Content drafts Claude wrote because it understood the brief.
It reads the brief, the prior work, the audience signal, and writes a first draft that captures the angle — not a generic post that needs to be rewritten from scratch.
Post drafted · social cuts queued. LinkedIn preview:
Daniel Reyes · 1st
Content lead · Arahi AI
Today · 11:30 AM ·
We rebuilt our onboarding flow with Claude in the loop — and watched activation jump from 31% to 61% in three weeks.
What worked: letting the model write the welcome copy, but having a human approve the next-step suggestions.
Here's the playbook.
Read the teardown → arahi.ai/blog/onboarding
Built in plain English.
You write the rule the way you'd describe it to a teammate. The agent reads the rule, breaks it into the actions it'll take, and confirms the apps it'll touch — before it does anything.
- 1Read the source content (post, transcript, brief)
- 2Match each channel's voice and length conventions
- 3Generate variants per platform with platform-native formatting
- 4Queue every draft for your review before publishing
Get started in three steps
Connect Anthropic (Claude)
Authorize Anthropic (Claude) in your Arahi AI dashboard. The secure connection takes less than 60 seconds.
Configure Your AI Agent
Set up triggers, actions, and conditions specific to how your team uses Anthropic (Claude).
Deploy & Monitor Results
Your AI agent goes live immediately. Track tasks automated, time saved, and accuracy metrics in real-time.
We rebuilt our onboarding flow with Claude in the loop — and watched activation jump from 31% to 61% in three weeks.
Twitter thread variant of today's launch announcement.
Newsletter teaser pulled from this week's top blog post.
Approve before it sends.
Every draft lands in a review queue. You approve, edit, or reject — the agent never acts on its own unless you explicitly turn that on for a workflow you trust.
Every action, with the reasoning attached.
Each step the agent takes is logged with what it did, why it did it, and which app it touched. Audit-ready, so security and compliance can sign off without backfilling.
- Priya10:15 AM
Approved the LinkedIn draft for tomorrow 9 AM.
- Agent10:13 AM
Drafted the LinkedIn post in Daniel Reyes's voice.
Reason: Voice sample showed bullet structure underperforms; switched to narrative.
- Agent10:12 AM
Generated channel-specific variants from the source post.
- Agent10:11 AM
Read this morning's product update.
- Agent10:00 AM
Triggered: Have @Claude expand this morning's teardown into a 1,200-word blog post in our v
Frequently asked questions
Explore more AI agent solutions
Start automating Content Creation for Anthropic (Claude)
7-day free trial. Works with the tools you already use.