Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics…
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution.
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference…
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model…
Scalable data processing for ML workloads.
Guides researchers through structured ideation frameworks to discover high-impact research directions.
Process and generate multimedia content using Google Gemini API.
Diagnoses Universal Development Standards (UDS) installation health and analyzes development patterns for better workflow alignment.
Analyzes pipeline coverage, tracks forecast accuracy with MAPE, and calculates GTM efficiency metrics for SaaS revenue optimization
Brand monitoring tool for tracking mentions across social media platforms.
Weekly engineering retrospective with persistent metrics — commit patterns, work sessions, code-quality trends.
Create a refreshable live operations artifact for customer success, support, or launch review workflows.
Analyze and engineer protein glycosylation.
Use when asked to analyze a funnel, find where users drop off, diagnose low conversion or activation rates, design a metrics framework…
Metrics architecture — produce a complete metrics plan given a product description.
Product analyst — metrics architecture, funnel analysis, A/B test design, retention, and growth measurement.
OKR trees, KPI dashboards, North Star Metric, leading/lagging indicators, and experiment design.
Check session status and measure goal drift
Guide for working with Splitrail's MCP server.
Use before modifying, refactoring, or deleting files in a codebase that has Repowise indexed (indicated by a .repowise/ directory).
Search and analyze your own session logs (older/parent conversations) using jq.