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
flash_attention_batch_bug
ai-agents-flash-attention-batc-using-flash-attention-2-with-batch-inference-on-ll-a5da304f
IFUsing flash_attention_2 with batch inference on LLaVA models produces garbled or repetitive outputs for some prompts.
THENAvoid setting `attn_implementation='flash_attention_2'` for batch inference until the fix is released. Stick with the default SDPA attention implementation, which works correctly. Ensure `padding_side='left'` on the processor as a best practice but note it does not resolve this specific bug.
Tier 170%
flash_attention_batch_bug
performance-flash-attention-batc-flash-attention-2-produces-repetitive-or-garbled-o-a5fdffa5
IFFlash Attention 2 produces repetitive or garbled output when used with batched inference in vision-language models like LLaVA, especially for the second or later samples in the batch.
THENAvoid using `attn_implementation="flash_attention_2"` for batched inference in models that process image tokens via a legacy expansion path. Instead, use SDPA (`attn_implementation="sdpa"`) or upgrade to a version of transformers where the legacy path is removed. The bug is caused by incorrect attention mask handling in the legacy image token expansion code, which corrupts the mask for Flash Attention but not SDPA.
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