eve-analyst
coleam00/eve-analyst
The eve-analyst is a data analyst agent built on the Eve framework, designed to answer data-related questions using SQL, enforce revenue rules, and run analysis in a sandboxed environment. It supports HTTP and Slack communication and is fully self-contained with an in-memory dataset.
Overview
The eve-analyst is a production-ready data analyst agent built on Vercel's Eve framework. It allows users to ask questions about company data in plain English, and the agent responds by writing read-only SQL, enforcing revenue rules, and running deeper analysis in an isolated sandbox. It supports HTTP and Slack communication, and its behavior is locked in by an evals suite. The dataset is seeded in memory, making it fully self-contained and deployable with a single command.
Capabilities
- ▸Answering data-related questions in plain English
- ▸Writing read-only SQL queries
- ▸Enforcing revenue rules
- ▸Running analysis in a sandboxed environment
- ▸Supporting HTTP and Slack communication
- ▸Delegating complex analysis to subagents
Best for
The eve-analyst is useful for answering data-related questions in a business context, enforcing revenue rules, running analysis in a sandboxed environment, and providing insights through HTTP or Slack communication. It can be used for data exploration, query approval, and subagent delegation.
Works with
Security considerations
The eve-analyst uses an Anthropic API key for model interactions and runs analysis in a sandboxed environment with no network access. It enforces read-only SQL queries and does not write to the filesystem, ensuring data safety and isolation.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.