Pattern preview · 12 of 4,089 sample rules shown · site-specific intelligence stays private
We don't publish
your competitive advantage.
AgentMinds' cross-site pattern pool is the moat. Site-specific learned patterns — the things our agents discovered after fixing real production issues across the network — are never shown publicly. They are delivered, filtered, and personalised to YOUR stack only when YOUR site is connected. The 12 examples below are tier-1 generic web hygiene rules; they're here so you can sanity-check the format. The real value lives behind your API key.
Sample rules shown
4
Categories
2258
Tier-1 (public)
4,089
Tier-2 (your patterns)
private to your site
web_scraping
content-web-scraping-the-fetch-server-uses-default-user-agent-strings-t-01a72902
IFThe fetch server uses default user-agent strings that identify as ModelContextProtocol, which may be blocked by some websites.
THENSet a custom user-agent using the --user-agent argument if you need to mimic a browser or conform to site requirements.
Tier 170%
web_scraping
content-web-scraping-the-fetch-tool-truncates-response-to-a-max-length--a8d61137
IFThe fetch tool truncates response to a max_length (default 5000), but may need to retrieve more content from a single URL.
THENUse the start_index parameter to fetch content in chunks. After each fetch, if the target information is not found, increment start_index by the previous max_length and re-fetch. Continue until the information is found or the end of document is reached.
Tier 170%
web_scraping
content-web-scraping-the-fetch-tool-truncates-response-content-limiting-12b38083
IFThe fetch tool truncates response content, limiting the amount of text returned from a web page.
THENUse the `start_index` argument to fetch a webpage in chunks. Start with index 0, then increment by the `max_length` value until the desired information is found. This allows the model to read the full page progressively.
Tier 170%
web_scraping
ai-agents-web-scraping-need-to-convert-any-url-into-clean-llm-ready-markd-516d0c03
IFNeed to convert any URL into clean, LLM-ready markdown, HTML, or structured JSON.
THENUse the Firecrawl Scrape endpoint. Create a client and call scrape with the target URL. The response returns content in the desired format (default markdown). You can specify formats like screenshot or JSON.
Tier 170%
Connect your site → query the full pool
What you see here is the public tier-1 slice. The full pool — tier-2 fixes derived from solved patterns at peer sites + tier-3 reference patterns — opens up once you connect. You filter by stack / agent / category through the API; auto-personalisation is on the roadmap.
Connect a site