zlacker

I use claude code daily, but I've never been in a situation where Claude code was "deciding which product to use," that doesn't make sense to me. Claude is never on the web reading documentation - as far as I can tell that's not even in its toolkit. Can anyone give me more context for this? How do you end up having Claude code reading documentation and "choosing" a product to use? What type of prompts lead to this? I'm typically using it to add features to an existing repo, which doesn't really require any new services, to be fair, so I just haven't run into it I guess, but I didn't even know it was possible.

>>window+(OP)
It has full web search I often have CC search out docs and compare opinions on an approach

>>window+(OP)
> Claude is never on the web reading documentation - as far as I can tell that's not even in its toolkit.

Of course it is; I use it every day.

>>window+(OP)
A developer spinning up greenfield projects in technologies they would never have touched without AI are probably going to use whatever AI suggests (or chooses without asking) because they have nothing else to compare it to. Like a webdev who wants to build a mobile app will possibly auto-approve a lot of the choices just to get something up and running. And as we all know, the prototype-to-production train is hard to stop.

>>window+(OP)
we were evaluating some marketing / crm platforms, and ai automation + api, ideally w/ mcp, were in the top 5 eval criteria

>>window+(OP)
The choice happens implicitly rather than explicitly. If Claude tries an approach and hits a wall, it'll try a different approach. If an API call keeps not working, it'll choose a different API. It a tool is broken, it'll use something else. If it can't find docs nor read the code, it'll try to implement functionality from scratch. If you give it messy tools with confusing docs, you'll notice Claude not calling them as you'd expect, and instead trying something simpler instead.

>>dangom+21
Yesterday I had it using an internal library without documentation or source code. LSP integration wasn't working. It didn't have decompilation tools or the ability to download them.

I came back to my terminal to find it had written its own tool to decompile the assembly, and successfully completed the task using that info.

>>window+(OP)
> Claude is never on the web reading documentation

That is how I use it almost every day. "Here's the link to an API doc. Read it, write a new Skill around it, and [solve this problem with it]."

>>window+(OP)
I get several folks per week claiming an ai/llm recommended them my product, while I personally wouldn't run a procurement process that way, some certainly do.

> Claude is never on the web reading documentation - as far as I can tell that's not even in its toolkit.

Add the Context7 and grep MCP servers to your installation, it'll change your life (well it'll make claude less dumb).

>>dangom+21
"something simpler/simpler approach" are terms I search for in evals because they almost always indicate the model going off the rails (assuming the input prompt was decent).

>>zmj+x3
That's hilarious

>>window+(OP)
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

>>window+(OP)
From the article: "Claude Code can rip out one service and replace it with another in minutes. ..."

Doesn't that assume there are many interchangable services available on the web which essentially do the same thing?

I can see this would be the case if there were many online services for say compiling C++ code. But for more human-centric services, are there many "replaceable services" out there? An API is not only its syntax, but also its semantics.

>>window+(OP)
If you're not letting Claude at least criticize your product/API/library choices you're probably holding yourself back.

>>window+(OP)
Wow that's really interesting. Something I do very often, for libraries, languages, APIs, even shopping is:

"look into the possibilities for X search the web, do thorough comparison. look on HackerNews both to gather sources and gauge sentiment in the comments"

this yields pretty good results IMO.

If I am using an API/library, I will also ask "is this approach idiomatic? what does the documentation say? look through at least 10 pages online"

>>rovr13+M8
Wow, I had no idea. Thanks.

>>window+5i
Yeah, it's pretty nifty.

It's got a couple tools built into it that it can use.

>>Curiou+N5
this is a really cool insight, going to use this on my team from now on!