Why run this experiment
I handed social posting entirely to AI for 30 days. Every caption for X and LinkedIn went through Claude with a structured prompt — no manual rewrites. Could AI-generated social content perform well enough to justify removing this task from my plate entirely?
📋 Experiment Setup
Duration: 30 days (March 2026). Platforms: X and LinkedIn. Posts per platform: 2 per day, scheduled via Buffer. AI tool: Claude (claude.ai). Human input: brief + topic only — no editing of captions before posting.
The numbers
What performed best
Contrarian takes consistently outperformed everything else. Posts that challenged a common assumption pulled 3–4x the engagement of informational posts. The AI generated these well when prompted with a specific counter-argument angle.
Short, sharp observations beat lists. LinkedIn outperformed X on reach for every format.
What flopped
Four posts got near-zero reach. Three shared a pattern: they were factually correct, well-structured, and completely unmemorable. AI defaults to competent when it doesn’t have a strong brief. The fourth had a fake-feeling statistic without a clear source — caught before it went out. Manual review of any specific data claims is non-negotiable.
The prompting system that worked
- Topic: One specific idea or finding (not a broad theme)
- Angle: Contrarian / surprising result / counter-intuitive
- Format: Insight post, under 200 characters
- Voice: Practitioner sharing what they tested, not brand announcement
With that brief, hit rate was around 80%. Without it, closer to 40%.
Would I recommend this workflow?
Yes, with one condition: invest 5 minutes in the brief, not zero. The 14 minutes a day is real. That’s a task that would have taken 45–60 minutes done manually with the same quality ceiling.