2023 was the year of the chatbot.
2024 was the year of RAG and finetuning.
2025 has been the year of MCP and tool use.
2026 will be the year of the computer environment and filesystem.
@alexalbert__
-
Evolution of AI: From Chatbots to Computer Environments
By
–
-
Spreadsheets as Solved Problem for AI Financial Services
By
–
The great thing about spreadsheets is they're structured, primarily text based, and often contain verifiable answers. They're on their way to being a solved problem.
— Alex Albert (@alexalbert__) 27 octobre 2025
Very bullish for AI financial products like Claude for Financial Services. https://t.co/RrxWQAO42bThe great thing about spreadsheets is they're structured, primarily text based, and often contain verifiable answers. They're on their way to being a solved problem. Very bullish for AI financial products like Claude for Financial Services.
-

Skills GitHub Stars Growth Comparison with MCP After One Week
By
–
Skills vs MCP github stars after one week Skills might be growing even faster than MCP did…
-
The Declining Friction of Going from Idea to Working App
By
–
The friction to start coding has dropped massively in just the past two years.
— Alex Albert (@alexalbert__) 20 octobre 2025
This is the next step where you can go from idea to working app without touching an IDE or a terminal.
The gap between thinking of something and building it keeps shrinking. https://t.co/uMqAEQxKxJThe friction to start coding has dropped massively in just the past two years. This is the next step where you can go from idea to working app without touching an IDE or a terminal. The gap between thinking of something and building it keeps shrinking.
-
Claude Creates Algorithmic Art PDF Flipbook Using Code
By
–
Claude made this insane PDF flipbook entirely through code using the algorithmic art skill in claude dot ai pic.twitter.com/NJ9OuCyQWe
— Alex Albert (@alexalbert__) 18 octobre 2025Claude made this insane PDF flipbook entirely through code using the algorithmic art skill in claude dot ai
-

Unlocking Hidden AI Capabilities Through Better Prompts and Skills
By
–
Skills are a glimpse into how much capability is already inside current models, just waiting to be unlocked by better prompts Claude made these PDF visuals entirely through code using the canvas-design skill in claude dot ai I had no clue this was possible before
-
Claude Multi-Agent Systems: Skills, Code, and Future Insights
By
–
Very interesting convo with @ErikSchluntz (multi-agent research lead) about all things agents:
— Alex Albert (@alexalbert__) 17 octobre 2025
– Why Claude is good at agent tasks
– Evolution from workflows to multi-agents
– Tips for creating Skills
– How code unlocks all other domains
– How to use subagents
– The future of… pic.twitter.com/NshRStZVdsVery interesting convo with @ErikSchluntz (multi-agent research lead) about all things agents:
– Why Claude is good at agent tasks
– Evolution from workflows to multi-agents
– Tips for creating Skills
– How code unlocks all other domains
– How to use subagents
– The future of -
Try Out Skills Feature on Claude AI Platform
By
–
Or go try out Skills in claude dot ai: https://t.co/W5GdkvlVKL
— Alex Albert (@alexalbert__) 16 octobre 2025Or go try out Skills in claude dot ai:
-
Skills as Foundation for Agent Learning and Future Expertise Sharing
By
–
Skills are the foundation for how agents will learn and share expertise in the future. We're exploring skill discovery and sharing next, and eventually: agents that create their own skills, codifying what works into reusable capabilities automatically.
-
Building Skills Iteratively with Claude: Best Practices
By
–
If you want to make a Skill, we recommend building iteratively. Run Claude on real tasks, watch where it struggles, then capture what worked. Claude can help you write skills as well with our skill builder skill in claude dot ai.