Data analysis, machine learning, LLM apps, and prompt design (9K skills)
Turn documents into a growing Markdown wiki and a knowledge graph, a map of entities and their relationships. Preserve source text, update linked pages as new material arrives, and answer questions with supporting evidence.
Plan Power BI reports around business goals and audience needs. Get recommendations for chart types, page layouts, filters, navigation, mobile views, and accessibility, along with design specifications and a framework for reviewing usability.
Review a Power BI data model’s tables, relationships, storage choices, performance, maintainability, and security. Use the findings to identify design issues and build a prioritized improvement plan with concrete recommendations and implementation guidance.
Build and run evaluations for AI applications using Phoenix. Start with observed failures, create checks in code or use a language model as a judge, run experiments, and validate automated judgments against human labels.
Review DAX formulas, the expressions used for calculations in Power BI, and propose clearer, more maintainable alternatives. Identify repeated calculations, costly filtering, and error-handling issues, then explain changes and recommend ways to test them.
Investigate LLM application failures with Phoenix CLI by reviewing execution records, recording observations, and grouping mistakes into counted categories. Inspect datasets and experiments to identify which failure types deserve evaluation tests first.
Build systems that use Pinecone to find documents for AI answers or retain agent memories across sessions. Guides index setup, data loading, meaning-based and keyword search, memory separation, and end-to-end checks.
Diagnose slow Power BI reports, data refreshes, and queries through structured measurement and troubleshooting. Get recommendations for data models, DAX calculation formulas, report layouts, and infrastructure, with guidance for validating improvements and ongoing monitoring.
Polish an existing prompt file by improving its wording, structure, and organization. Correct spelling, grammar, and unclear instructions while preserving the original intent, front matter, encoding, and Markdown structure.
Plan and explain Lakehouse solutions in Microsoft Fabric, a place to manage tables and files together. Understand data organization, links to data without copying, access controls, and table maintenance options for designing and improving a solution.
Review an AI workflow across five areas: prompts, use of context, tools, system structure, and safety. Receive scores, specific findings, and prioritized actions to address quality and reliability problems.
Prepare raw credit data for pre-loan modeling by checking data quality and screening variables. Review missing values, predictive usefulness, stability, noise, and correlation, then export an Excel report with organization-level statistics and cleaning results.
Review Python and BigQuery pipelines for excessive costs, duplicate writes on reruns, and hard-to-diagnose failures. Receive a structured assessment with specific function and line references, prioritized fixes, and rough estimates of the largest cost risks.
Refine task prompts through questions about scope, deliverables, constraints, and success criteria. Receive an organized Markdown prompt in chat and on your clipboard, with revisions supported through the Joyride extension.
Design workflows that evaluate and refine AI outputs through self-review, separate generation and evaluation roles, tests, or weighted scoring criteria. Includes patterns for structured feedback, iteration limits, and stopping when quality stops improving.
Add Arize AX tracing to an LLM application, recording how model calls and tool executions connect. Inspect the existing code, select suitable integrations, add instrumentation, and verify that the application runs and traces reach Arize.
Organize human review in Arize by defining label choices, numeric ranges, or free-text feedback fields. Manage review queues and reviewers, submit annotations for individual records, and apply existing labels to project spans, or individual processing records, in bulk.
Design an AI agent around its requirements, or audit an existing agent for architectural problems. Deliver justified decisions, verification plans, and a PDF report with a diagram, covering budgets, permissions, stopping rules, and failure handling.
Inspect existing LLM application records in Arize to investigate errors, slow operations, or behavior changes. Export traces, which group related operations, or individual operations and conversation sessions as JSON using the ax command-line tool.
Create and run evaluations in Arize using an LLM as the judge. Define scoring criteria, connect them to actual data fields, evaluate recorded operations or experiment results, and set up continuous scoring for new data.
Create and analyze AI model evaluation experiments in Arize using the ax CLI, a command-line tool. Collect real model outputs, export results, compare evaluation scores, and identify examples where a new model performs worse.
Create and manage Arize datasets for evaluation and experiments using the ax CLI. Import records from files, append examples, inspect dataset versions, and export a chosen version for offline analysis, with checks for field consistency and export completeness.
Create shareable links that open specific Arize resources, including traces, datasets, and evaluators. Use IDs from logs or exported data, with suitable time ranges, to direct teammates to the relevant view.
Manage the credentials Arize uses to call LLM providers such as OpenAI and Anthropic. Create, inspect, update, or delete connections, configure allowed models and authentication methods, and retrieve connection IDs for use in evaluations.