company-contact-finder

# company-contact-finder

Find decision-makers at a specific company by name and target titles. Uses Gooseworks MCP tools (Apollo, Crustdata, Fiber, PDL) with a layered fallback strategy to maximize results while minimizing cost.

## Inputs

| Input | Required | Default | Description |
|-------|----------|---------|-------------|
| company_name | Yes | -- | The company to search (e.g., "EisnerAmper") |
| company_linkedin_url | No | -- | Company LinkedIn URL for disambiguation |
| target_titles | Yes | -- | List of titles to find (e.g., ["Partner", "Controller", "VP Finance"]) |
| num_results | No | 10 | How many contacts to return |

## Procedure

### Step 1: Understand the Request

Parse the user's request to extract:
- **company_name** (required) -- the company to search at
- **company_linkedin_url** (optional) -- helps disambiguate common names
- **target_titles** (required) -- list of job titles or roles to find (e.g., ["Partner", "Controller", "VP Finance", "CFO"])
- **num_results** (optional, default 10) -- how many contacts to return

If the user does not provide target titles, ask for them. Suggest common senior titles based on context:
- For accounting/CPA firms: Partner, Managing Director, Controller, CFO, VP Finance
- For tech companies: VP Engineering, CTO, Head of Product, Director of Engineering
- For general B2B: VP, Director, C-Level, Head of

### Step 2: Apollo Search (Primary — cheapest at $0.01/call)

Apollo is the cheapest search provider. Start here for all searches.

**Call:**
```
apollo_person_search(
  person_titles: ["Partner", "Controller", "VP Finance"],
  organization_domains: ["eisneramper.com"],
  per_page: 25
)
```

If you don't have the company domain, use `q_keywords` with the company name:
```
apollo_person_search(
  person_titles: ["Partner", "Controller", "VP Finance"],
  q_keywords: "EisnerAmper",
  per_page: 25
)
```

**Parse the response:**
Each result contains: name, title, company, LinkedIn URL, location, email, and other profile fields. Extract and collect all results into a working list.

### Step 3: Evaluate Results

Check how many results from Step 2 match the target titles at the target company.

**Quality checks:**
1. Filter out results where the company name does not match (fuzzy match is fine -- "EisnerAmper LLP" matches "EisnerAmper")
2. Filter out results where the title does not reasonably match any target title
3. Count remaining high-quality matches

**Decision:**
- If 3+ quality matches found: skip to Step 7 (Output)
- If fewer than 3 quality matches: proceed to Step 4

### Step 4: Fiber Search (Fallback 1 — $0.02/record)

Fiber supports natural-language queries and may have profiles Apollo does not.

**Call:**
```
fiber_person_search(
  query: "[title1] OR [title2] OR [title3] at [company_name]",
  page_size: 25
)
```

**After results return:**
1. Parse results (extract name, title, company, LinkedIn URL, location)
2. Merge with all previous results
3. Deduplicate by LinkedIn URL

**Decision:**
- If 3+ total unique quality matches: skip to Step 7 (Output)
- If still fewer than 3: proceed to Step 5

### Step 5: Crustdata Structured Search (Fallback 2 — $0.66/page)

Use Crustdata's structured filter search for more precise matching. Run one search per target title, then merge results.

**For each target title, call:**
```
crustdata_person_search(
  conditions: [
    {"column": "current_employers.name", "type": "in", "value": "[company_name]"},
    {"column": "current_employers.title", "type": "(.)", "value": "[target_title]"}
  ],
  filter_op: "and",
  limit: 25
)
```

**Example for "Partner" at EisnerAmper:**
```
crustdata_person_search(
  conditions: [
    {"column": "current_employers.name", "type": "=", "value": "EisnerAmper"},
    {"column": "current_employers.title", "type": "(.)", "value": "Partner"}
  ],
  filter_op: "and",
  limit: 25
)
```

**Optional seniority filter:** If the user requests senior decision-makers broadly (rather than specific titles), add:
```
{"column": "current_employers.seniority_level", "type": "in", "value": "VP,C-Level,Director"}
```

**TIP:** Use `preview: true` first to check result count for free before fetching full data.

**After all title searches complete:**
1. Merge all results into one list
2. Deduplicate by LinkedIn URL (keep the first occurrence)
3. Combine with results from previous steps

**Decision:**
- If 3+ total unique quality matches: skip to Step 7 (Output)
- If still fewer than 3: proceed to Step 6

### Step 6: PDL Search (Fallback 3 — $0.30/record, most expensive)

PeopleDataLabs is the most expensive search provider. Only use as a last resort when other sources have insufficient results.

**Call:**
```
pdl_person_search(
  job_titles: ["Partner", "Controller", "VP Finance"],
  company_names: ["EisnerAmper"],
  num_results: 10
)
```

**After results return:**
1. Parse results (extract name, title, company, LinkedIn URL, location)
2. Merge with all previous results
3. Deduplicate by LinkedIn URL

### Step 7: Output

Present the final deduplicated contact list.

**Table format (for the user):**

| # | Name | Title | Company | LinkedIn URL | Location |
|---|------|-------|---------|--------------|----------|
| 1 | Jane Smith | Partner | EisnerAmper | https://linkedin.com/in/janesmith | New York, NY |
| 2 | John Doe | Controller | EisnerAmper | https://linkedin.com/in/johndoe | Chicago, IL |
| ... | | | | | |

**JSON format (for downstream skills):**

```json
{
  "company": "EisnerAmper",
  "search_titles": ["Partner", "Controller", "VP Finance"],
  "contacts": [
    {
      "name": "Jane Smith",
      "title": "Partner",
      "company": "EisnerAmper",
      "linkedin_url": "https://linkedin.com/in/janesmith",
      "location": "New York, NY"
    }
  ],
  "total_found": 10,
  "sources": ["apollo", "fiber", "crustdata", "pdl"]
}
```

**Summary line:**
> Found X contacts matching [titles] at [company]. Sources used: [list of sources that returned results].

If fewer than 3 contacts we