Attio Buying Committee Expansion

What this skill does

Surfaces the rest of the buying committee for an open Attio deal. Starting from the deal's associated company, it searches MoltSets for people in the target titles and seniority levels, dedupes them against the people already linked to the deal, fills email gaps, creates the new person records in Attio, and links each one to the deal's people reference attribute. It finds the stakeholders your reps did not know to look for.

Chain

Attio open deal record
  to attio/get-record                   (deal + associated company domain, read directly off the deal's reference attributes)
  to MoltSets:
      search_people                     (company_domain + target titles / seniority / department)
  to dedupe against existing deal-linked people + suppression rules
  to linkedin_to_best_email             (fill email gaps where search_people has none)
  to attio/create-record                (create new person records)
  to attio/update-record                (add new people to the deal's people reference attribute)

Inputs

• Deal - the Attio deal to expand, or a filter for a set of open deals
• Target roles - the titles, seniority levels, and departments that make up your buying committee
• Coverage - how many people per account to add, and any hard caps
• Suppression rules - domains, existing records, and do-not-contact lists to exclude
• Acceptable risk scores - which A-F deliverability grades to keep (recommended: A, B, C and F; D excluded)

How it works

1. Reads the deal record directly, resolving the associated company's domain from the deal's own reference attribute rather than a separate association call
2. Reads the people already linked to the deal so they can be excluded from the results
3. Runs search_people filtered on the company domain plus your target titles (via query), seniority, and department filters
4. Dedupes the returned people against existing deal-linked people and your suppression rules
5. Uses the business_email returned by search_people where present, and runs linkedin_to_best_email to fill any gaps
6. Creates the new person records in Attio and adds each one to the deal's people reference attribute

Output

Deal company:            X
Existing deal people:    X
Candidates found:        X
New records added:       X
Emails found:            X/N (XX%)
MoltSets tokens used:    X

Email risk scores:
  A: X   B: X   C: X   D: X   F: X
  kept (accepted grades):  X
  filtered (excluded):     X

Search filters

search_people filters on query, company, company_domain, country, state, city, seniority, department or functional_area, industry, linkedin_industry, naics_code, employee_range, and revenue_range.

• Filters are free precision - execution cost comes from the free-text query, so a filters-only search runs ~40x cheaper and lands more precisely. A bare query is never the right shape; at minimum it gets country attached (~99% fill rate).
• Size and revenue apply to the person's current employer - "VPs at 51-200 employee software companies" is one call, not a company search followed by a people search.
• Three industry vocabularies - broad industry buckets, LinkedIn's ~150 niche labels, or a NAICS code at any depth. Shortening the code widens the net.
• Sparse filters are the usual cause of a thin result set - seniority/industry/department are ~60% filled and naics_code/linkedin_industry ~50%, and every filter is exact-match, silently dropping records where the field is empty.
• Sizing is free - count_only: true returns a match count without fetching data or charging tokens, and every response carries results.total to read before paginating.

Tips

• Requires the Attio MCP (mcp.attio.com) and the MoltSets MCP connected in the same client
• search_people returns a business email in many records, so check that field before spending a token on a separate email call
• Use company_domain for the account match rather than free-text company name, since domain is exact
• Set a per-account cap so a large company does not flood the deal with dozens of loosely relevant records
• Creating records and updating the deal's reference attribute changes the deal, so run a dry-run pass and confirm before writing
• This pattern works identically for a custom deal-like object, since the reference-attribute model is the same across standard and custom objects in Attio
• Every returned email carries an A-F deliverability risk score; you're asked up front which grades to keep, and out-of-range grades are shown and flagged rather than silently dropped