• BUDGET
  • TIMELINE
  • REPORTS
  • HUMAN

How to compare planned vs actual hours with your AI

Connect Runn to your AI client once. From there, you can audit project budgets and timelines without manual data exports.

Ask AI about this page

Short answer

How do I compare planned vs actual hours with my AI?

Your AI pulls forecasted work and logged timesheets from Runn to find discrepancies. You get a clear view of where projects are over budget or falling behind schedule.

The outcomes.

Where your data lands.

The AI organizes the comparison into these specific outcomes.

BUDGET

Identify overruns

The AI compares planned hours against logged entries. You see exactly which projects are burning through their budget too fast.

TIMELINE

Spot schedule drifts

By looking at phase progress, your agent identifies where work is taking longer than the original forecast.

REPORTS

Get summary tables

The AI compiles the raw data into clean lists or tables. You can then ask for specific breakdowns of certain teams or clients.

HUMAN

Review and adjust

The AI cannot change your Runn data. You must manually update forecasts or timesheets in Runn once you identify an issue.

The workflow

What your AI does when the request arrives.

The AI performs these steps to bridge the gap between your plan and reality.

  1. Fetch project scope

    The AI pulls your current project list to establish the baseline for the audit.

    list_projects

  2. Isolate project phases

    It drills down into specific project stages to see how much time was allocated to each part of the work.

    list_phases

  3. Pull logged time

    The agent retrieves the actual hours recorded in timesheets to compare against those phase estimates.

    list_actuals

  4. Calculate variances

    The AI compares the three data points to highlight where the actual hours exceed the planned hours.

    list_actuals

Try it

Copy these to start.

Use these prompts to begin your audit.

Starting points

These are starting points. Swap out the project names or client names with your own.

Runn API Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_R01M56JJJpYIg7GIrR6EtNtq96sDdR9Exy9H3SjK/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Runn API capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "runn-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_R01M56JJJpYIg7GIrR6EtNtq96sDdR9Exy9H3SjK/mcp"
    }
  }
}
Copy into chat04

  • Compare the planned hours versus actual hours for the Apollo Project.

  • Which phases in the Website Redesign project are currently over budget?

  • Show me a list of all projects where actual hours have exceeded the forecast.

  • Summarize the budget status for the Q3 Marketing campaign.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Runn once, then ask.

Just link your account. Your credentials stay encrypted, and you can immediately start asking questions about your project data.

Connect Runn to your AI

FAQ

How this task behaves.

  • 01

    Can the AI change my project timelines in Runn?

    No. The AI can only read your project, phase, and actual data. You have to make all changes directly in Runn.

  • 02

    Does the AI see all my Runn data?

    The AI only sees the data it needs to answer your specific question using the available tools.

  • 03

    Can I ask for a comparison of specific team members?

    Yes, as long as their hours are logged in the actuals data the AI can access.

  • 04

    Will the AI delete any of my timesheet entries?

    No. This MCP does not have any tools that allow for deleting or modifying your data.

  • 05

    How does the AI know which project I am talking about?

    It uses the project list to match your natural language request to the correct project ID in Runn.

  • More questions about Runn? The Connector page answers them. See everything the Runn Connector can do

Connect Runn API to Claude, Cursor, ChatGPT & more