• contact@verticalserve.com
Home / Engineering / Post 114
Engineering Blog · Post #114

Inside the Prioritization Agent: Six P&C Scenarios Showing How InsightUW Ranks Every Submission in the Queue

Once the Intake Triage Agent has classified an inbound as a real submission, a second question has to be answered before an underwriter ever opens it: which one do I work first? A commercial P&C team gets 200–800 submissions a day. Some are marquee renewals from a key broker with inception in six days; some are $2M new-business shots from a walk-up broker effective next quarter. The Prioritization Agent scores every submission across seven weighted business factors, produces a 0–100 number and a HIGH / MEDIUM / LOW band, and orders the queue — deterministically, with a written rationale on every score.


The architecture in one picture

The Prioritization Agent is a deterministic, rule-based scorer — not a black-box model. Seven factors, each with a fixed maximum, sum to a 0–100 score. The LLM's only job is to narrate why the score came out the way it did in plain English; it never sets the number. That split matters: the ranking is fully explainable and reproducible, and the same submission always scores the same way regardless of model drift.

Prioritization Agent architecture — inputs already on the submission (broker + scorecard tier, effective / inception date, LOB + growth plan, requested limit / premium, source new vs renewal, rush flag + SLA, appetite score) feed a 7-factor deterministic scorer (Key Broker 20, Inception Date 20, Growth LOB 15, Premium 15, Renewal 15, Rush 10, Appetite 5) producing priority_score + HIGH / MEDIUM / LOW band; an LLM (Haiku) narrates the rationale without influencing the score; outputs drive the live leaderboard (underwriter queue order) and a UWAuditEntry persisted for audit.
The Prioritization Agent — inputs already on the submission feed a seven-factor deterministic scorer that produces a 0–100 priority_score and a HIGH / MEDIUM / LOW band. The LLM narrates the rationale for clarity but never sets the number; the outputs drive the live leaderboard (the underwriter queue order) and a UWAuditEntry persisted for audit and traceability.
Click the image to open at full resolution.

The seven factors

Every factor is capped, so no single signal can dominate. A submission can only reach HIGH by stacking real business reasons — a key broker and imminent inception and a growth line, or a renewal and a rush event.

#FactorMaxLogic
1Key Broker20Key tier = 20, Preferred = 12, Standard = 0 (from the broker scorecard)
2Inception Date Proximity20≤7d = 20, ≤14d = 16, ≤30d = 12, ≤60d = 6, >60d = 2
3Growth Target LOB15Cyber = 15, Environmental = 12, D&O = 10, E&O = 8, others = 0
4Premium Size15≥$25M = 15, ≥$10M = 12, ≥$5M = 8, ≥$1M = 4, <$1M = 1
5Retention / Renewal15Renewal = 15, New business = 0
6Rush Submission10Rush = 10, Normal = 0
7Appetite Fit5≥80 = 5, ≥60 = 3, >0 = 1, none = 0

The three bands

HIGH (70–100) — the drop-everything work. A key broker with imminent inception on a growth line, a large renewal, or a rush event stacked on real premium. Pinned to the top of the workbench queue; these are what the day should be spent on.

MEDIUM (40–69) — real work with some, but not all, accelerants. A marquee account from a key broker that happens to be a non-growth line; a growth-line account from a preferred broker. It gets worked, in order, after the HIGHs.

LOW (0–39) — standard broker, distant inception, small premium, new business. Not ignored — correctly ranked below the work that actually moves the book today, so nothing gets lost but nothing marginal jumps the line.


Six P&C scenarios

Each card below is a real submission scored by the engine. The factor math is shown exactly as it sums — the number is never a vibe, it's an addition. The "What the UW sees" line is the outcome on the InsightUW workbench and the live leaderboard.

Scenario 1 · Large D&O renewal from a key broker, inception in 12 days HIGH · 78

Submission Stillwater Manufacturing · D&O · $10M limit · renewal · effective 2026-08-01
Broker Marsh & McLennan (key tier) · appetite score 80
Factor math Key broker 20 · inception ≤14d 16 · D&O growth 10 · $10M premium 12 · renewal 15 · rush 0 · appetite ≥80 5  →  78 / HIGH
What UW sees Pinned at the top of the D&O workbench with a green HIGH pill. Rationale reads: "Key broker (Marsh) · D&O growth target · renewal — prioritize for retention · inception in 12 days · strong appetite fit (80)." The Renewal Pull-Forward Agent's cloned prior-term is already attached.
Audit row UWAuditEntry · action=priority_scored · priority=high · priority_score=78 · performed_by=priority_engine

Scenario 2 · Cyber new business with an active-incident rush flag HIGH · 76 · RUSH

