Frontier
Frontier
Turn a Viva Insights export into a finished dashboard, executive deck, or ROI analysis by pasting a prompt into a coding agent. Includes reusable prompts, schema guides, and example outputs.
Frontier
Turn a Viva Insights export into a finished dashboard, executive deck, or ROI analysis by pasting a prompt into a coding agent.
Frontier is a collection of ready-to-use prompts, schema guides, and example outputs for Viva Insights. Instead of writing analysis code from scratch, you export your data, pick a prompt, and let a coding agent such as GitHub Copilot or Claude Code generate the deliverable for you to review and adapt.
Note: Everything in this section is sample code and starter assets. It is not production software. Outputs require review, validation, and adaptation to your environment before use.
Which asset should I use?
Frontier offers four ways to bring this work into a coding agent. Pick a card to jump straight to what you need, or see the full comparison below for more nuance.
Full comparison
| Mechanism | What it is | Status | Use it when |
|---|---|---|---|
| Prompt Library | Structured text you copy and paste into any coding agent for a single analysis task. | Available | Your agent does not support Skills or MCP, or you want a one-off analysis without any setup. |
| Skills | A packaged capability that a compatible coding agent loads automatically, so it applies the right conventions without you pasting anything. See the skills folder on GitHub. | Available | Your coding agent supports the Skill format (for example GitHub Copilot CLI or Claude Code) and you want ongoing, repeated Viva Insights work to follow consistent conventions. |
| vivainsights-context.md | A single context file you paste once at the start of a session. | Available | Your agent does not support Skills, but you still want to avoid repeating setup instructions in every prompt. |
| mcp/ | A protocol-level integration that would let an agent query prompts, schemas, and tools directly from a server. | Concept only, no server implemented | Not yet. Read the folder for the design intent and to track progress. |
Who is this for?
- People analytics leads building dashboards and reports from Viva Insights exports
- HR analysts who need repeatable, transparent analysis workflows
- Analytics consultants delivering Copilot adoption or workplace analytics engagements
- Technically capable users comfortable with R or Python and willing to work with a coding agent
You do not need to be a software engineer. If you can export a CSV from Viva Insights and paste a prompt into a coding agent, you can use these assets.
What’s inside
| Section | Description |
|---|---|
| Schema Documentation | Data dictionaries for person query exports, Purview audit logs, join patterns, and common data pitfalls. |
Additional resources available on GitHub:
| Folder | Description |
|---|---|
| examples/ | Sample output specifications describing what a finished deliverable looks like. |
| templates/ | Templates for contributing new prompt cards, skills, and schema docs. |
Getting started
Prerequisites
Before you start, make sure you have:
-
Exported Viva Insights data. Typically a person query CSV exported from the Viva Insights Analyst portal. Person query data has a panel structure with rows keyed by
PersonIdandMetricDate(person-week or person-day granularity). HR attributes such as organization, function, geography, and level are included as columns. - An R or Python environment. You need one of the following set up locally:
- R (4.1+) with vivainsights installed:
install.packages("vivainsights") - Python (3.9+) with vivainsights installed:
pip install vivainsights
- R (4.1+) with vivainsights installed:
- A coding agent. Any AI-assisted coding tool that can run R or Python:
- GitHub Copilot (in VS Code, JetBrains, or CLI)
- Claude Code
- Other coding agents with code execution capabilities
Don’t have a coding agent yet?
- GitHub Copilot is free to start with a personal GitHub account. Install the Copilot extension in VS Code, or install the GitHub Copilot CLI and sign in from a terminal.
- Claude Code is a terminal-based coding agent from Anthropic. Its getting started guide covers installation.
- If your organization already provides an enterprise-hosted coding agent, use that instead, especially when working with real HR data, since it keeps your data inside your organization’s boundary.
Once installed, open the agent in a folder that has R or Python available, then continue with the workflow below.
Workflow
- Export your data. Run a person query (or other query type) from the Viva Insights Analyst portal and download the CSV.
- Pick a prompt card. Browse the Prompt Library for the analysis task that matches your use case.
- Review the schema docs. Check Schema Documentation to understand the structure of your exported data: column definitions, expected granularity, and common pitfalls.
- Open your coding agent. Launch GitHub Copilot, Claude Code, or a similar tool in a workspace with R or Python available.
- Paste the prompt. Copy the prompt text from the card, point it at your data file, and let the agent generate the output.
- Review and iterate. Check the output against the documented failure modes and adaptation notes. Refine as needed.
Tips for working with coding agents
- Be specific about your data. Tell the agent the file name, column names, and date range. The more context you give, the better the output.
- Iterate in small steps. If the output is not right, ask the agent to fix one thing at a time rather than re-generating everything.
- Validate the output. Spot-check row counts, date ranges, and aggregation logic. Coding agents can make plausible-looking mistakes.
- Use the vivainsights packages. The R and Python packages handle common data validation and visualization tasks. Prompts that reference these functions tend to produce cleaner code.
See “Responsible use & data privacy” below before you work with real HR data.
Responsible use & data privacy
- Suppress small groups. Apply a minimum group-size threshold to every breakdown, segment, and chart — Viva Insights typically uses 5–10. Raise it for smaller organizations.
- Never expose individuals. Do not print raw UPNs or email addresses; hash, truncate, or report only aggregates. Person query
PersonIdis already de-identified, but PurviewUserIdis not. - Analyze groups, not individuals. These outputs are for understanding cohorts and trends — not for evaluating, ranking, or monitoring named employees.
- Keep data in approved environments. Don't paste sensitive HR data into cloud agents unless your organization's policies allow it; prefer local or enterprise-hosted tools. Validate every agent output before sharing.
Quick links
Contributing
See the Contributing guide for how to add prompt cards and schema documentation.
This project uses the Microsoft Open Source Code of Conduct and requires a Contributor License Agreement for all contributions.