Sign in
Lead & Account Scoring

ICP & Persona Definition Agent

ai

Builds a defensible, origin-tagged Ideal Customer Profile and refreshed buyer personas by contrasting closed-won against closed-lost accounts, producing a versioned ICP with traceable attribute origins and a diff against the prior version.

Sales / Revenue OperationsCompetitive / Product MarketingSales Leadership
Versioned
ICP with traceable attribute origins
8x
Faster ICP refresh vs. manual analysis
Win/Loss
Grounded in closed-won vs. closed-lost contrast
One refresh, end to end

New fiscal year. New ICP ready.

See the ICP agent take a fiscal-year refresh from annual planning to a versioned ICP with a diff.

Refresh ICP-0412

Fiscal-year ICP and persona refresh

  • AI
  • 8x faster refresh
  1. Intake
  2. Organize
  3. Evaluate
  4. Deliver

01 · Intake

Refresh requested

Annual planning triggers a new fiscal-year ICP

New case

Packet open
Requester
Sales / Revenue Operations
Trigger
Annual planning
Request
Refresh ICP and buyer personas · For the new fiscal year
Baseline
Current ICP and personas
Case packet · 3 sourcesComplete

Incoming

  • CRMSalesforce, HubSpot accountsReceived
  • Win/Loss & Opportunity DataClosed-won and closed-lost opportunitiesReceived
  • ICP & Persona RecordsCurrent ICP and buyer personasReceived

02 · Organize

Cohorts segmented

Closed-won vs. closed-lost split by firmographics

Pulled together

Cohorts built
  • Accounts and opportunities pulledFrom the CRM, joined to win/loss outcomes
  • Won and lost cohorts builtSegment, size, region and environment
  • Prior ICP loaded as baselineCurrent version held for the diff

Matched record

Record
Current ICP
Status
Prior version
Personas
Loaded for refresh
Compared against
Closed-won vs. closed-lost cohorts

03 · Evaluate

Attributes tagged

Separating attributes found and origin-tagged

Checks applied

Origins tagged
  • EHR environmentWeak signal is now a strong win predictorWin/loss cohorts
  • Company-size band500 to 2,000 employees wins disproportionatelyWin/loss cohorts
  • High-growth attributeWeakened since the last version, downgradedPrior ICP
Deciding finding

Data contradicts a held belief

Win/loss data shows a higher close rate in enterprise, while the mid-market focus is a founder hypothesis.

Attribute origins

Enterprise close rate
Derived from data
Mid-market focus
Founder hypothesis
EHR environment
Derived from win/loss data

04 · Deliver

Version and diff produced

Diff flags the enterprise conflict for review

Version drafted

New ICP version with diff

Each attribute traces to win/loss cohorts, a founder hypothesis or an external source, and the conflict is flagged.

Strengthened
EHR environment
Tightened
500 to 2,000 employees
Downgraded
High-growth

Conflict flagged

Enterprise vs. mid-market

Not silently resolved

Next step

Sales leadership

Approve the version

Audit trail

  1. Accounts and opportunities pulled09:00
  2. Won and lost cohorts segmented09:04
  3. Attributes origin-tagged09:09
  4. Versioned ICP and diff producedConflict flagged09:12

8x faster ICP refresh vs. manual analysis

Illustrative case · sample data

Use Case 1

ICP & Persona Refresh

Trigger: Annual planning or a strategy shift

1.Retrieve accounts, opportunities, current ICP, and personas
2.Segment closed-won vs. closed-lost by firmographics
3.Identify attributes that separate wins from losses
4.Origin-tag each attribute by evidence source
5.Generate a versioned ICP record
6.Produce a human-readable diff against the prior version
7.Surface conflicts between data and assumptions
✓

A defensible, versioned ICP that downstream agents consume—with every attribute traceable to its source.

Use Case 2

Assumption-vs-Data Reconciliation

Trigger: Win/loss data contradicts a held belief

1.Label the data-derived finding and the hypothesis separately
2.Present both without overriding strategy
3.Flag the tension in the diff for review
4.Avoid silently resolving the conflict
5.Hold the version pending leadership decision
✓

Leadership sees where evidence and assumption diverge before committing the ICP.

Integrations

CRM (Salesforce, HubSpot)
ICP & Persona Records
Win/Loss & Opportunity Data
External Firmographic Data
Google Workspace (Sheets, Drive)

Industries

all

Built in Actava.ai

See it in action

A conversation that moves the work forward.

An agent at work

Illustrative example

Refresh our ICP for the new fiscal year.

ICP & Persona Definition Agent

I compare closed-won and closed-lost accounts to find the attributes that separate winners from losers, then tag where each came from. The output is a versioned ICP with a readable diff.

Inputs pulled

  • Accounts

    Closed-won and closed-lost, split by segment, size, region, environment

  • Opportunities

    Outcomes used to find what separates winners from losers

  • Current ICP and personas

    Baseline for the diff and contradiction checks

Example complete

1 / 3

Sample scenarios. Actions and outputs are illustrative.