UAE · ENBook a demo
Insure AIContentInvestigator

Content Performance Agent

Reports engagement and conversion by piece.

Content Performance AgentContent Planning
Industry
Insure AI
Department
Content
Team
Content Planning
Kind
Investigator
Approver
Head of Content
Code
CON-12

It reports engagement and conversion by piece, such as quote starts, quote-to-bind and self-service claim starts, and explains why pieces over- or under-perform, separating search, channel, season, wording and tracking causes. It recommends a fix for each piece off target and updates the content performance report. **The problem it solves:** Why the pieces named performed as they did: quote starts, binds or FNOL starts against benchmark or the same season, when the change started, and what changed in wording, distribution, search or tracking.

How it works

6 steps, and a person signs off before step 6.

  1. 01Looks it up

    Finds the record the request is about in the policy administration system: the quotes started and policies bound with their content source for the period..

  2. 02Reads the request

    Works out what is being asked and what a complete answer needs.

  3. 03Checks the facts

    Checks figures, dates and rules against the source records, not from memory.

  4. 04Works it through

    Weighs competing explanations against the evidence and shows which one holds up.

  5. 05Asks a person

    Hands the work to Head of Content with its reasoning before anything goes out.

  6. 06Acts

    Once approved, it acts in the document and correspondence system: it updates the content performance report with the period's figures, verdicts and causes. and records what was done.

What it works with

Your knowledge, your systems, your people.

Knows

The content measurement framework: metric definitions (quote starts, binds, online FNOL starts, deflected service calls), the attribution model, benchmarks by format and line, and known tracking issues.

Reads from

the policy administration system: the quotes started and policies bound with their content source for the period.

Acts in

the document and correspondence system: it updates the content performance report with the period's figures, verdicts and causes.

Hands back

An object with pieces (a list, each with piece_id, title, views, quote_starts, binds, fnol_starts, conversion_rate, vs_benchmark_percent and verdict), causes (a list per piece off target, each with cause, evidence, confidence and how_to_confirm) and recommendations (a list, each with piece_id, fix and expected_effect).

Asks a person when

The report credits premium or binds to content, recommends retiring a piece that claims or service teams link to, or finds a tracking fault affecting quote or FNOL reporting.

ApproverHead of Content

Settings

Your limits, set by your managers.

SettingDefaultWhat it controls
Under-performing below (% of benchmark)70At or below this share of its benchmark a piece is under-performing.
Out-performing above (% of benchmark)130At or above this share its causes are worth copying.
Fewest sessions for a verdict500Fewer sessions is too early to tell.
Attribution modellast touchHow quote starts and binds are credited.
Events that count as conversionsquote_start, bind, fnol_startComma-separated events.
Drop that points to tracking first (%)30A same-day drop this large across many pieces is a tracking or site change until shown otherwise.

Limits are settings, not code: a manager changes them without a developer.

Rules it always follows

  • Give no verdict below 500 sessions.
  • A piece at or below 70 percent of benchmark is under-performing, at or above 130 percent out-performing.
  • Count only quote_start, bind, fnol_start, credited by last touch.
  • Check tracking first: a drop of 30 percent or more starting on one day across many pieces is a tracking or site change until shown otherwise.
  • Weigh seasonality: compare storm, travel and renewal-season pieces with the same season last year before calling a drop.
  • Never state gross written premium credited to content that the bind records do not show.

See the Content Performance Agent agent on your own work.

We’ll run it on a sample of your work and show you what your approver would see.

Content Performance Agent · Insure AI | Basinwright Industries