CONTEXT(CLONE)
Sign in

Map one exposure across the whole wording portfolio

For: Wordings manager or portfolio underwriter responsible for product wordings

Pattern: Map, verify, reduceNeeds scaleDesigned for 40 to 800 agents
Get early accessSign in to use

The pain today

When a new exposure appears, nobody knows which wordings, endorsements and legacy versions cover it, exclude it or say nothing. Finding out means reading every wording by hand.

The ask

“I attached all our policy wordings, endorsements and legacy versions. For cyber-related loss, tell me for each wording whether it is expressly covered, expressly excluded or silent, quote the clause, and list wordings where an endorsement changes the answer.”

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

  • Policy wordings, all current versions
  • Endorsement library
  • Legacy wordings still in force
  • Definition of the exposure in plain words

The unit of work

One worker task per one wording or endorsement version.

Why a swarm fits

Each wording is read on its own against one question. Hundreds of versions are independent, and the only shared context is the definition of the exposure.

Not for

Predicting how a court would read a clause. It reports what the text says and where it is silent.

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

    Is this document a policy wording or endorsement for a class of business that could respond to the exposure as defined?

    Sees only: The document's title page, class of business and table of contents, and the exposure definition

    Why: Keeps unrelated classes out of the map without risking a missed wording.

    • Yes: 0.60 or higherthenAccept
    • Unsure: 0.30 up to 0.60thenAccept
    • No: below 0.30thenSkip this unit

  2. Before workers, before a task runs

    Small worker or strong modelYes or no, with a probability

    Before a task runs

    Is this a standard wording with a conventional layout of insuring clauses, definitions and exclusions, rather than a bespoke manuscript wording?

    Sees only: The wording's table of contents and first insuring clause

    Why: Bespoke wordings hide cover in unusual places and deserve the stronger reader.

    • Yes: 0.60 or higherthenAccept
    • Unsure: 0.40 up to 0.60thenEscalate to a strong model
    • No: below 0.40thenEscalate to a strong model

  3. After workers, the judge checks

    Evidence checkA choice among options

    After a worker answers

    What does the quoted clause, read with the definitions it uses, state about loss arising from the defined exposure?

    Sees only: The exposure definition, one quoted clause and the definitions it relies on

    Why: Forces a four-way reading so ambiguity is recorded rather than rounded to covered or excluded.

    • Expressly coversthenAccept
    • Expressly excludesthenAccept
    • Does not address itthenReject and retry
    • AmbiguousthenMark unresolved

  4. Evidence checkYes or no, with a probability

    After a worker answers

    Do the insuring clauses, exclusions, definitions and conditions shown contain no language that addresses the defined exposure?

    Sees only: The exposure definition and every clause the worker searched, by heading

    Why: Silent cover is the costly finding, so a silent verdict must survive a second look.

    • Yes: 0.85 or higherthenAccept
    • Unsure: 0.50 up to 0.85thenEscalate to a strong model
    • No: below 0.50thenReject and retry

  5. Reconciler, while merging

    Conflict checkYes or no, with a probability

    While reconciling

    Does this endorsement change the base wording's position on the exposure from covered to excluded, or the reverse?

    Sees only: The base wording's accepted clause and one endorsement that amends it

    Why: The map must show the wording as sold, not only as first drafted.

    • Yes: 0.70 or higherthenMark unresolved
    • Unsure: 0.30 up to 0.70thenEscalate to a strong model
    • No: below 0.30thenAccept

  6. Accountable person, before anything is settled

    Person decidesYes or no, with a probability

    Before anything is reported as settled

    Does this map entry state or imply a position on whether policyholders under this wording have cover for the exposure?

    Sees only: One map entry with its quoted clauses

    Why: What silence or ambiguity means for policyholders is for the wordings manager and coverage counsel.

    Accountable: The wordings manager and coverage counsel decide what silence means and which wordings are revised.

    • Yes: 0.20 or higherthenAsk a person
    • Unsure: 0.05 up to 0.20thenAsk a person
    • No: below 0.05thenAccept

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 turns the exposure into a fixed set of questions and links endorsements to base wordings.

    Decisions here:1. Scope check

  2. Workers

    Small fast workers from an open-weight family, one per wording version, quoting insuring clauses, exclusions and definitions.

    Designed for 40 to 800 agents, one worker task per one wording or endorsement version. 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 the quoted clause supports covered, excluded or silent.

    Decisions here:3. Evidence check4. Evidence check

  4. Reconciler

    A strong reasoning model builds the portfolio map and shows where an endorsement reverses the base wording.

    Decisions here:5. Conflict check

  5. Accountable person

    The wordings manager and coverage counsel decide what silence means and which wordings are revised.

    Decisions here:6. Person decides

Checked before anything is accepted

  • Covered and excluded findings must quote the operative clause and any definition it uses
  • Silent findings are rechecked across the whole wording, not only the exclusions section
  • Endorsements are applied to the base wording version they actually amend
  • Ambiguous clauses are reported as ambiguous, not forced into a class

What comes back

  • Portfolio map: covered, excluded, silent or ambiguous per wording
  • Quoted clauses behind each entry
  • Wordings where an endorsement changes the answer
  • Ambiguous clauses for coverage counsel

What to measure

  • Share of entries the wordings manager confirms
  • Wordings later found to be misclassified
  • Reviewer hours per product line
  • Cost per wording version read

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

More in Insurance and claims

Prepare a coverage brief with clauses for and against

For: Claims handler or coverage specialist preparing a position on a complex commercial loss

The schedule, wording, endorsements and loss report each run long.

Pattern: Cross-examinationRuns today7 decisionsDesigned for 4 to 32 agents

Watch wording changes and recheck only what depends on them

For: Product governance lead or wordings manager at an insurer or managing agent

A clause edit in a base wording silently affects endorsements, customer summaries, claims guidance and broker templates built on it.

Pattern: WatchtowerNeeds a connector5 decisionsDesigned for 20 to 500 agents

Test a fraud pattern hypothesis before it is acted on

For: Special investigations lead examining a suspected organised pattern across referred files

A suspected pattern, such as the same repairer invoices across many files, is persuasive once stated.

Pattern: Adversarial reviewNeeds live models6 decisionsDesigned for 10 to 200 agents