AI for insights and analytics
An office retains 92 of 100 clients and 79 percent of the income, because the ones it lost were large and unremarketed. AI analytics reads the policy, renewal and claims files, watches the notice window, and answers the office head's question: which renewals are at risk, and what has been done about them.
These are the questions brokers ask. Each one maps to a measure our tools compute from your files. The AI model chooses the measure and explains the result; the arithmetic is done by our code, and every total is checked.
| The question | The measure behind it | What comes back |
|---|---|---|
| Which renewals are at risk in the next ninety days? | Renewal watch | Clients inside the notice window with no remarketing logged, a slow claim, or a premium jump, by income. |
| What is our retention by income, not just by count? | Retention, count and income | Clients retained over due, and income retained over due, by office and executive, with the lost accounts listed. |
| Which clients hold fewer lines than their sector norm? | Lines held against sector norm | Lines per client against the median for its sector and size, with the gap valued. |
| How much of each client's placement do we hold? | Placement share per client | Lines placed by us over lines the client holds, where known, with the gap. |
| Where has remarketing not happened? | Remarketing activity | Renewals due with no market approach logged inside the window, by executive. |
| Are we over-dependent on one carrier in a line? | Carrier concentration per line | Premium share by carrier per line, with the lines above the threshold. |
Every figure below was computed by a tool from the rows and checked before it was shown. The lines sum; the percentages match; each line opens to the rows that make it.
How much renewal income is at risk in the next ninety days?
Renewal income at risk in the next ninety days is $2.6m across 3 offices, counting clients with no remarketing logged, a claim over ninety days to settle, or a premium rise above ten percent. Central office holds $1.3m, 50% of it.
| Central office | $1.3m | 50% of the total |
| Docklands office | $800k | 31% of the total |
| Western office | $500k | 19% of the total |
| The 3 lines sum to | $2.6m | 0 unexplained |
Which Central clients?
3 clients hold $970k of the $1.3m at risk at the Central office, 75% of it. Two have a claim still open past ninety days and none has a market approach logged.
| Bellway Haulage | $420k | claim open 128 days; no remarketing |
| Fenwick Retail Group | $360k | premium up 14%; no remarketing |
| Orchard Care Homes | $190k | claim open 96 days; second largest client |
| These 3 are | $970k | 75% of Central office |
What does the office do this week?
Chase the two open claims with the carriers and start remarketing all three before the notice date. The renewal watch is reviewed weekly until each is either retained or lost with a reason.
| Account executives | Log a market approach on all three; chase the open claims | This week |
| Office head | Review the renewal watch every Monday | Weekly |
| Sales director | Report income retention beside count retention | Monthly |
Each measure has one formula, one source and one meaning. They are computed per account executive and office and in total, and every one carries an identity that must hold before it is shown.
| Measure | Formula | From | What it tells you |
|---|---|---|---|
| Retention, count and income | Clients renewed ÷ clients due; prior income of renewed clients ÷ prior income due | Policy ledger | Whether the clients leaving are the large ones |
| Renewal watch | Policies inside the notice window with no remarketing or review activity logged, by income | Policy ledger; activity log | Renewals drifting toward expiry |
| Placement share per client | Premium placed by the broker ÷ estimated total programme premium | Placement ledger; client schedule; estimates by source | Lines placed elsewhere |
| Lines held against sector norm | Lines placed ÷ median lines for clients of the sector and size | Placement ledger; client master | Clients thinner than their peers |
| New business against lost | New income won − income lost, per office and executive | Policy ledger | Whether the book is growing or being replaced |
| Carrier concentration per line | Largest carrier share of premium, per line; top three share | Placement ledger | Dependence on one market's appetite |
| Remarketing activity | Renewals with alternative quotes obtained ÷ renewals over a stated income | Activity log; quote records | Whether large renewals are tested before the client tests them |
| Claims experience against retention | Retention for clients with a claim in the year, by outcome and handling time, against those without | Claims file; policy ledger | Whether claims service is keeping or losing clients |
| Income per client after servicing | Commission and fees − servicing cost by activity | Ledger; time or activity records | Clients who cost more than they earn |
| Book mix per executive | New income ÷ total income in the book; clients per executive | Policy ledger | Books that stopped growing |
Each measure is worked through, with the export it comes from and what to drop, in Sales KPIs for commercial insurance brokers.
From your question and the measures declared for insurance brokers, the model picks the one that answers it, and the period and comparison the question implies.
Deterministic code reads the rows, computes the measure, and checks the identities below. The same question on the same data gives the same answer, every time.
The AI model writes the sentence around the result, naming the account executive or account behind it. It states no figure that is not in the result, and every figure links to its rows.
| Retention | Due = renewed + renewed late + lost + pending |
| Placement | Client premium by line sums to the placement ledger; carrier shares sum to 100 percent per line |
| New against lost | Opening income + new − lost ± rate and exposure change = closing income |
| Book mix | Every client has one executive |
The exports brokers already produce. Column names are mapped once and the mapping is reused. A file is the way in; scheduled delivery and connections to your systems come with the plan, and every source is listed here.
An answer is a list with an owner and a cadence, or it is a chart nobody works.
| Measures | Owner | Cadence |
|---|---|---|
| Renewal watch; remarketing activity | Account executives; office head | Weekly |
| Retention; new against lost; book mix | Office head; sales director | Monthly |
| Placement share; lines against norm | Account executives; sales director | Quarterly |
| Carrier concentration; claims and retention; income after servicing | Placement head; claims head; finance | Quarterly |
Because losing eight clients of a hundred sounds fine until they include the second and fifth largest. Count retention was 92 percent and income retention 79. The tool reports both, and the renewal watch ranks by income at risk, so the office works on the accounts that decide the year.
The ones in your files: no remarketing logged inside the notice window, a claim open longer than your threshold, a premium change above your threshold, and contact recency. Each is a fact from a file, listed against the client. There is no model score; the thresholds are yours and visible.
Yes, from the placement file. Premium share by carrier is computed per line and per office, and lines where one carrier holds more than the share you set are flagged. The figure is a fact about the book; what to do about it is the placement team's call.
The policy or placement file with client, line, carrier, premium and renewal date; the claims file; and the activity log. Income by client turns placements into retention by income. Each file is matched to your columns once and reused.
Renewal calendar · Lost at renewal · Carrier concentration · Claims band · Norm penetration · Renewal rate
Asset managers · Commercial banking · Compliance · Construction and building materials · Consulting and advisory · Customer service · Distributors · Education · Finance and FP&A teams · Financial services · FMCG and CPG brands · Foodservice distributors · Freight brokers and 3PLs · Healthcare and med-tech · Hospitality · Industrial distributors · Industrial manufacturers · Investment banking · Law firms · Oil and gas services · Pharma · Procurement · Retail banking · SaaS · Sales teams · Shipping and logistics · Sports · Supply chain · Tax and accounting · Telecoms and connectivity · Trading · Wealth managers
Bring a few thousand rows. The data map opens next, every column mapped once, and the first question is answered in minutes. Free, in your browser, no account.