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
2
Categories
2258
Tier-1 (public)
4,089
Tier-2 (your patterns)
private to your site
guided_decoding_bug
ai-agents-guided-decoding-bug-when-serving-qwen3-models-with-vllm-0-9-0-if-enabl-a4193cb9
IFWhen serving Qwen3 models with vLLM 0.9.0, if `enable_thinking=False` is set and a `guided_json` schema is provided, the model output is malformed JSON (extra braces, backticks, or gibberish). The bug occurs with both `xgrammar` and `guidance` backends.
THENSet `enable_thinking=True` in the `chat_template_kwargs`, or append "/no_think" to the user prompt to bypass the thinking mode. Alternatively, avoid using the `qwen3` reasoning parser by not setting `--reasoning-parser qwen3`. For example: `extra_body={"guided_json": <schema>, "chat_template_kwargs": {"enable_thinking": True}}`.
Tier 170%
guided_decoding_bug
ai-agents-guided-decoding-bug-using-qwen3-models-with-enable-thinking-false-and--a6878421
IFUsing Qwen3 models with `enable_thinking=False` and guided JSON decoding produces invalid JSON output (extra brackets, markdown fences, or gibberish).
THENEnable thinking (`enable_thinking=True`) in the chat template kwargs, or remove the reasoning parser entirely. If you must disable thinking, avoid using guided decoding on Qwen3 models until the bug is fixed upstream.
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