We were promised autonomous AI agents. But got Workflow Automation 2.0 instead.
2025: The Year of AI Agents 😄
2025: The Year of AI Agents 😄 2026: The Year of Workflow Automation 2.0 😐
In early 2025, I was buzzing with excitement.
I built workflows in n8n that could do prospect research and send personalized emails as if they were from me. I saw the possibility of automating entire knowledge jobs with AI agents.
“2025 is the year of AI agents”, I believed it. With a 200k to 1m token context window, models can process 500+ to 2500+ pages of text. More than enough to give them any complex instruction to follow.
Fast forward to 2026. After using Claude Code with Opus 4.5 (one of the best models available) heavily for a few months, I’ve since lowered my expectations.
At 80k token context, we got poor instruction-following, hallucinations, Claude Code telling me a task is completed when it clearly isn’t.
Here’s what I’ve learned:
What DOESN’T work: Giving AI a detailed plan and a long-running task, then expecting it to finish reliably.
What ACTUALLY works:
- Break tasks into VERY SMALL sub-tasks
- Create specialized skills for how to DO each task
- Create specialized skills for how to REVIEW each task
- Create master skills with a step-by-step workflow that spawn agents to repeat do + review cycles
Each skill? Best kept within 40k tokens.
That doesn’t sound like autonomous AI agents as promised. It increasingly feels like I’m doing workflow automation 2.0.
So what’s the difference?
Workflow Automation 1.0: → Steps drawn as flowcharts → Code written to process data at each node → Structured input required → Deterministic output guaranteed
Workflow Automation 2.0: → Steps written in natural language, as skills → Data processing described in natural language, as skills → Input can be less structured → Output is non-deterministic
We’re trading determinism and accuracy for robustness and flexibility.
That’s the real state of AI right now.
Don’t get me wrong. Workflow Automation 2.0 is still very useful. It’s just that it is a far cry from “intelligence” as claimed.
I think we’ve hit the ceiling of what LLMs can do.
I am looking forward to the next release of frontier models to prove me wrong.
What do you think? Are we in the age of AI agents, or just workflow automation 2.0?
Enjoyed this? Subscribe for more.
Practical insights on AI, growth, and independent learning. No spam.
More in AI Agents
Harness the power of AI Agents for Sales, Marketing and Customer Engagement
Building AI agent skills is the most important thing you can learn right now. There are 4 levels of skill complexity.
If you use an AI agent out of the box, you are running the same model as everyone else. It gives you average output. It does not know your work, your standar...
Gemini CLI stubbornly insisted its code was right and even did a Google search to prove it with an outdated article.
I was speechless. 😂
💡 Little-known hack to get the most out of Cursor for FREE
If you're using Cursor on the free plan, you will eventually hit the dreaded "servers overload" screen.
AI amazes me from time to time.
Yesterday, I caught up with an old friend from my hometown, Penang.
Cursor's Pricing Changes Caused an Uproar
They have to do it because subsidizing the market with cheap tokens is not sustainable in the long run.
Harness the power of AI Agents for Sales, Marketing and Customer Engagement
Gemini CLI stubbornly insisted its code was right and even did a Google search to prove it with an outdated article.
I was speechless. 😂
AI amazes me from time to time.
Yesterday, I caught up with an old friend from my hometown, Penang.
Building AI agent skills is the most important thing you can learn right now. There are 4 levels of skill complexity.
If you use an AI agent out of the box, you are running the same model as everyone else. It gives you average output. It does not know your work, your standar...
💡 Little-known hack to get the most out of Cursor for FREE
If you're using Cursor on the free plan, you will eventually hit the dreaded "servers overload" screen.
Cursor's Pricing Changes Caused an Uproar
They have to do it because subsidizing the market with cheap tokens is not sustainable in the long run.