Submission Bridgepoint Logistics · Cyber · $8M limit · new business · effective in 6 days
Broker Lockton (key tier) · appetite score 78 · is_rush=true (intake caught "ransomware" — 2h SLA)
Factor math Key broker 20 · inception ≤7d 20 · Cyber growth 15 · $8M premium 8 · new biz 0 · rush 10 · appetite ≥60 3  →  76 / HIGH
What UW sees Top of the Cyber queue with both a HIGH pill and a red RUSH pill; the 2h SLA clock (started by intake at email-landed) is already running. This is the case the whole scoring model exists to catch — a growth line, key broker, imminent, and time-critical, all at once.
Audit row UWAuditEntry · action=priority_scored · priority=high · priority_score=76 · rush=true

Scenario 3 · Large Property account — great, but no accelerant fires MEDIUM · 57

Submission Harborview REIT · Property · $15M TIV · new business · effective in 6 days
Broker Lockton (key tier) · appetite score 82
Factor math Key broker 20 · inception ≤7d 20 · Property (non-growth) 0 · $15M premium 12 · new biz 0 · rush 0 · appetite ≥80 5  →  57 / MEDIUM
What UW sees An amber MEDIUM pill, worked right after the HIGHs. The teaching point: even a marquee Property account from a top broker with imminent inception lands mid-pack when the line isn't a growth target, it isn't a renewal, and there's no rush. The score is honest about the strategic weighting — it isn't just "big premium = top."
Audit row UWAuditEntry · action=priority_scored · priority=medium · priority_score=57

Scenario 4 · A smaller E&O account pulled up by the growth plan MEDIUM · 44

Submission Cedar Peak Advisors · E&O · $5M limit · new business · effective in 10 days
Broker Gallagher (preferred tier) · appetite not yet scored
Factor math Preferred broker 12 · inception ≤14d 16 · E&O growth 8 · $5M premium 8 · new biz 0 · rush 0 · appetite none 0  →  44 / MEDIUM
What UW sees A mid-$5M account that would sit low on premium alone, lifted into MEDIUM because E&O is on the growth plan and inception is close. Rationale: "E&O growth target · inception in 10 days · preferred broker (Gallagher)." Exactly the account a carrier wants surfaced when it's actively trying to grow a line.
Audit row UWAuditEntry · action=priority_scored · priority=medium · priority_score=44

Scenario 5 · Small WC shot from a walk-up broker, effective next quarter LOW · 11

Submission Roadline Freight · Workers' Comp · $2M limit · new business · effective in 55 days
Broker Hub International (standard tier) · appetite score 50
Factor math Standard broker 0 · inception ≤60d 6 · WC (non-growth) 0 · $2M premium 4 · new biz 0 · rush 0 · appetite >0 1  →  11 / LOW
What UW sees A red LOW pill, sitting below the day's real work. It isn't dropped or declined — it's correctly ranked. When the HIGH and MEDIUM queue clears, or as inception gets closer and factor 2 climbs, it rises on its own at the next re-score. Nothing gets lost; nothing marginal jumps the line.
Audit row UWAuditEntry · action=priority_scored · priority=low · priority_score=11

Scenario 6 · A CAT watch re-ranks a Property renewal mid-morning RE-RANK · 52 → 62

Overnight The batch score-all pass ranked Gulfport Terminals (Property renewal, $12M, inception 21 days) at 52 — #38 on the leaderboard.
09:12 trigger A hurricane watch is issued for the Gulf. A CAT rush keyword hits (or Ops toggles is_rush); POST /score-all re-runs.
Re-score Same factors, now with rush +10  →  62 → climbs to #14 within MEDIUM, ahead of every non-time-critical account below it.
What UW sees The leaderboard reshuffles live; the account surfaces near the top with a RUSH pill before the storm develops. The same mechanism runs off the Claims-Driven Priority Signal service — a large reported loss on an insured raises a UWPrioritySignal that pins the account for review, independent of the seven-factor score.
Audit row UWAuditEntry · action=priority_scored · priority_score=62 · reason=rush_rescore · trigger=cat_watch

How the score is computed — and why it's deterministic

The merge is not a model call. Each factor is a lookup against config, the results are summed, and the band is a threshold on the total:

  1. Every factor is a table lookup. Broker tier from the scorecard, inception bucket from the effective date, growth weight from the strategic plan, premium tier from the requested limit. No factor is subjective, so two underwriters — or two re-runs a week apart — get the identical number.
  2. The sum is the score; the band is a threshold. 70+ is HIGH, 40–69 MEDIUM, below 40 LOW. There's no rounding away of the reasoning — the priority_rationale JSON stores every factor's contribution so the workbench can render the full breakdown, not just the total.
  3. The LLM narrates, it does not decide. Claude Haiku turns the factor array into the one-line human rationale ("key broker · growth line · imminent inception"). If the model were unavailable, the number and band are unchanged — only the prose sentence would fall back to a templated string.
  4. Re-scoring is cheap and continuous. score-all re-runs across the open book on a cadence and on any material change (rush flag flips, appetite score lands, inception ticks into a closer bucket), so the leaderboard reflects reality, not the state at submission time.

