Claude Code is your customer

>>nine_k+ksg
Without a strong propsition as to why I, as a customer, would use an agent over not doing so? Whats the value prop?

Thats always missing from these sorts of articles and comments, is why is this better

Related query: how is this really any different than what the W3C has proposed with Hydra[0] or other linked data APIs and formats? Who benefits by making their APIs more transparent, when 15 years or so ago there was a big push for this exact thing and it failed due to business concerns, not technical ones.

It's simply assuming what the way forward is without positing why other ways will not work to justify the position.

My secondary critque of the article, is using this as a basis of comparison:

>any product that can't be used by an agent will be as dead as a product without mobile support is today

First, I think its important 'mobile support' is defined. Is it as simple as a mobile friendly website or an app? Are we talking equivalent functionalities as well with the desktop counterpart?

Second, it ignores a ton of successful projects and products. Blender, Maya, Unreal engine. There's also a huge swath of games that only launch on PC or consoles.

If equivalent 1:1 functionality is to be considered, Adobe suite is still primarily a desktop tool, as is Figma.

I know there are a huge host of apps I'm missing too.

While more consumer apps migrated to web + mobile, you can often find functional differences between accessing on desktop vs mobile, where desktop is more complete. Its still not uncommon to have a mobile / tablet version of an app that is missing features that the desktop or website version is not.

[0]: https://www.hydra-cg.com/spec/latest/core/

>>window+iwg
Here's an example, https://shottr.cc/s/165K/SCR-20260131-oys.png

        Claude Code v2.1.29
      Opus 4.5 · Claude Team
           ~/stow/tmp
    
     I have a new project
      In it, I want to scrape hacker news data.
      The project will be built in python.
      I want to search first what are the latest projects in python that could help me extract the data. This could be via api or scraping it.
      Once you have a plan, ask me 10 questions to help navigate the structure.
    
     I'll help you research the latest Python options for extracting Hacker News data. Let me search for current tools and approaches.
    
     Web Search("Python Hacker News API scraping library 2026")
      ⎿  Did 1 search in 20s
    
     Web Search("Hacker News official API Python wrapper 2025 2026")
      ⎿  Did 1 search in 17s
    
     Web Search("best Python library scrape Hacker News data extraction")
      ⎿  Did 1 search in 20s
    
     Let me get more details on the official Hacker News API and some specific library documentation.
    
     Fetch(https://github.com/HackerNews/API)
      ⎿  Received 373.8KB (200 OK)
    
     Fetch(https://pypi.org/project/hackernews-python/)
      ⎿  Received 3KB (200 OK)
    
     Fetch(https://github.com/avinassh/haxor)
      ⎿  Received 378.1KB (200 OK)
    
     I've gathered comprehensive research on the available options. Let me write up my findings and then ask you the 10 questions.
    
     Updated plan
      ⎿  /plan to preview
    
     Research Summary
    
      I found several solid options for extracting Hacker News data in Python:
    
      Best Options Found:
    
      1. Official HN API (Firebase-based) - Free, no rate limits, real-time data
        - Source: https://github.com/HackerNews/API
      2. haxor - Most popular Python wrapper for the official API
        - Source: https://github.com/avinassh/haxor
        - Install: pip install haxor
      3. DIY Scraping - BeautifulSoup + Requests/httpx for data not in the API
        - Source: https://www.proxiesapi.com/blog/scraping-the-hacker-news-with-python-and-beautiful.html.php
      4. Commercial - https://apify.com/epctex/hackernews-scraper for hosted solutions
    
      ---
      Now, here are my 10 questions to help define your project structure:
    ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
    ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
    ←   Data Source   Data Types   Storage   Use Case   Submit  →
    
    Do you want to use the official HN API (recommended, no rate limits) or scrape the website directly?
    
     1. Official API (Recommended)
         Use Firebase-based API - reliable, real-time, no rate limits
      2. Web Scraping
         Scrape HTML directly - more flexible but requires maintenance
      3. Both
         API as primary, scraping for data not available via API
      4. Type something.
    ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
      5. Chat about this
      6. Skip interview and plan immediately
    
    Enter to select · Tab/Arrow keys to navigate · Esc to cancel

zlacker

Claude Code is your customer