@canion There is a plugin already made for this. github.com/lizard-he…
@viktorpali.bsky.social I am eagerly waiting for the API/MCP integration. Any chance to get into the beta?
@zsolt.decoding.io And I’m sure there are more examples like this in Liquid Glass.
I miss the times when we had long WWDC sessions talking about pixel level spacing and shaming weird UIs.
www.youtube.com/watch?v=Elr…
@zsolt.decoding.io I understand that Alan Dye wants to capsulate the whole world, but should we clip scrollbars?
@zsolt.decoding.io Checkbox labels should not contain explination text. The best: the same settings window contains the proper example. 🙃
@zsolt.decoding.io Since when do we indent preferences like this?
@zsolt.decoding.io Photos is the worst offender. The interface flips from black to white and back as you scroll through your library. Meanwhile Safari keeps the old blurred rectangle while Mail gets progressive blur. There’s no consistency in the toolbar background logic.
@zsolt.decoding.io Apple left existing 3rd-party apps alone so they still work with the previous design. That’s smart. But the new adaptive system needs serious work.
decoding.io/2025/08/fir…
@zsolt.decoding.io The token savings are significant, but the real benefit is focus.
Each persona does one thing well with the right tools for that job. The system prompts shaped distinct behaviors.
@zsolt.decoding.io Read the full post:
decoding.io/2025/08/sol…
@zsolt.decoding.io Based on subagents I had the following idea: what if I split Claude into specialized personas, each loading only the tools it actually needs? Main persona stays clean and fast.
@zsolt.decoding.io Research persona loads Zen for multi-model reasoning, Context7 for library docs, Octocode for code search. GTD persona connects to OmniFocus, Obsidian, DEVONthink.
The most powerful aspect isn’t just the separation. It’s the ability for personas to delegate to each other.
@zsolt.decoding.io When delegation happens, I must approve it first. The main persona will say something like: “I’d like to ask the research persona to analyze this Rails controller for N+1 queries using its specialized tools.”
@zsolt.decoding.io No service objects, no complex abstractions. Business logic resides in models, while controllers remain concise.
@zsolt.decoding.io Everything renders JSON for now, as we haven’t developed a Turbo-based UI yet. We focused on getting the Rails conventions right: nested routes, proper placement of calculations, and correct naming.
@zsolt.decoding.io Full details: decoding.io/2025/07/pez…
@zsolt.decoding.io Still need to test thoroughly and build the UI, but the foundation is solid. The models track progress, adjust for current balances, and integrate with the existing budget structure.
@zsolt.decoding.io Full post: decoding.io/2025/07/pez…
@zsolt.decoding.io Claude searches the codebase and manages task creation while ChatGPT analyzes patterns and suggests Rails-idiomatic approaches. Sometimes I jump in to guide them or ask them to wait for my approval on design decisions.
@zsolt.decoding.io The result?
7 detailed task files with 56 test cases total. Each test case addresses real edge cases like “what happens when a monthly goal already has surplus funds?”
Tomorrow, Claude Code takes these plans and starts implementing.
Full post: decoding.io/2025/07/pez…
@zsolt.decoding.io The technical challenge: handling goal changes over time. I went with snapshots where each month preserves what you were thinking at the time.
January’s allocation stays based on January’s goal settings, even if you change everything in March.
@zsolt.decoding.io Full post: decoding.io/2025/07/pez…
@zsolt.decoding.io What happens when you change a goal target mid-year? When you never spend from a monthly budget? When you miss a deadline payment?
These edge cases needed proper handling.
@zsolt.decoding.io Full post: decoding.io/2025/07/pez…