What the agent does — and what it doesn't

Prioritization has a deliberately narrow job: rank the queue. It consumes signals other agents produce and it never makes an underwriting call.

The agent doesThe agent does NOT
Score every submission 0–100 across seven business factorsDecide appetite fit — it only reads the appetite score (that's the Appetite model)
Assign a HIGH / MEDIUM / LOW band and order the leaderboardJudge submission readiness — that's the Quality Scoring Agent's 7 dimensions
Re-score on material change and on a batch cadenceExtract or validate fields — that's the Document Extraction Agent
Write the factor-by-factor rationale and audit rowRun sanctions / capacity / BOR checks — that's the Clearance Agent
Honor the rush flag and inception proximity in real timeDetect rush at intake — the Intake Triage Agent sets is_rush; this agent consumes it
Surface claims-driven priority signals on the leaderboardDecide to decline — that's the Auto-Declination Agent

Priority is one of three scores

Prioritization answers "is this important?" — but the workbench shows it alongside two sibling scores so the underwriter has the full picture before opening a submission. Priority tells you what to work; quality tells you whether it's ready to work; appetite tells you whether it fits.

ScoreQuestionSignals
Priority (0–100)Is it important — work it now?Broker tier, inception proximity, growth LOB, premium, renewal, rush, appetite fit
Quality (0–100)Is it ready — can I actually work it?Document + data completeness, clearance status, classification, appetite alignment, freshness, broker responsiveness
Appetite (0–100)Does it fit — should we even want it?LOB fit, industry class, limit vs capacity, territory, loss history

A submission that's HIGH priority but LOW quality tells the underwriter something specific: this matters, but chase the missing docs before you spend time on it. That's the combination the three-score model exists to make visible.


Tunables a carrier owns

Every weight, tier, and threshold the agent uses is meant to be admin-owned per tenant — the score encodes the carrier's strategy, and strategy changes without an engineering release:

  • Broker tiers — which brokers are key vs preferred vs standard (reference data on the scorecard)
  • Growth-target LOBs and their weights — this quarter's strategic plan (Cyber 15, Environmental 12, D&O 10, E&O 8 by default)
  • Inception-proximity thresholds — the 7 / 14 / 30 / 60-day buckets
  • Premium tiers — the $1M / $5M / $10M / $25M breakpoints
  • Band cutoffs — where HIGH / MEDIUM / LOW split (70 / 40 default)
  • Rush weight — how hard a rush event pulls a submission up
  • Re-score cadence — how often score-all sweeps the open book
  • Claims-signal thresholds — what loss activity raises a priority signal on the leaderboard

Why this matters for P&C

Without a scoring engine, queue order is whatever's on top of the inbox — newest first, or loudest broker first. Rush submissions sit until someone opens them; growth-line accounts the carrier is actively trying to win get the same attention as a $1M walk-up; and no one can explain why one submission got worked before another.

OutcomeInbox-order triageInsightUW Prioritization Agent
Queue orderNewest-first, or whoever emails mostRanked by seven weighted business factors
Rush / CAT submissionsNoticed when someone opens the emailPulled to the top on the rush flag, re-scored live
Growth-line focusInvisible — depends on the UW remembering the planEncoded as a factor weight; growth LOBs rise automatically
Renewal retentionEasy to miss under new-business volume+15 renewal factor keeps in-force business front of queue
Explainability"I just worked it in the order it came"Factor-by-factor rationale + audit row on every score
ConsistencyVaries by underwriter and by dayDeterministic — same inputs always produce the same rank

What's Next

This post covered the Prioritization Agent and its place in the three-score model. Subsequent posts will go deeper on:

  • The Quality Scoring Agent — the seven readiness dimensions, how document and data completeness are measured against the missing-info tracker, and how quality gates the work before priority sends it to the top
  • The Appetite model — LOB fit, limit-vs-capacity, territory, and loss-history scoring, and how appetite feeds both priority and the auto-declination path
  • The Claims-Driven Priority Signal service — how loss activity on an in-force insured raises a leaderboard signal independent of the seven-factor score

Want to see the Prioritization Agent rank your actual open book — with the factor-by-factor rationale on every submission and a live re-score when a rush event fires — in a 45-minute working session? Request a demo.

See InsightUW run on your data

A 45-minute working session with your open book and your LOBs.

Request a demo