outreach." The composite handles both evaluation-only (Steps 1-3) and full outreach (Steps 1-6).

Input Flexibility

This composite accepts three input modes:

| Mode | Input | Example | |------|-------|---------| | News → Companies | A news item. Extract companies/people mentioned, qualify them. | "Here's an article about new FDA regulations on telehealth" | | Companies → News | A list of companies. Find recent news about them, evaluate relevance. | "Check these 50 companies for any news we can use as an outreach angle" | | Person → News | A person or list of people. Find recent news about them or their company, evaluate relevance. | "Check if any of these prospects have been in the news" |

Step 0: Configuration (One-Time Setup)

On first run for a client/user, collect and store these preferences. Skip on subsequent runs.

ICP Definition

| Question | Purpose | Stored As | |----------|---------|-----------| | What does your company do? (1-2 sentences) | Relevance matching | company_description | | What problem do you solve? | Connection angle identification | pain_point | | What industries do you sell to? | ICP filter | target_industries | | What company sizes? | ICP filter | target_company_size | | What geographies? | ICP filter (optional) | target_geographies | | Any disqualifiers? | Hard no's | disqualifiers | | Who are your buyers? (titles) | Contact finding | buyer_titles | | Who are your champions? (titles) | Contact finding | champion_titles | | Who are your users? (titles) | Contact finding | user_titles |

Your Company Context

| Question | Purpose | Stored As | |----------|---------|-----------| | What specific outcomes does your product deliver? | Relevance angle building | product_outcomes | | Name 2-3 proof points (customers, metrics) | Email credibility | proof_points | | What categories of news are most relevant to your product? | Helps prioritize | relevant_news_categories |

Examples of relevant_news_categories:

# For a cybersecurity product:
relevant_news_categories: ["data breach", "compliance regulation", "security incident",
  "digital transformation", "cloud migration", "IPO/going public"]

# For a sales AI product:
relevant_news_categories: ["sales team scaling", "market expansion", "new product launch",
  "competitor acquisition", "cost cutting", "revenue miss"]

# For an HR tech product:
relevant_news_categories: ["layoffs", "rapid hiring", "remote work policy",
  "DEI initiative", "union activity", "culture crisis"]

Signal Detection Config

| Question | Options | Stored As | |----------|---------|-----------| | How should we find news? | Web search / Google News / RSS feeds / Social media | news_tool | | How far back should we look? (when scanning companies for news) | 7 / 14 / 30 / 60 days | lookback_days |

Contact Finding & Outreach Config

| Question | Options | Stored As | |----------|---------|-----------| | How should we find contacts? | Apollo / LinkedIn / Clearbit / Web search | contact_tool | | Where do you want outreach sent? | Smartlead / Instantly / Outreach.io / CSV export | outreach_tool | | Email or multi-channel? | Email only / Email + LinkedIn | outreach_channels |

Store config in: clients/<client-name>/config/signal-outreach.json or equivalent.

Step 1: Parse & Extract

Purpose: Take the raw news input — whatever form it arrives in — and extract structured entities (companies, people) and the core event.

Input Contract

Three modes:

Mode A: News → Companies/People

news_input: {
  mode: "news_to_targets"
  items: [
    {
      type: "url" | "text" | "structured"
      content: string               # URL to article, raw text, or structured summary
      source: string | null          # "TechCrunch", "LinkedIn post", "user provided", etc.
    }
  ]
}

Mode B: Companies → News

news_input: {
  mode: "targets_to_news"
  companies: [
    {
      name: string
      domain: string
      industry?: string
    }
  ]
  lookback_days: integer
}

Mode C: People → News

news_input: {
  mode: "people_to_news"
  people: [
    {
      full_name: string
      company: string
      linkedin_url?: string
    }
  ]
  lookback_days: integer
}

Process

Mode A: News → Companies/People

1. Fetch and parse the news content:
2. If URL → fetch the page, extract article text
3. If raw text → use as-is
4. If structured → use as-is

1. Extract entities:
2. Companies mentioned (name, role in the story — subject, affected party, partner, competitor)
3. People mentioned (name, title, company, role in the story)
4. The core event (what happened, in one sentence)
5. Event category (regulation, acquisition, partnership, product launch, market event, crisis, expansion, contraction, etc.)
6. Date of event
7. Affected industries

1. Expand if needed: If the news implies a broader set of affected companies beyond those mentioned:
2. "New FDA regulation on telehealth" → all telehealth companies, not just ones in the article
3. "Major data breach at [company]" → the breached company AND their competitors (who can capitalize)
4. "Industry report shows X trend" → companies in that industry

Mode B: Companies → News

1. For each company, search for recent news using configured news_tool:
2. Web search: "{company_name}" AND (news OR announced OR launches OR raises OR expands OR partners) within lookback_days
3. Filter results against relevant_news_categories from config
4. Extract the same fields as Mode A for each news item found

1. Group results: Company → list of news items, ranked by relevance to your product

Mode C: People → News

1. For each person, search for recent news/activity:
2. Web search: "{full_name}" AND "{company}" within lookback_days
3. LinkedIn activity (if available): recent posts, shares, co