AI Engineering

Audit Tenant Settings compares Fabric and Power BI tenant settings against a curated baseline and surfaces drift, delegated overrides, and related Entra group context. Use it when reviewing tenant governance or investigating setting behavior.

Connect To Power Bi Desktop uses PowerShell with TOM and ADOMD.NET to query and edit the local Analysis Services model in Power BI Desktop. It is used for model enumeration, DAX queries, metadata changes, and Desktop Bridge reload or screenshot checks.

Help Me Get Started guides new users through Power BI agentic development setup and concepts. Use it for installation help, prerequisites, terminal guidance, safety questions, or learning about models, context, prompts, tools, and environments.

Improve My Agent Setup audits an agentic-development setup across skills, memory, tools, permissions, hooks, and secrets hygiene. Use it to review workflow health, score weak spots, and decide what to fix next.

Pbir Cli manages Power BI reports through the pbir command-line tool. Use it to explore, create, format, validate, publish, refresh, screenshot, and verify .pbir, .pbip, and .pbix reports.

Refresh Semantic Model triggers, monitors, validates, and troubleshoots Power BI semantic model refreshes. Use it to run full or partial refreshes, check status, and confirm new data arrived.

SVG Visuals generates inline SVG graphics with DAX measures for Power BI reports. Use it when you need sparklines, progress bars, KPIs, gauges, or other DAX-generated visuals rendered as images.

TMDL Authoring edits .tmdl files directly in PBIP semantic models and converts BIM to TMDL. Use it for quick text-level fixes, adding measures or descriptions, and handling TMDL syntax and indentation.

Dataset Transformation generates code to convert datasets between ML training and evaluation schemas. Use it when a dataset needs to be reformatted for OpenAI, SageMaker, HuggingFace, Bedrock Nova, VERL, or custom JSONL outputs.

Finetuning generates code for SageMaker serverless training jobs to fine-tune a base model. Use it when starting training or when a plan reaches the finetuning step, including SFT, DPO, RLVR, and RLAIF workflows.

Finetuning Technique helps choose and validate a fine-tuning method such as SFT, DPO, RLVR, or RLAIF for a selected base model. Use it after model selection when you need to match a technique to a use case and supported recipes.

Agent Factory generates production-ready Claude Code agents and sub-agents with YAML frontmatter, tool access patterns, execution rules, and MCP integration support. Use it when creating or validating custom agents for a workflow or domain.