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
3
Categories
2258
Tier-1 (public)
4,089
Tier-2 (your patterns)
private to your site
mps_support
ai-agents-mps-support-some-pytorch-operations-are-not-implemented-on-mps-3250ddde
IFSome PyTorch operations are not implemented on MPS and raise errors, preventing training on Mac M1.
THENSet the environment variable `PYTORCH_ENABLE_MPS_FALLBACK=1` before running your script. This causes unsupported operations to fall back to CPU, though a UserWarning will still appear.
Tier 170%
mps_support
performance-mps-support-when-using-trainer-train-on-a-mac-with-m1-m2-gpu-t-384f0e03
IFWhen using Trainer.train on a Mac with M1/M2 GPU, training runs on CPU instead of the MPS device despite PyTorch 1.12+ supporting MPS.
THENOverride the TrainingArguments.device property to check for MPS availability. Subclass TrainingArguments and return torch.device('mps') when torch.backends.mps.is_available(). Use this subclass with Trainer. Alternatively, set the environment variable PYTORCH_ENABLE_MPS_FALLBACK=1 to allow CPU fallback for unsupported MPS operations.
Tier 170%
mps_support
ai-agents-mps-support-trainingarguments-does-not-automatically-detect-mp-bf393b27
IFTrainingArguments does not automatically detect MPS device on Mac M1 GPUs when using PyTorch >=1.12.
THENSubclass TrainingArguments and override the `device` property to check `torch.backends.mps.is_available()`. If available, return `torch.device('mps')` before falling back to CPU. This forces the Trainer to use the MPS GPU.
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