Skip to content

bdr_account_research

The one-call orchestrator for the BDR account brief. Reads the tenant’s account_research configuration, derives in-scope use cases, and pulls 10-K extracts, employee LinkedIn footprint, intent signals, and AI-scored prospects in parallel. Ships everything plus an inline render_spec that defines how the agent should render the brief.

Whenever the user asks to:

  • “Generate a report on X.”
  • “Research account Y.”
  • “Build a BDR brief for Z.”
  • Or mentions a company domain alongside use cases, intent signals, or 10-K context.
ParameterTypeRequiredDescription
company_websitestringYesTarget company website (e.g. "capitalone.com").
tenant_idstringYesTenant whose configuration drives keyword choice and prospecting enablement.
company_linkedin_urlstringNoRequired for the LinkedIn footprint section and for AI prospecting.
include_prospectsbooleanNoSkip the prospecting run when false. Default true.
signals_sincestringNoISO date floor for signals (e.g. "2025-01-01").
signals_limitintegerNoRow cap for the signals pull. Default 100.
filings_limitintegerNoFilings to consider. Default 1 (most recent).
footprint_limitintegerNoRow cap for the footprint pull. Default 30.

One JSON envelope containing tenant config + derived use cases, 10-K extracts, LinkedIn footprint, intent signals, AI-scored prospects (when enabled), an inline render_spec, and a flat datasets map.

datasets holds dataset IDs for each section (filings_10k, linkedin_footprint, intent_signals, prospects) the agent can slice further via query_datasets without re-running this tool.

Prospecting is asynchronous (1–3 minutes). When it hasn’t finished within the per-call budget the response carries status="still_running". Re-call this tool with the same arguments to resume.