Sign in
Set up for Pharma

AI for insights and analytics

AI analytics for pharma

A territory reports 80 percent reach over ten targets, but two are blocked and fourteen of twenty-eight calls went to accounts that cannot prescribe. AI analytics reads the call, access and prescription files, and answers the district manager: which calls could not have worked, and where has an access win not pulled through.

Ask it in your own words

These are the questions pharma commercial teams 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 questionThe measure behind itWhat comes back
What is reach and frequency among accounts that can actually prescribe?Reach and frequency, access-awareReach and frequency over accessible targets only, by territory, beside the unadjusted figures.
How many calls went to blocked accounts?Calls on blocked accountsCalls by territory on accounts with no access, with the accounts and the reps.
Where did an access win not turn into prescriptions?Pull-through after access winPrescriptions after a formulary or access change against the expected curve, by account.
Is the target list current?Target list currencyTargets whose access, address or prescribing status changed since the list was set, by territory.
Which new prescribers activated after the first call?New prescriber activationTargets with a first prescription within the window after first call, by territory.
Which open-access accounts received no call?Share within accessible accountsAccessible targets uncalled in the cycle, by tier, with the potential.

A conversation, with the figures

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 many calls this cycle went to accounts that cannot prescribe?

450 calls this cycle went to blocked or unknown-access accounts across 3 districts, out of 2,900 calls made. Northeast district accounts for 210 of them, 47% of the wasted calls.

Northeast district21047% of the total
Southeast district15033% of the total
Central district9020% of the total
The 3 lines sum to4500 unexplained

Which northeast territories?

3 territories account for 185 of the 210 blocked calls in the Northeast district, 88% of them. In the largest, seven calls went to one blocked account while two open-access tier-one targets received none.

Territory NE-04847 calls on one blocked account; 2 tier-one targets uncalled
Territory NE-0761target list 9 months old
Territory NE-02403 targets changed access mid-cycle
These 3 are18588% of Northeast district

What does the district manager change before next cycle?

Refresh the target lists with current access, move the blocked calls to the uncalled tier-one accounts, and report access-aware reach beside the headline. The same question next cycle shows the shift.

District manager, NortheastRefresh target lists with current access statusBefore next cycle
Reps NE-04 and NE-07Call the uncalled open-access tier-one targetsThis cycle
Commercial operationsReport access-aware reach and frequency by territoryEach cycle
What is reach and frequency among accounts that can actually prescribe?How many calls went to blocked accounts?Where did an access win not turn into prescriptions?Is the target list current?

The measures behind the answers

Each measure has one formula, one source and one meaning. They are computed per territory and rep and in total, and every one carries an identity that must hold before it is shown.

MeasureFormulaFromWhat it tells you
Reach and frequency, access-awareAccessible targets called ÷ accessible targets; calls ÷ accessible targets calledCall log; dated access fileCoverage where a prescription is possible
Calls on blocked accountsCalls made while the account was blocked ÷ all callsCall log; dated access fileEffort that could not convert
Access-weighted territory potentialCategory volume of accounts, weighted by access status, per territoryPrescription data; access fileWhere reps should be
Pull-through after access winChange in share in accounts covered by the win, months 1 to 6, against own prior trendPrescription data; access fileWhether prescribing followed access
Call plan attainment by versionPlanned calls completed ÷ planned, each against the plan version in force on its dateCall log; versioned planAttainment that can be reproduced
Sample to prescription relationshipChange in prescriptions against samples left, per territory, with lagSample log; prescription dataWhat the samples moved
Target list currencyTargets with status reviewed in the cycle ÷ targets; high prescribers not on the listTarget list; prescription dataLists built on last year
New prescriber activationTargets writing a first prescription in the period ÷ targets with none beforePrescription dataWhether calls create prescribers
Share within accessible accountsProduct prescriptions ÷ category prescriptions, in accessible accountsPrescription data; access filePerformance where it could be achieved
Off-plan call rateCalls on accounts not in the plan ÷ calls, with the outcome of those accountsCall log; planReps following judgement the plan lacks, or avoiding the plan

Each measure is worked through, with the export it comes from and what to drop, in Commercial KPIs for pharma sales teams.

What the AI model does, and what our tools do

The AI model chooses the measure

From your question and the measures declared for pharma, the model picks the one that answers it, and the period and comparison the question implies.

Our tools do the arithmetic

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 explains, and cites

The AI model writes the sentence around the result, naming the territory or account behind it. It states no figure that is not in the result, and every figure links to its rows.

The identities that must hold

AccessTargets = open + restricted + blocked + unknown, on any date
CallsCalls = on plan + off plan; on accessible + on blocked + on unknown
PlanEvery call is assessed against exactly one plan version
PrescriptionsAccount prescriptions sum to the territory total in the data source

What it reads

The exports pharma commercial teams 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.

  • Call log
  • Dated access file
  • Prescription data
  • Access file
  • Versioned plan
  • Sample log
  • Target list
  • Plan

Who owns each answer

An answer is a list with an owner and a cadence, or it is a chart nobody works.

MeasuresOwnerCadence
Access-aware reach and frequency; blocked callsDistrict managersEach cycle, weekly within it
Pull-throughCommercial head with market accessMonthly after each win
Attainment by version; off-plan rate; list currencySales force effectivenessEach cycle
Access-weighted potential; share in accessible accountsCommercial headQuarterly, and at realignment

Questions pharma commercial teams ask about AI analytics

What does access-aware mean?

Reach and frequency computed only over accounts that can prescribe, from the access file you provide. A territory at 80 percent reach over ten targets is 71 percent over the seven accessible ones, and the difference is calls that could not have worked. Both figures are shown, and the blocked calls are listed.

Can it measure pull-through?

Yes, when the prescription file and the access change dates are loaded. Prescriptions after an access win are compared with the expected curve you set, by account, and the accounts that have not moved are listed with the calls made since. The tool computes; the commercial head decides whether the field or market access owns the gap.

Is patient or prescriber data safe?

The tool needs prescriber-level call and prescription counts, not patient data. Prescriber identifiers can be replaced with codes before upload on Enterprise, and every file is read where you choose to run it. The model never receives the rows.

What files does a commercial team need?

The call file by rep and account, the target list with tiers, the access file with status and change dates, and prescription data by prescriber and month. Sample records add the sample-to-prescription relationship.

See it on your data

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.