Plan Submission Pre-Check Agent

The Plan Submission Pre-Check Agent checks building plans against the deemed-to-satisfy rules of the National Building Regulations and SANS 10400, the zoning parameters for the erf, and the receiving municipality's submission checklist. It lists every likely rejection point and missing document, and which professional on the team must resolve it, before the plans are lodged.

Ideal forArchitects

The difference

From 1-2 days per submission check to 2-3 hours

Your architects lodge complete submissions the first time, instead of losing months to rejection and resubmission.

Done by hand

1-2 days per submission check

With the Vanine agent

2-3 hours

Time returned to your team

85%

Indicative figures. We measure your own baseline in the first fortnight so the numbers you see are yours.

Fewer rejections

Most rejections are for missing documents, zoning breaches or simple regulation points. The agent catches them before the municipality does.

Months saved on the programme

Every resubmission cycle adds weeks or months. A complete first submission protects site start.

Each metro's rules applied

Johannesburg, Tshwane, Cape Town and eThekwini each ask for different things. The agent checks against the right checklist.

Capabilities

Building plans checked before the municipality rejects them.

Built for architects, development managers and project managers preparing building plan submissions to South African municipalities.

Zoning parameters

Checks coverage, floor area ratio, height, building lines and parking against the zoning scheme and title deed conditions.

Deemed-to-satisfy checks

Checks drawings against the deemed-to-satisfy rules of SANS 10400, including fire, accessibility, energy, ventilation and structural parts.

Rational design flags

Lists elements that need a rational design and a competent person's appointment and sign-off.

Submission completeness

Checks forms, appointments, certificates and drawings against the municipality's submission checklist.

Responsibility list

Assigns each issue to the architect, engineer, fire consultant or other professional responsible.

Pre-submission report

Produces a report of issues ranked by rejection risk.

How it works

From your systems to a result you sign off

The responsible registered professionals resolve each issue and sign the submission. The agent never certifies compliance.

AutodeskSharePointOutlookTeamsExcelWord
Any system you use
Connects

Connect the places your design records already live.

Drawings and design reports from SharePoint, Aconex or Revit, zoning data from municipal GIS, and the title deed and site information. Already use something else? We connect that too.

  • OpenAI Frontier
  • Your own AI platform or models
  • Microsoft 365 (Teams, SharePoint, Outlook, Excel)
  • Copilot Studio
  • Revit and IFC models
  • Procore and Aconex
  • Municipal GIS and zoning data
  • Licensed standards library
Works in

Runs before each building plan submission and resubmission, or on request in Teams or OpenAI Frontier.

Zoning parameters
Deemed-to-satisfy checks
Rational design flags
Submission completeness
Responsibility list
Pre-submission report
Delivers to

A pre-submission report in Word, a responsibility list in Excel, and status updates to the Statutory Approvals Tracker Agent.

Step by step

  1. 01

    The professional team assembles the submission set.

  2. 02

    The agent reads the drawings, reports, site data and title deed.

  3. 03

    It checks zoning parameters and deemed-to-satisfy rules.

  4. 04

    It checks completeness against the municipality's checklist.

  5. 05

    It reports issues, ranked by rejection risk, with owners.

  6. 06

    The professionals resolve the issues and lodge the submission.

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.

Model Context Protocol

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.

Adopting frontier AI across your teams
Called from ClaudeMCP connected

"Does the design comply with the zoning?"

Toolplan_submission_pre_check.check_zoning
municipality
City of Johannesburg
scope
Zoning, SANS 10400
Returned2 breachesEvery finding linked to its source document
Self-hosted

On a model you host yourself

Run the agent on open-weight models in your data centre or private cloud. Your design records never leave your network, which keeps POPIA and data residency straightforward.

  • Llama
  • Mistral
  • Ollama
  • or any OpenAI-compatible endpoint
Sovereign AI on your infrastructure
Bespoke systems

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
Custom integrations from our software factory
Governance

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 your data is handled

DATA SECURITY & PRIVACY

Your design records stay yours.

The agent runs inside your tenancy, reads only what each task needs, and never trains on your design records. Every step is logged so your auditors can see exactly what it touched.

Built for regulated work.

+
WHAT THE AGENT KEEPSONLY THE OUTPUTENCRYPTED AT REST0 BIT AES0% DELETABLE0 TRAINING RUNS

YOUR DESIGN RECORDS NEVER LEAVE YOUR ENVIRONMENT

Precision AI for Institutional Workflows

Build once.Deploy across teams.Improve over time.