Sorry I really should check bsky more often... to your question, I do use API, some I just use my sessions.
I ask ChatGPT to guide me through the settings of n8n :)

Still hard: messy data, security, cost, culture.

Future = ultra-long context + RAG cache + MCP agents, powered by AI-native knowledge graphs.

Which solution would help your workflow first?

Breakthrough 2 → Agent workflows: frameworks wire LLMs to plan steps, call APIs and loop until done.

Breakthrough 3 → MCP: a lightweight JSON/HTTP “socket” any tool can expose, so agents plug in without bespoke wrappers.

What makes you say it's getting more stable just by looking at the graph?

I'm trying to set up a one-click scheduling system using n8n, so I can plan all my social posts across platforms, including Bluesky, to go out at the same time on the selected dates.

Why do you say so?

Lol, I received some of these too… the most diligent visitors are our least wanted ones.

Thanks, your answer helps. Definitely the feeling is a mixture of excitement and trying to be realistic.

Thank you for your insights Bryan. Your answer is very helpful for me to not get lost in the trend.

Am I sticking to an outdated style? Should I rethink my approach? #indiedev #buildinpublic

Here’s my recent (still unpolished) SaaS with a more traditional layout. quickviralnotes.xyz Would love your thoughts—what’s working for you? Do you prefer one-page designs or classic multi-page navigation?

Thanks for sharing! This is exactly what beginners like me like to see.

I’m not an SEO expert, but I know my articles can get penalized if they have too much of an “AI-generated” feel. My approach is: I draft my content with personal experiences, then use AI to refine grammar and flow, it works pretty well.

Thank you for the encouragement!

Great idea! I would love to see the results 👀