CampaignPacks
Your AI marketing agency, review-first.
- Platform
- Web
- Pricing
- Free during early access
CampaignPacks
Marketing
Overview
- Status
- Early access
- Category
- Marketing
- Platform
- Web
- Version
- 0.1.0
- Access
- Invite only
- Export
- Canva, Markdown, JSON, CSV
Most marketing tools write a caption and stop. CampaignPacks runs the whole engagement. Give it a website URL or a plain-text brief and it returns a Launch Pack: positioning, an ideal customer profile, offer analysis, a landing-page critique, brand voice, content pillars, a 14-day campaign calendar, social posts for LinkedIn, X, and Instagram, an email launch sequence, and Canva-ready design briefs.
It is review-first by design. Every asset arrives with a confidence score and honest quality warnings, and nothing reaches Canva until you approve it. Missing proof is named, not invented: no fabricated metrics, no borrowed testimonials.
CampaignPacks is an agency operating system, not a chatbot and not a generic content generator. It creates, you review, you export. Your AI keys stay encrypted at rest, and it never posts, schedules, or emails on your behalf.
Walkthrough
How it works.
Paste a URL or a brief
Give CampaignPacks a website URL or write a plain-text brief. It ingests the site and analyses what you sell, to whom, and how you say it.
The agency brain runs
Eleven playbooks run in order: offer, ICP, positioning, landing critique, brand voice, pillars, campaign plan, copy, design briefs, quality scoring, and approvals.
Review on the Campaign Board
The Launch Pack lands on the Campaign Board. Every asset carries a confidence score and honest quality warnings, so you review with the full picture.
Approve asset by asset
Approve each asset on its own terms. Nothing reaches Canva without your sign-off.
Export
Export the finished pack: Canva designs, Markdown, JSON, or a campaign-calendar CSV.
Features
What it does well.
Strategy first
03Positioning and ICP
Every campaign starts from a named audience: positioning, an ideal customer profile, and offer analysis, so each asset traces back to who it is for.
Landing-page critique
CampaignPacks reads your live site and returns a specific critique of the landing page, not generic best-practice advice.
Brand voice and pillars
It derives a brand voice and a set of content pillars from your own material, then holds every asset to them.
The Launch Pack
0414-day campaign calendar
A dated, 14-day launch calendar sequences the whole push, channel by channel, so the pack is a plan and not a pile of posts.
Social posts
Ready-to-review posts for LinkedIn, X, and Instagram, written to the brand voice and mapped to the calendar.
Email launch sequence
A full email launch sequence, staged across the two weeks alongside the social calendar.
Canva design briefs
Design briefs written for Canva, so the visual work starts from a clear spec rather than a blank page.
Review-first
03Approval state everywhere
Approval status is visible on every asset and every board, so you always know what is signed off and what is still waiting.
Gated Canva creation
Canva creation is gated server-side on approval. Nothing is built or exported until you say so.
Confidence and warnings
Confidence scores and quality warnings are first-class in the interface, never hidden behind a polished draft.
Honest by construction
02No invented proof
Missing proof is named, not faked. CampaignPacks will not invent metrics or testimonials to fill a gap.
Stakeholder review links
Share a pack with a stakeholder through a link with comment threads, and collect feedback in one place.
Trust and control
03Your keys, encrypted
You bring your own AI keys, encrypted at rest with AES-256-GCM.
It never acts for you
CampaignPacks never posts, schedules, or emails on your behalf. It creates, you review, you export.
Export anywhere
Export the pack to Canva designs, Markdown, JSON, or a campaign-calendar CSV.
More from the studio
ProjScan
ProjScan tells reviewers when to bootstrap, prove, or stop. Review Gate returns one decision; bootstrap is explicit. Local proof, no code upload.
View
AgentLoopKit
The local control plane for low-token, verifiable agent loops. It owns scope, gates, and completion decisions, with a token receipt on every step.
View
AgentFlight
agentflight guard watches local trust while your coding agent works; agentflight finish writes the Review Passport that proves the result.
View