Review each target entity by legal, tax, people, IP and environment

For: Deal lead coordinating workstreams on a multi-entity, multi-country acquisition

Pattern: Specialist panelNeeds scaleDesigned for 20 to 800 agents

The pain today

Workstreams read the same entity folders separately and report in separate memos. Issues that cross briefs, such as an IP assignment missing from an employment contract, fall between teams until after signing.

The ask

I attached the data room folders for each company in the target group and the checklists for our legal, tax, employment, IP and environmental workstreams. Review every company from each of those angles, show the documents behind each finding, and point out issues that touch more than one workstream.

Plain words, as you would say it to a colleague. Edit it to fit your case before you send it.

What you attach or connect

  • Data room folders per target entity
  • Workstream checklists
  • Group structure chart
  • Seller's information memorandum and Q&A log

The unit of work

One worker task per one entity folder under one workstream brief.

Why a swarm fits

Entities multiplied by workstreams gives a wide grid of independent cells, each needing one folder and one checklist. Cross-brief issues appear only when the cells are reconciled side by side.

Not for

A single-entity target with a thin data room: the specialist teams read it directly in less time than a review takes.

The decision tree

6 typed decisions, each with an action for every answer

At fixed moments in a run, the engine puts one narrow question to a decision model. The decision model never writes text: it answers yes or no with a probability, picks from listed options, or gives a score, about a small slice of the material. The engine then does exactly what this tree says, which is what makes the run auditable. The thresholds are the template's design values, not measured results.

  1. Planner, while planning

    Scope checkYes or no, with a probability

    Before work starts on a unit

    Does the document name this cell's legal entity, as shown on the structure chart, as a party or subject?

    Sees only: The document's party block and the structure chart entry

    Why: Findings pinned on the wrong group company mislead the whole report.

    • Yes: 0.70 or higherthenAccept
    • Unsure: 0.40 up to 0.70thenEscalate to a strong model
    • No: below 0.40thenSkip this unit
  2. Before workers, before a task runs

    Small worker or strong modelYes or no, with a probability

    Before a task runs

    Does this checklist item turn on a foreign-language document, a regulated licence or a tax ruling?

    Sees only: The checklist item and the candidate documents' titles and languages

    Why: Routine corporate records stay cheap; licences and rulings do not.

    • Yes: 0.50 or higherthenEscalate to a strong model
    • Unsure: 0.30 up to 0.50thenEscalate to a strong model
    • No: below 0.30thenAccept
  3. After workers, the judge checks

    Evidence checkYes or no, with a probability

    After a worker answers

    Does the cited data room document show the defect stated in the finding, such as an employment contract without an IP assignment clause?

    Sees only: The finding and the quoted document passage with its index number

    Why: A reportable finding must be one click from its proof.

    • Yes: 0.85 or higherthenAccept
    • Unsure: 0.50 up to 0.85thenEscalate to a strong model
    • No: below 0.50thenReject and retry
  4. Reconciler, while merging

    Conflict checkA choice among options

    While reconciling

    Two workstreams raised findings on the same document: how do they relate?

    Sees only: The two findings and the shared document passage

    Why: Cross-workstream issues are what separate memos never show.

    • Same issue seen from two briefsthenAccept
    • They contradict each otherthenMark unresolved
    • Separate issuesthenAccept
  5. Run control, between rounds

    Retry or stopA choice among options

    After a rejection or low confidence

    Nothing was found for this checklist item: what does the data room index show?

    Sees only: The checklist item and the folder's index

    Why: An information gap becomes a request to the seller only when it is real.

    • Index shows no such documentthenMark unresolved
    • Index lists a likely document not yet readthenReject and retry
  6. Accountable person, before anything is settled

    Person decidesYes or no, with a probability

    Before anything is reported as settled

    Does this finding carry a money exposure, a licence risk or an effect on more than one workstream?

    Sees only: The finding with its sources

    Why: Workstream leads decide what is reportable and material.

    Accountable: Each workstream lead decides what is reportable and material; the deal lead owns the recommendation to the committee.

    • Yes: 0.40 or higherthenAsk a person
    • Unsure: 0.15 up to 0.40thenAsk a person
    • No: below 0.15thenAccept

The fleet: who does what

Model tiers by role, not brands: you choose the models. Strong reasoning models plan and reconcile, small fast models do the wide work, and the judge is a decision model from a different family, so it does not share the workers' blind spots.

  1. Planner

    A strong reasoning model maps data room folders to entities and workstreams and sets the checklist per cell.

    Decisions here:1. Scope check

  2. Workers

    Small fast workers, each holding one workstream brief, review one entity folder and cite documents per finding.

    Designed for 20 to 800 agents, one worker task per one entity folder under one workstream brief. Each worker receives only its own unit.

    Decisions here:2. Small worker or strong model

  3. Judge, from a different model family

    A decision model from a different family checks that each finding is supported by the cited document and concerns this entity.

    Decisions here:3. Evidence check

  4. Reconciler

    A strong reasoning model joins findings across briefs per entity and surfaces issues that span workstreams.

    Decisions here:4. Conflict check5. Retry or stop

  5. Accountable person

    Each workstream lead decides what is reportable and material; the deal lead owns the recommendation to the committee.

    Decisions here:6. Person decides

Checked before anything is accepted

  • Every finding cites the data room document and index number
  • The legal entity named in the document is matched to the structure chart
  • Checklist items with no document found are listed as information gaps
  • Findings raised by two briefs are compared for contradiction before merging

What comes back

  • Findings per entity and workstream with sources
  • Cross-workstream issues
  • Information gaps and document requests per entity
  • Draft report sections for specialist review

What to measure

  • Findings specialists confirm as reportable
  • Cross-workstream issues not raised by any single team
  • Specialist hours per entity

Names of measures only. No result is claimed for this template.

Templates open in the workspace chat with the ask filled in. Nothing runs until you send it.

Get early accessSign in to use

Red-flag customer contracts for change of control and exit rights

For: M&A associate or corporate development manager on a buy-side review

The value of the target sits in its customer contracts, and the data room holds hundreds with order forms and amendments.

Pattern: Map, verify, reduceRuns today6 decisionsDesigned for 4 to 300 agents

Test every claim in the information memorandum against the data room

For: Private equity investment manager or corporate development lead before a binding offer

The seller's memorandum and management presentation make claims about customers, retention, pipeline, capacity and compliance.

Pattern: Adversarial reviewNeeds live models6 decisionsDesigned for 8 to 400 agents

Read each disclosure against the warranty it qualifies

For: Transaction counsel for buyer or seller negotiating the disclosure letter

A disclosure letter arrives late with general and specific disclosures and bundles of documents.

Pattern: Cross-examinationNeeds live models6 decisionsDesigned for 6 to 250 agents