Check model data against project rules before it reaches drawings

Short answer

Use Copilot in Excel or Gemini in Google Sheets: Export model data to a sheet and have the AI write the rule checks (missing marks, wrong types, empty parameters) as formulas or filters. Design data platforms connect Revit, Rhino and IFC, validate each model version, and let you ask questions of live model data. A person still checks: flagged items in the model; rules only catch what you defined.

AI tie-in

Tool: Copilot in Excel or Gemini in Google Sheets

Export model data to a sheet and have the AI write the rule checks (missing marks, wrong types, empty parameters) as formulas or filters.

Prompt 1

This sheet is a model export with columns [list]. Add a column that flags rows where [rule 1], [rule 2], [rule 3], and a summary of counts per rule.

Human check: Flagged items in the model; rules only catch what you defined.

The problem

Catch model problems before they reach drawings. This is a common, time-consuming task for a structural engineer.

What this workflow does

Design data platforms connect Revit, Rhino and IFC, validate each model version, and let you ask questions of live model data.

How it works: AI drafts or analyzes. A person operates the tools, checks the work, and takes action.

Your checkpoint: Validation only checks the rules you write. It does not check structural adequacy.

Before you start

Access to the named tool; confirm license, version and cost with the vendor.
A small, non-confidential sample to try the workflow on first.
A qualified person to review the output before it is used.

Tools and access

Speckle

Follow the steps

Connect your Revit or analysis model to Speckle.
Set up validation rules (missing parameters, naming, untagged members).
Review the report on every new version.
Ask the AI questions like which beams lack a size.

Try a small example

Replace the bracketed fields with your own project details. No tested sample run is published for this workflow yet.

Sample input

Fill in the bracketed [fields] in the text below with your project data.

Starter prompt

From this exported member schedule, list members missing size, material, or level, and any duplicate marks: [paste CSV]

Expected output

Not published yet. Treat any output as a draft and check it against the source documents.

Check the result

Every value, citation or quantity traces back to a source document.
Missing information is marked as missing, not filled in.

Limits and recovery

Validation only checks the rules you write. It does not check structural adequacy.
Check your organization’s data policy before sharing project files with third-party tools.

Stop or switch when: The source cannot be verified, permissions are missing, or the result contains unsupported facts.

Frequently asked questions

How does AI help with this?

Copilot in Excel or Gemini in Google Sheets: Export model data to a sheet and have the AI write the rule checks (missing marks, wrong types, empty parameters) as formulas or filters. A person still checks: Flagged items in the model; rules only catch what you defined.

How do I check model data against project rules before it reaches drawings?

Connect your Revit or analysis model to Speckle. Set up validation rules (missing parameters, naming, untagged members). Review the report on every new version. The full step list is above.

Does this use an AI agent or regular software?

It is labeled AI assists: AI drafts or analyzes. A person operates the tools, checks the work, and takes action.

What tools do I need?

Speckle. Confirm license, version and cost with the vendor, and try it on a small non-confidential sample first.

Has this workflow been tested?

Workflow guide · not independently tested. It is written from vendor documentation and practitioner use.

Evidence and maintenance

Written from vendor documentation and practitioner use. Labels apply to the steps described here, not every feature of a product. Links were checked when the page was written.

Speckle (vendor site)