Content Performance Agent
Reports engagement and conversion by piece.
- Industry
- Procure AI
- Department
- Content
- Team
- Content Planning
- Kind
- Investigator
- Approver
- Content Lead
- Code
- CON-12
It reports engagement and conversion by piece, such as spend-assessment requests, webinar sign-ups and requisitioner guide usage in the client portal, and explains why pieces over- or under-perform. It ranks the likely causes for each piece off target, recommends the fix and updates the content performance report. **The problem it solves:** Why the pieces named performed as they did: the metrics against their benchmark or earlier period, when the change started, and what changed in publishing, distribution, search, the client portal or tracking around then.
How it works
6 steps, and a person signs off before step 6.
- 01Looks it up
Finds the record the request is about in the analytics warehouse: page views, engaged time, traffic sources, search rankings, portal guide views, service-desk ticket volumes and conversion events for the pieces and period named..
- 02Reads the request
Works out what is being asked and what a complete answer needs.
- 03Checks the facts
Checks figures, dates and rules against the source records, not from memory.
- 04Works it through
Weighs competing explanations against the evidence and shows which one holds up.
- 05Asks a person
Hands the work to Content Lead with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the content reporting dashboard: 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, the attribution model for spend-assessment requests and pipeline, targets by format and channel, how portal guide usage links to fewer service-desk tickets, and known tracking issues.
Reads from
the analytics warehouse: page views, engaged time, traffic sources, search rankings, portal guide views, service-desk ticket volumes and conversion events for the pieces and period named.
Acts in
the content reporting dashboard: 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, avg_engaged_seconds, conversions, conversion_rate, vs_benchmark_percent and verdict (out_performing, on_target, under_performing or too_early)), causes (a list for each piece off target, each with piece_id, 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 pipeline or signed services revenue to content, recommends retiring a requisitioner or supplier guide, or finds a tracking fault that affects other teams' reports.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Under-performing below (% of benchmark) | 70 | A piece at or below this share of its format benchmark is under-performing. |
| Out-performing above (% of benchmark) | 130 | A piece at or above this share is out-performing and its causes are worth copying. |
| Fewest sessions for a verdict | 300 | A piece with fewer sessions is reported as too early to tell; B2B procurement audiences are small. |
| Attribution model | position based | How spend-assessment requests and pipeline are credited to pieces. |
| Events that count as conversions | spend_assessment_request, webinar_signup, demo_request | Comma-separated events from the analytics warehouse. |
| Drop that points to tracking first (%) | 30 | A drop this large starting on one day across many pieces is treated as 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 on a piece with fewer than 300 sessions; report it as too early to tell.
- A piece at or below 70 percent of its format benchmark is under-performing, and at or above 130 percent is out-performing.
- Count as conversions only spend_assessment_request, webinar_signup, demo_request, credited by position based.
- 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.
- For client portal guides, compare guide views with the matching service-desk ticket volume before claiming deflection.
- Rank causes by evidence and say what would confirm each; never state pipeline or revenue figures the records do not give.
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.