ZeroTwo for marketers
Prompts for marketers
Campaign packs, positioning, briefs, and the monthly report that has to explain what moved and why. These prompts cover the production work so the thinking gets the time.
- Claims traced to a source
- Brand and tone rules reapplied
- You approve before anything ships
Prompts for marketers
How do I write a campaign brief?
Name the audience, the single message, the proof, and what success would look like before any asset exists.
- Product_notes.docx
How do I build a full campaign pack from one brief?
Generate every asset from the same brief so the message does not drift between channels.
- Campaign_brief.docx
How do I test whether my positioning is actually different?
Put your claims beside competitors' and see which ones only you could make.
- Positioning.docx
How do I turn a brief into a first draft that is on brand?
Attach the brand rules and prior work so the draft starts inside your voice, not a generic one.
- Brand_voice.pdf
- Example_post.docx
How do I repurpose one piece across channels?
Rewrite for each channel's reading behaviour rather than truncating the same text.
- Source_article.docx
How do I check my copy is not making claims we cannot support?
Have every factual and comparative claim listed with the evidence behind it, before legal or a customer finds them.
- Draft_copy.docx
How do I research a market without weeks of reading?
Get a structured brief with sources attached, and a clear list of what the evidence cannot answer.
How do I find the language customers actually use?
Pull verbatim phrasing out of real inputs instead of paraphrasing it into marketing voice.
- Voice_of_customer.csv
How do I run a competitor teardown quickly?
Compare on the dimensions that decide the deal, not on feature counts.
How do I report on a campaign honestly?
Separate what moved, what you cannot attribute, and what you would do differently.
- Campaign_metrics.xlsx
How do I regenerate the monthly marketing report?
Keep last cycle's format, refresh the numbers, and lead with what changed.
- Last_month.docx
- This_month.xlsx
How do I explain a drop in performance?
Decompose the change before narrating it, and name what the data cannot attribute.
- Period_compare.xlsx
Prompts are starting points. Filenames shown are placeholders — attach your own.
In short
ZeroTwo is an AI workspace for marketers who ship campaigns, content and reporting on a cycle. It drafts against your brief and brand rules, keeps research claims tied to sources, and reports on results without inventing the ones you did not measure.
How a prompt becomes a deliverable
A prompt starts the work; it is not the work. Every card above runs the same four beats, and stops in the same place.
Inputs, as they are
Transcripts, exports, the client's own documents, last cycle's deck. No re-typing or restructuring first.
A plan you can adjust
ZeroTwo shows what it intends to do. You set the source boundaries before it starts.
Assembly, with sources kept
Claims stay tied to the line they came from. Gaps and conflicts are surfaced, not smoothed over.
A first-review artifact
Complete enough to review against a written standard. Not a signed deliverable.
ZeroTwo stops at the judgment
The approval boundary is a product feature, not a disclaimer. ZeroTwo does the assembly. You keep the part the client is actually paying for.
ZeroTwo does
- Gather and organise the inputs
- Extract, theme and cross-reference
- Keep every claim tied to its source
- Surface gaps and contradictions
- Format to your conventions
You do
- Set the source boundaries
- Resolve the contradictions
- Verify the arithmetic
- Write the recommendation
- Sign it and send it
Against what you are doing now
| Approach | Where it works | Where it breaks on a deliverable | ZeroTwo's difference |
|---|---|---|---|
| General chat assistant | Fast answers, flexible, already paid for | Stops at a draft. marketing teams own the path across files, slides and sheets, and re-explain the project every session. | Context and sources persist across the whole engagement |
| Specialist point tool | Deep fit for one format or step | Work fragments across the rest of the process; each tool holds a different half of the context. | One accountable path from inputs to artifact |
| Doing it by hand | Trusted method, clear accountability | Senior time goes to production and cleanup; recurring work restarts from memory each cycle. | The second run reuses the first run's method |
| A contractor | Human judgment, flexible capacity | Lead time and context transfer exceed the window when the deadline is days away. | Available at the moment the brief lands |
Questions marketers ask first
Will the output sound like our brand?
Attach your tone-of-voice rules and a couple of strong examples and they are used as the standard, then saved as project context so later drafts start there. It is a first draft to edit, not something to publish unread.
Will it invent statistics?
The claim-checking prompts exist because that is the failure that matters here. Ask for every factual and comparative claim to be listed with the evidence behind it, and supply the facts yourself rather than accepting invented ones.
Which models can I use?
You can run the same prompt against 60+ models in one workspace and pick per task — a long research build and a quick subject-line rewrite do not need the same model.
Can it use our existing research and brand documents?
Yes. Attach briefs, prior campaigns, brand rules and research and they become the context the work is produced from, rather than something you re-explain each session.
Does this replace a marketer?
It removes the production and reformatting. Positioning, judgment about what is true, and the decision to ship stay with you.
Takeaways
- One brief drives the whole campaign pack, so the message does not drift between channels.
- Every factual and comparative claim can be listed with the evidence behind it before anything ships.
- Brand rules and prior work are reused as context rather than re-explained each session.
- Reporting separates what moved from what the measurement cannot attribute.
Where this runs
The surfaces marketers use most once a prompt is running.
Run the prompt against 60+ models in one thread
Work agentHand off a multi-step task and watch the plan
AI workspaceProjects, files and context that persist between runs
Document analysisAsk questions across a folder of PDFs and exports
Agent platformApproval gates, tool access and model choice
Data analysisTurn a dataset into a checked, footnoted exhibit
ZeroTwo for
Cited briefs, synthesis and proposals
AnalystsData checks, exhibits and reporting
Fractional executivesProposals, SOWs and monthly reports
SalesAccount research and pitch responses
Start with the last deliverable that ran late.
Open a prompt above, run it on inputs you are comfortable sharing, and judge it on the artifact.