Programme and Delay Analysis Agent
The Programme and Delay Analysis Agent reads Primavera P6 or MS Project programmes and updates, compares the baseline to actual progress and identifies critical path movements and delay events. It drafts delay analysis narratives that link each delay to its cause, supporting extension of time claims, NEC programme submissions and management reporting.
Ideal forPlanners
The difference
From 2-3 days per monthly update to 3-5 hours
Your planners and project managers act on delays while there is still time to recover, and claims are backed by a clear analysis.
Done by hand
2-3 days per monthly update
With the Vanine agent
3-5 hours
Time returned to your team
80%
Indicative figures. We measure your own baseline in the first fortnight so the numbers you see are yours.
Spot slippage while you can still act
Comparing monthly updates by hand is slow, so problems surface late. The agent highlights critical path changes as soon as a new update arrives.
Delay claims built on evidence
Extension of time claims need a clear link between cause and effect. The agent ties delay events to programme impact and site records.
Clear reporting for clients and funders
Principal agents, employers and funders want to understand why dates are moving. The agent turns programme data into plain-language narratives.
Capabilities
See critical path movement early and explain delay with confidence.
Built for planners, project managers, contractors' commercial teams, principal agents and claims consultants managing programmes on South African construction projects.
Programme import
Reads Primavera P6 XER and XML files and MS Project files, including baseline and each update.
Baseline versus actual
Compares planned and actual start, finish and duration for every activity and summarises variances by area and trade.
Critical path tracking
Identifies changes to the critical path and near-critical paths between updates, and shows float erosion.
Delay event identification
Links activity delays to site diaries, instructions, weather records and correspondence to identify probable causes.
Programme quality checks
Flags open ends, constraints, negative float, missing logic and out-of-sequence progress that weaken the programme.
Delay narratives
Drafts delay analysis narratives using recognised methods such as time impact or windows analysis, for the planner and claims team to finalise.
How it works
From your systems to a result you sign off
Your planner reviews the analysis and the commercial manager decides what is submitted. Extensions of time are granted by the principal agent or project manager under the contract.
Connect the places your programme data already live.
Primavera P6 or MS Project baseline and update files, plus site diaries, instructions and correspondence from Procore, Aconex or SharePoint. Already use something else? We connect that too.
- OpenAI Frontier
- Your own AI platform or models
- Microsoft 365 (Teams, SharePoint, Outlook, Excel)
- Copilot Studio
- Primavera P6
- MS Project
- Procore and Aconex
- Power BI
Runs each time a programme update is issued or on request in Teams or OpenAI Frontier, using the models your organisation approves.
Variance reports, critical path comparisons and draft delay narratives in Word, Excel or Power BI.
Step by step
- 01
A new programme update is issued.
- 02
The agent imports the baseline and update files.
- 03
It compares progress, tracks the critical path and checks programme quality.
- 04
It links delays to site records and identifies probable causes.
- 05
It drafts the variance report and delay narrative.
- 06
Your planner reviews and finalises before it is issued.
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.
"Compare the update to the baseline"
- programme
- Primavera P6
- update
- March
On a model you host yourself
Run the agent on open-weight models in your data centre or private cloud. Your programme data 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 programme data stay yours.
The agent runs inside your tenancy, reads only what each task needs, and never trains on your programme data. Every step is logged so your auditors can see exactly what it touched.
Built for regulated work.
+YOUR PROGRAMME DATA 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
