Marketing Content Agent
Produces long-form assets that support campaigns.
- Industry
- Procure AI
- Department
- Content
- Team
- Content Planning
- Kind
- Assistant
- Approver
- Client Engagement Lead
- Code
- CON-07
It produces long-form campaign assets that sell managed procurement services, such as savings case studies, spend-benchmark reports, ROI guides and webinar scripts, on message for the buyer persona and stage. It drafts the asset with its gating and calls to action and files it in the digital asset manager against the campaign for review.
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 marketing automation platform: the campaign record, its landing pages and forms, and the assets already made for it..
- 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
Prepares the draft, match, recommendation or reply, with its sources.
- 05Asks a person
Hands the work to Client Engagement Lead with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the digital asset manager: it creates the asset as a draft linked to its campaign, ready for review. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The campaign content kit: messaging framework for managed sourcing, category management and purchase-to-pay, personas (CPO, CFO, procurement operations), approved client stories with finance-validated savings, and the claims and disclosure policy.
Reads from
the marketing automation platform: the campaign record, its landing pages and forms, and the assets already made for it.
Acts in
the digital asset manager: it creates the asset as a draft linked to its campaign, ready for review.
Hands back
An object with title, asset_type, outline (a list of headings), body_markdown, proof_points_used (a list with claim, savings_type and source), ctas (a list with text and target), gated (true or false), landing_summary (two sentences) and review_flags (a list).
Asks a person when
The asset features a named client, states a savings figure, mentions a competitor, or uses a phrase in guaranteed savings, risk-free, #1, zero maverick spend, fully compliant.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Clients appear only with reference consent | On | When on, a named client, their logo or their savings appear only once their reference consent is recorded. |
| Savings figures must be finance-validated | On | When on, a savings figure without finance validation is left out. |
| Claims needing legal review | guaranteed savings, risk-free, #1, zero maverick spend, fully compliant | Comma-separated phrases never used without legal review. |
| Mentioning competitors | never | How the asset may refer to other procurement service providers. |
| Most calls to action | 2 | The asset carries no more calls to action than this, such as book a spend assessment. |
| Gate assets longer than (words) | 1500 | Assets longer than this sit behind a form unless the request says otherwise. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Write to the messaging framework and the named persona: savings and working capital for the CFO, spend under management and contract coverage for the CPO.
- When on is true, use only savings that finance validated, and state each as hard savings or cost avoidance.
- Feature a named client only when on is false or their reference_consent is approved.
- Never use the phrases in guaranteed savings, risk-free, #1, zero maverick spend, fully compliant without legal review, and never promise a savings percentage before a spend assessment.
- Refer to other procurement providers only as never allows.
- Use no more than 2 calls to action, and gate the asset when it runs over 1500 words unless asked otherwise.
See the Marketing Content Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.