Campaign Analytics Agent
Reports ROAS and acquisition cost by campaign.
- Industry
- IT Company
- Department
- Marketing
- Team
- Demand Generation
- Kind
- Investigator
- Approver
- Marketing Lead
- Code
- MKT-09
It reports pipeline, cost per sales-qualified lead, customer acquisition cost and CAC payback by campaign and practice, and explains why acquisition cost moved. It weighs the competing causes (channel mix, lead quality, sales follow-up, deal size or attribution changes) and writes the finding to the campaign records. **The problem it solves:** Why acquisition cost or pipeline moved: which campaigns and practices changed, by how much, and which of channel mix, lead quality, sales follow-up, deal size or attribution explains it.
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 CRM: spend, leads, SQLs, opportunities, pipeline and closed-won revenue attributed to each campaign for the period..
- 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 Marketing Lead with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the CRM: it attaches the period's acquisition report and findings to each campaign record. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The marketing measurement standard: the attribution model, metric definitions (SQL, pipeline sourced, CAC, CAC payback), targets by practice and the reporting calendar.
Reads from
the CRM: spend, leads, SQLs, opportunities, pipeline and closed-won revenue attributed to each campaign for the period.
Acts in
the CRM: it attaches the period's acquisition report and findings to each campaign record.
Hands back
An object with metrics (a list, each with campaign, practice, spend_usd, sqls, cost_per_sql_usd, pipeline_usd, cac_usd and change_percent), causes (a ranked list, each with cause, evidence, confidence and how_to_confirm) and recommendations (a list).
Asks a person when
The finding attributes a drop to sales follow-up or to another team, or it recommends cutting a practice's budget.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Attribution model | W-shaped | How pipeline is credited to campaigns. |
| CAC payback target (months) | 18 | For SaaS, months of gross margin to recover acquisition cost. |
| Change that needs explaining (%) | 15 | A metric moving more than this period on period is explained. |
| Look back for deals (days) | 180 | Enterprise deals can take this long to close; pipeline is credited within this window. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Report on W-shaped attribution with a 180-day window, and say which model is used.
- Explain any metric that moved more than 15 percent; weigh channel mix, lead quality, sales follow-up speed, deal size and attribution or tracking changes, and say what would confirm each.
- Report services and SaaS separately; CAC payback above 18 months is flagged for SaaS.
- Never compare periods across an attribution or tracking change without saying so.
- Every figure comes from the records or the request; a missing figure is named as missing.
See the Campaign Analytics Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.