LinkedIn growth
Slow Content Is Winning Again
Fewer posts, more evidence. Why long, sourced, slow-built pieces are outperforming daily volume on LinkedIn in 2026.
3 min
The ClawLI Journal
Notes from the agent floor
Field notes on autonomous agents, LinkedIn distribution, and building content systems that survive contact with a real audience. Written by hand, published twice a month through spring and weekly since May.
Latest, Go-to-market
After the Crackdown: Operating a LinkedIn Program That Survives Enforcement
Every growth team that built on automation is now discovering which parts of the program were strategy and which parts were arbitrage.
Read it 3 min
Archive, 21 pieces
Agent engineering
Multi-Agent Systems Fail Quietly
Multi-agent systems degrade without erroring. Traces, spans, and the telemetry that turns an inexplicable bad output into a fixable bug.
3 min
Agent engineering
Pre-Flight: The Checks That Run Before an Agent Publishes
Nine deterministic checks that catch the errors a model will never catch about itself, running in the last second before publish.
3 min
Content operations
Voice Without the Cringe
How to encode a real writing voice for an AI system, and why "professional but approachable" produces the exact opposite.
3 min
Go-to-market
Attribution for Content That Actually Closes
Impressions do not pay salaries. A practical model for connecting posts and comments to pipeline without pretending to be certain.
3 min
AI agents
Autonomy Levels for Content Agents
A five-level framework for deciding how much your agents get to do on their own, and how they earn the next level.
3 min
LinkedIn growth
Comments Are the Channel Now
Posts get you seen. Comments get you known. Why the reply field became the highest-leverage surface on LinkedIn, and why automating it is a trap.
3 min
Go-to-market
Token Budgets Are the New Headcount
How to plan, allocate, and defend AI spend when your capacity is measured in context windows instead of people.
3 min
Go-to-market
Nobody Wants Another Copilot
The copilot pattern put the work back on the user and called it collaboration. Buyers in 2026 are pricing outcomes instead.
3 min
Content operations
The Four-Agent Newsroom
A working blueprint for content operations: researcher, writer, critic, and scheduler, with contracts between them and a human at the gate.
3 min
LinkedIn growth
Stop Posting Daily. Start Publishing With a Thesis.
Daily posting was a supply-side strategy for a supply-constrained feed. That feed is gone. Here is what replaced it.
3 min
AI agents
Memory Is the Moat
Why your AI still writes like a stranger after six months, and what a memory layer has to do to fix it.
3 min
Agent engineering
Evals or It Didn’t Ship
LLM evals for agents that write, when there is no correct answer. Golden sets, rubric judges, and the metrics that survive contact with reality.
3 min
Content operations
Approval Is the Product
Human-in-the-loop is usually sold as a safety compromise. Designed properly it is the fastest quality loop you have.
3 min
LinkedIn growth
Ghostwriters vs Agents: What Actually Scales a Founder’s Voice
A ghostwriter learns your voice by interviewing you. An agent learns it from artefacts. Both fail the same way, and the fix is identical.
3 min
Agent engineering
Your Agent Costs 10x More in Production Than in the Demo
Where the money actually goes when an agent leaves the prototype: retries, context growth, judge models, and the human review nobody budgeted.
3 min
Agent engineering
Context Engineering Beat Prompt Engineering. Here’s the Handoff.
Four pillars of context work (selection, compaction, ordering, and isolation) and the failure each one prevents in production agents.
3 min
Content operations
The Anti-Slop Standard
A publishable checklist for beating AI slop: what to ban, what to require, and how to enforce it before a draft ever reaches a human.
3 min
AI agents
Prompting Is Not a Strategy
The prompt was never the product. Why 2026 belongs to agent systems with memory, tools, and a definition of done.
4 min
LinkedIn growth
The LinkedIn Feed Broke in 2026. Here’s What Still Works.
Reach collapsed for generic posts and held for specific ones. A working theory of the LinkedIn algorithm in 2026, and how to publish inside it.
4 min