Unsolicited Proposal Screening Agent
The Unsolicited Proposal Screening Agent assesses unsolicited PPP proposals against the Treasury Regulation 16 framework, which formally recognises them from June 2025, and against your institution's priorities. It checks completeness, innovation, value for money indicators and risks, and prepares a screening note so your institution can decide whether to consider the proposal formally.
Ideal forPPP units
The difference
From 15-25 hours per proposal to 2-4 hours
Proponents receive timely, well-reasoned responses and your team keeps its capacity for the proposals worth pursuing.
Done by hand
15-25 hours per proposal
With the Vanine agent
2-4 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.
A consistent front door
Unsolicited proposals arrive in every shape and quality. The agent applies the same framework to each, so proponents are treated fairly and decisions are documented.
Priorities come first
Each proposal is tested against your institution's plans and priority sectors such as transport, health, and water and sanitation, so effort goes to proposals that fit.
Risks spotted early
Affordability, contingent liabilities and development fee expectations are flagged at screening, before your institution commits time or signals support.
Capabilities
Screen unsolicited PPP proposals quickly, fairly and on the record.
Built for PPP units, infrastructure departments, municipal project offices, GTAC advisers and accounting officers receiving unsolicited PPP proposals.
Completeness check
Checks the submission against the information your institution requires, including the proponent's profile, project concept, technical approach, indicative costs and funding.
Framework alignment
Assesses the proposal against the Treasury Regulation 16 unsolicited proposal provisions, including innovation and development fee recovery considerations.
Strategic fit review
Tests alignment with your institution's strategic plan, infrastructure plans and priority sectors, and notes overlap with projects already in your pipeline.
Value for money indicators
Summarises early indicators of value for money and affordability, and highlights where a full feasibility study would need further evidence.
Risk and liability flags
Identifies risks the proposal shifts to government, contingent liabilities, land and regulatory dependencies and any conflicts of interest to investigate.
Screening note drafting
Drafts a structured screening note with findings, open questions for the proponent and options for the accounting officer's consideration.
How it works
From your systems to a result you sign off
Your PPP unit reviews the findings and the accounting officer decides whether the proposal proceeds to formal consideration.
Connect the places your proposals already live.
Proposal documents from your intake mailbox or register, plus institutional plans, pipeline lists and budget data from SharePoint and Excel. Already use something else? We connect that too.
- OpenAI Frontier
- Your own AI platform or models
- Microsoft 365 (Teams, SharePoint, Outlook, Excel)
- Copilot Studio
- Proposal intake mailboxes and document registers
- Institutional plans and budget data in Excel
Runs in Teams, Copilot Studio, OpenAI Frontier or your own AI platform, using the models your institution approves.
A completeness checklist, risk register and draft screening note in Word, filed in SharePoint.
Step by step
- 01
An unsolicited proposal is logged in your intake register or mailbox.
- 02
The agent checks completeness and requests missing information through your team.
- 03
It assesses framework alignment, strategic fit, value for money indicators and risks.
- 04
It drafts the screening note and questions for the proponent.
- 05
Your PPP unit reviews and finalises the note.
- 06
The accounting officer decides on formal consideration.
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.
"Does it match our infrastructure plan?"
- proposal
- UP-2026-03
- framework
- Treasury guidance
On a model you host yourself
Run the agent on open-weight models in your data centre or private cloud. Your proposals 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 proposals stay yours.
The agent runs inside your tenancy, reads only what each task needs, and never trains on your proposals. Every step is logged so your auditors can see exactly what it touched.
Built for regulated work.
+YOUR PROPOSALS 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
