Hand a founder's LinkedIn to a Claude Code agent pipeline for seven weeks, with a human approving every post, and read the median not the headline
A non-coder consultancy founder describes running LinkedIn through Claude Code with strategist, writer, editor and analyst roles, and reports a 25 times lift in total reach alongside a 1.3 times lift in the median post.
Evidence: The author reports this. We have not checked it beyond reading the source.
The business problem
A founder with no time wants to post consistently and learn which posts work, without writing everything by hand.
What was tried
Write the brand rules, audience, pain points and strategy down once for the system to read. Run four roles in Claude Code: a strategist that writes briefs, a writer that drafts, an editor that reviews drafts against performance data, and an analyst that reads weekly numbers. Repeatable skills check an idea sheet daily, scan local business news weekly, schedule posts and ingest metrics. Posts move through idea, draft, review, approved, scheduled and published, and an adversarial editor then a human must approve each one before it ships.
What was reported (mixed)
Posting went from 1.5 to 5.9 posts a week and monthly reach from about 2,200 to about 54,000. Average reach per post rose 6.2 times (2.8 times without two viral posts), median reach only about 1.3 times (242 to 309), and comments per post rose from 0.9 to 4.4. About half the AI posts performed no better than before.
Limitations
Self-reported by the founder of a consulting firm that ends by selling its services. The author says the account was recovering from an earlier algorithm dip, so some lift may not come from AI, and recent posts were still maturing. No hours saved are given, the comparison covers about 14 weeks against 6 weeks, and the article is inconsistent on one post's impressions. Posts without a sharp angle or a real story landed flat. Reach is not leads or revenue.
What you need
Claude Code, a LinkedIn profile, written brand and audience notes, and someone to approve every post.
Sources
- Scaling-Up! Ventures (Moonshi MohsenRuddin; sells consulting) ↗ Firsthand write-up, published June 10, 2026
Source published: June 10, 2026. Last reviewed here: October 14, 2026. Spot a mistake? Tell us.
Tools in this workflow
- Claude Code: Runs the strategist, writer, editor and analyst rolesTry Claude Code
Related workflows
Install an open-source library of 200+ go-to-market skills for Claude Code covering SEO, outreach, ads research and competitor tracking
A maintained repository packages go-to-market tasks as skill files for coding agents, including SEO research, lead finding and enrichment, outreach drafting, content, competitor tracking and social monitoring.
Give your coding agent an email marketing playbook: an open-source Claude Code skill for audits, flows, copy and compliance checks
A founder of several email businesses published a free, open-source knowledge base and Claude Code skill that lets an agent audit an email account, build welcome, cart and win-back flows, draft copy and check compliance.
Run four OpenClaw agents for content, leads and ops on Gemini's free tier, with a quality gate and a hard cap on requests
A solo developer in Taiwan describes four OpenClaw agents on a home machine that draft social posts, reply to comments, research, scan for leads and monitor endpoints, using Gemini's free tier at about 105 of 1,500 daily requests.
Plan ten Claude Code skills for a small service business, one a day, and review the first 20 to 50 runs before anything is sent or paid
An agency guide lists ten back-office tasks to turn into Claude Code skills, such as inbox triage, reply drafts, invoice processing and weekly reconciliation, with a rule to review early runs by hand before irreversible actions.