Rate Library and Benchmark Agent
The Rate Library and Benchmark Agent turns your archive of priced BoQs, tenders and final accounts into a searchable rate library, normalised to standard item descriptions and escalated to today's prices. It benchmarks new estimates and tender submissions against that library and flags rates that are out of range, front-loaded or unbalanced.
Ideal forQuantity surveyors
The difference
From 1-2 hours per rate check to minutes
Your estimators and quantity surveyors price from real evidence on every item, not from memory and old spreadsheets.
Done by hand
1-2 hours per rate check
With the Vanine agent
minutes
Time returned to your team
90%
Indicative figures. We measure your own baseline in the first fortnight so the numbers you see are yours.
Years of pricing put to work
Most firms hold hundreds of priced BoQs they never search. The agent turns them into an asset.
Rates brought to today
Every historical rate is escalated with the relevant indices, so a 2021 rate can be compared fairly with a 2026 one.
Unbalanced bids caught
Front-loaded preliminaries and inflated early-stage rates are flagged before a tender is recommended.
Capabilities
Your own past projects, turned into a rate library you can price from.
Built for quantity surveyors, estimators and cost managers at South African consultancies, contractors and developers with a history of priced work.
Historical rate capture
Extracts rates from priced BoQs, tenders and final accounts in Candy, Excel and PDF.
Description normalisation
Maps varied item descriptions to standard items under the applicable system of measurement.
Escalation to today
Escalates each rate to current prices using the relevant indices.
Context filters
Filters rates by region, project type, size, date and contract form.
Estimate benchmarking
Compares a new estimate item by item with the library and flags outliers.
Unbalanced rate detection
Flags front-loaded and unbalanced rates in tenderer submissions.
How it works
From your systems to a result you sign off
Your quantity surveyor or estimator decides every rate. The agent shows the evidence behind each benchmark.
Connect the places your pricing records already live.
Priced BoQs, tenders and final accounts from Candy, WinQS and SharePoint archives, plus escalation indices. Already use something else? We connect that too.
- OpenAI Frontier
- Your own AI platform or models
- Microsoft 365 (Teams, SharePoint, Outlook, Excel)
- Copilot Studio
- Candy and WinQS
- BuildSmart
- SharePoint and Excel
- Stats SA indices
Runs once to build the library and then on each new priced document, or on request in Teams or OpenAI Frontier.
A rate library in Excel or your own database, benchmark reports for estimates and tenders, and outlier flags passed to the Tender Adjudication Report Agent.
Step by step
- 01
The agent reads your archive of priced documents.
- 02
It extracts and normalises every rate with its project context.
- 03
It escalates each rate to today's prices.
- 04
A new estimate or tender is loaded for benchmarking.
- 05
It flags outliers and unbalanced rates with comparable evidence.
- 06
Your quantity surveyor decides and records the outcome.
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.
"Build the library from our priced archive"
- section
- Concrete, formwork and reinforcement
- region
- Gauteng
On a model you host yourself
Run the agent on open-weight models in your data centre or private cloud. Your pricing records 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 pricing records stay yours.
The agent runs inside your tenancy, reads only what each task needs, and never trains on your pricing records. Every step is logged so your auditors can see exactly what it touched.
Built for regulated work.
+YOUR PRICING RECORDS 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
