3. Data, Science & AI

Enables distributed data processing and machine learning using Domino's Spark, Ray, and Dask clusters for large-scale workloads.

Configures Domino Workspaces for data science and AI development, enabling environment setup, hardware configuration, and IDE management.

Provides a secure proxy for accessing external LLM providers with centralized API key management, usage monitoring, and compliance features.

Deploys and monitors AI model API endpoints in Domino, featuring version management, Grafana dashboards, and NVIDIA Triton GPU inference.

Identifies and analyzes gaps in datasets, such as missing values or inconsistencies, to enhance data quality and decision-making.

Integrates pull request feedback into the Violet AI model for continuous learning and enhanced code review capabilities.

Manages Domino Datasets for versioned, high-performance data storage, enabling reproducible data versions and cross-project sharing with optimized mounting paths.

Provides AI-native session continuity using shape anchors to maintain and restore state across sessions, replacing linear logs for efficient context management.

Builds and maintains scalable data pipelines for efficient processing and analytics infrastructure.

Provides programmatic access to Domino Data Platform features including SQL data sources, dataset management, ML training sets, and Pinecone vector database integration via Python SDK.

Extracts and displays the final message from a Claude agent's JSONL output file for quick review of agent results.

Enables business users to execute data analyses, generate reports, and trigger predictions via parameterized web forms without coding, with email notifications and access control.

Orchestrates multi-step machine learning workflows with typed inputs, reproducibility, and lineage tracking using Domino Flows built on Flyte.

Monitors production ML models for data drift, quality degradation, and triggers alerts for timely remediation.

Converts PDF documents to markdown text for easy readability and text extraction.

Tracks ML experiments in Domino using MLflow, supporting auto-logging for sklearn, TensorFlow, and PyTorch.

Identifies data gaps and metrics discrepancies to enable data-driven insights and decision making.

Debugs spectrum analyzer and waterfall display issues in WaveCap-SDR, including FFT visualization problems, frequency inaccuracies, and noise floor optimization.

Creates and manages WaveCap-SDR recipe templates for configuring radio monitoring scenarios including band plans, trunking systems, and multi-channel setups.

Designs and tests digital signal processing filters (highpass, lowpass, bandpass, notch) for WaveCap-SDR demodulation pipelines and response tuning.

Processes CSV files and pandas DataFrames for querying, analyzing, and manipulating structured data.

Analyzes WaveCap-SDR audio streams to assess quality, detect silence, noise, and distortion for SDR channel configuration and debugging.

Automates parameter sweeps and validation for WaveCap-SDR test harness, enabling regression testing and benchmarking of audio quality and demodulation performance across hardware configurations.

Provides AI operations context for Open Commerce MCP, enabling seamless AI integration and management within e-commerce platforms.