The mandate
A traditional, entrepreneur-led search fund pursuing its first platform acquisition in lower-middle-market business services, backed by a syndicate of search-fund investors.
The operating constraint
The searcher must run proprietary outreach and intermediated deal flow simultaneously, with a fraction of the resources of an institutional buyer. Owner-operated companies, small sponsor-held businesses, and broker packages arrive in inconsistent formats. Critical context sits in inboxes, spreadsheets, and call notes. Each new opportunity restarts the analysis, and the questions that decide whether a company is worth pursuing, such as ownership situation, owner dependence, and customer concentration, surface late, often after an IOI has already been submitted.
The multi-agent architecture
A saved mandate defines the universe by geography, sector, size, and ownership type. A discovery agent builds and maintains the target list from licensed data, public records, and broker packages, applying layout-aware parsing to CIMs and teasers and resolving entities into schema-validated company profiles. An ownership agent records who owns each company, for how long, and any visible succession or liquidity context. A screening agent scores each target against the thesis and records the rationale with citation-level provenance. When a company advances, a diligence agent reconciles reported figures, models a normalized working-capital peg, and sizes an SBA 7(a) or senior-plus-seller-note capital stack on a deterministic engine. An adversarial critic challenges add-backs and unsupported claims before the LOI rationale is drafted.
The work product
- A searchable, schema-consistent universe spanning proprietary and intermediated deal flow, with the reason to call on every company
- Source-linked target profiles with ownership context, normalized SDE and adjusted EBITDA, and thesis-fit scoring
- A QoE-aligned diligence request list for the companies that advance
- Draft IOI/LOI rationale, capital-stack scenarios, and a searcher investor update
The operating shift
The intended result is a search process with persistent memory: the searcher can see why a target cleared the screen, what changed between the teaser and the data room, and which owners deserve the next call, and can concentrate on owner conversations and deal structuring. Investment judgment, valuation, and all outreach remain with the searcher.
Human-in-the-loop governance
Human-in-the-loop checkpoints govern every consequential step: the searcher approves screening decisions, owner and broker outreach, IOI/LOI terms, and all investor communications.