The content calendar that fills itself.
Describe your content process once — brand voice, stages, publish rules. From then on AI agents draft, format and stage every piece, and your team just approves what goes live.
Free while in beta · No credit card · Runs on your models and tools
Q3 pricing update announcement
Case study: onboarding revamp
Drafting from the interview notes…
Blog: 5 signs you've outgrown spreadsheets
Waiting on your approval
LinkedIn thread from launch post
Published 9:04
The week you know too well
The calendar is always behind
The plan says three posts a week. Reality says one, late, because every draft waits on the same overloaded writer.
Everything bottlenecks on review
Drafts sit in docs, feedback lives in chat, and nobody can see what's stuck where — so 'in review' quietly means 'dead'.
Repurposing never happens
Every article should become a LinkedIn post, a newsletter blurb and three snippets. It almost never does, because it's nobody's job.
What marketing teams run on Veloop
These three loops come pre-wired — columns, playbooks and publish steps included. Point them at your CMS and channels and they run from day one.
Content publishing
Every weekday morning
- Agent
- Picks the next brief, drafts in your brand voice, runs the SEO checklist, and stages it in your CMS.
- Human
- Skims the draft in “Needs approval” and clicks approve — or leaves one comment to revise.
Social repurposing
On every published article
- Agent
- Turns each article into platform-native posts — LinkedIn, X, newsletter blurb — with the right tone per channel.
- Human
- Approves the batch in one pass; edits land back on the card, not in a chat thread.
Competitor & keyword watch
Every Monday
- Agent
- Sweeps competitor blogs, pricing pages and rankings, then writes a diffed weekly digest with content angles.
- Human
- Reads the digest, picks the angles worth writing, and drops them straight into the content backlog.
From reading this to a first run — about ten minutes
Paste one prompt
Hand the starter prompt to Claude Code, Codex or any agent. It installs the CLI, creates your account, and wires up the loop — about ten minutes to a first run.
Agents run the loop
On schedule or on trigger, agents pick up tasks, follow your playbooks, comment as they go, and move cards across the board.
You approve what matters
Watch live, weigh in with a comment, approve the gated steps. Every run makes the playbooks — and the next run — better.
Agents do the work. You keep the control.
Approval gates you define
Nothing customer-facing moves without a human unless you explicitly allow it — per loop, per stage.
Your models, your tools
Vendor-independent by design. Agents run with the CLIs, APIs and models you already use.
Unlimited free runs
Pricing counts loops with accountable humans — never runs, tasks or agents. Volume is free.
No lock-in
Playbooks are plain markdown you own. Your processes stay yours — exportable, portable, readable.
Before and after the loop
Veloop for marketing teams, answered
- Will AI publish content without a human seeing it?
- Only if you configure it that way. Every loop has explicit approval stages — by default nothing moves to Live until a person moves it. You decide per loop which steps auto-run and which wait for sign-off.
- How does the agent learn our brand voice?
- Each loop carries playbooks — markdown instructions like your style guide, tone rules and banned phrases. Agents read them on every run, and you refine them whenever a draft misses the mark, so quality compounds.
- Does it work with our CMS and social tools?
- Veloop is vendor-independent: agents run with the CLI tools and APIs you already use (your CMS, scheduler, analytics). If your team can script it or an agent can call it, a loop can ship it.
- What does it cost?
- Veloop is free while in beta. Pricing will count loops with accountable humans — never runs, tasks or agents — so a loop publishing daily costs the same as one publishing monthly.
Veloop for other teams
Your next post could draft itself tonight.
Set up the content publishing loop in about ten minutes — free while in beta.