Drawing Revision Impact Agent
The Drawing Revision Impact Agent compares each new drawing revision with the one before it and lists every change, including the ones that were never clouded. It maps each change to the affected BoQ items, estimates the quantity and cost difference, and flags changes that should be treated as variations or compensation events.
Ideal forQuantity surveyors
The difference
From 2-4 hours per revision to 20-30 minutes
Your quantity surveyor sees the cost of every revision on the day it is issued, not at final account.
Done by hand
2-4 hours per revision
With the Vanine agent
20-30 minutes
Time returned to your team
85%
Indicative figures. We measure your own baseline in the first fortnight so the numbers you see are yours.
No more unclouded changes
Revisions often change more than the clouds show. The agent compares the whole sheet, so quiet scope additions are caught.
Cost known on issue
Each revision arrives with a priced impact, so the team can raise a variation or query before the work is built.
A cleaner final account
Every revision is traced to its cost effect as the project runs, so there is far less to argue about at the end.
Capabilities
Every drawing revision compared, measured and priced before it becomes free work.
Built for quantity surveyors, contracts managers and design managers at South African contractors and consultancies handling frequent drawing issues on building and civil projects.
Revision comparison
Compares successive revisions of drawings and models and lists every added, removed or changed element.
Change classification
Separates design development within the original scope from genuine changes to scope.
BoQ mapping
Links each change to the BoQ items it affects, including provisional sums and rate-only items.
Quantity and cost estimate
Estimates the quantity difference and prices it from contract rates or pro-rata rates.
Variation flagging
Flags changes that should be raised as variations, instructions requested or compensation events.
Revision log
Keeps a log of every revision with its cost impact for the cost report and final account.
How it works
From your systems to a result you sign off
Your quantity surveyor confirms every measured change and decides which are raised with the principal agent.
Connect the places your drawings already live.
Drawing issues and transmittals from Aconex, Procore or SharePoint, models in IFC or Revit, and the priced BoQ from Candy or WinQS. Already use something else? We connect that too.
- OpenAI Frontier
- Your own AI platform or models
- Microsoft 365 (Teams, SharePoint, Outlook, Excel)
- Copilot Studio
- Procore and Aconex
- Revit and IFC models
- Candy and WinQS
- SharePoint and Excel
Runs each time a new revision is issued through document control, or on request in Teams or OpenAI Frontier.
A revision impact report in Excel, marked-up comparison sheets in PDF, and variation flags passed to the Variations and Claims Agent.
Step by step
- 01
A new drawing revision is issued through document control.
- 02
The agent compares it with the previous revision and lists every change.
- 03
It classifies each change and maps it to BoQ items.
- 04
It estimates the quantity and cost difference.
- 05
Your quantity surveyor confirms the measurement and decides on variations.
- 06
The revision log and cost report update.
Deployment
Runs inside the tools your team already uses
The same agent and the same cited output, delivered three ways: through the AI assistant you have rolled out, on a model you host yourself, or inside your own software.
In the frontier assistant you already pay for
We publish the agent as an MCP server. Add it as a connector and your team calls it from the chat they use every day, with no new tool to learn.
"What changed between Rev B and Rev C?"
- set
- Structural, Level 2
- revisions
- B to C
On a model you host yourself
Run the agent on open-weight models in your data centre or private cloud. Your drawings never leave your network, which keeps POPIA and data residency straightforward.
- Llama
- Mistral
- Ollama
- or any OpenAI-compatible endpoint
Inside your own software
Trigger a run from your own workflows, and push the finished output into your ERP, GRC or reporting systems. We build the integration with your team.
- REST API
- Webhooks
- Batch jobs
- Embeddable review panel
Governed the same way, every route
Whichever way your team reaches the agent, identity, permissions and audit stay with your existing controls.
- Single sign-on through Entra ID, Okta or Google Workspace
- Reads only the documents each user is already allowed to open
- Every tool call written to an audit log you can export
How we deliver it
One agent, three ways to hold it
Start where your team already works, then take it as far into your systems as the value justifies.
DATA SECURITY & PRIVACY
Your drawings stay yours.
The agent runs inside your tenancy, reads only what each task needs, and never trains on your drawings. Every step is logged so your auditors can see exactly what it touched.
Built for regulated work.
+YOUR DRAWINGS NEVER LEAVE YOUR ENVIRONMENT
More agents
More agents we build for South African enterprises
Each one is built on the same foundation: your documents, your rules, and your people signing off.
Precision AI for Institutional Workflows
