Specification and Terms of Reference Agent
The Specification and Terms of Reference Agent drafts specifications, terms of reference and evaluation criteria from the end-user's needs, previous tenders and your SCM policy. It keeps requirements objective, measurable and non-restrictive, aligned to the PPPFA and Preferential Procurement Regulations 2022, and ready for the Public Procurement Act as it comes into force.
Ideal forSupply chain management teams
The difference
From 16-24 hours per specification to 4-6 hours
Specifications reach the committee sooner and in better shape, shortening the time from need to advertised tender.
Done by hand
16-24 hours per specification
With the Vanine agent
4-6 hours
Time returned to your team
75%
Indicative figures. We measure your own baseline in the first fortnight so the numbers you see are yours.
Fewer challenges and cancellations
Vague or brand-specific specifications invite complaints, poor bids and cancelled tenders. The agent flags restrictive wording and unclear deliverables before the tender is advertised.
Criteria evaluators can apply
Functionality criteria without clear scoring guidance lead to inconsistent scores. The agent drafts measurable criteria with scoring indicators the committee can apply consistently.
Built for audit scrutiny
Irregular expenditure findings often trace back to flawed procurement documents. Aligning specifications to your SCM policy and the PPPFA from the start protects the process.
Capabilities
Clear, fair specifications that attract the right bids and survive audit.
Built for bid specification committees, SCM practitioners, end-user departments and procurement managers in national and provincial departments, municipalities, SOEs and private-sector procurement teams.
Needs to specification
Turns end-user requirements, meeting notes and previous tenders into a structured specification or terms of reference with scope, deliverables and timelines.
Restrictive wording checks
Flags brand names, unnecessary experience thresholds and requirements that could unfairly limit competition, and suggests neutral alternatives.
Evaluation criteria design
Drafts functionality criteria, weightings and scoring guides, and sets out the applicable 80/20 or 90/10 preference point system and specific goals.
Policy alignment
Checks the draft against your SCM policy, the PPPFA and Preferential Procurement Regulations 2022, and applicable Treasury instructions.
Returnables and conditions
Lists the required SBD forms, CSD registration, tax compliance, CIDB grading and any local content or designated sector requirements that apply.
Public procurement act readiness
Tracks how your documents will need to change as the Public Procurement Act and its regulations are implemented, so you can adapt early.
How it works
From your systems to a result you sign off
The bid specification committee reviews and approves the specification, and the accounting officer or delegate authorises the tender.
Connect the places your procurement documents already live.
End-user requirements, previous tenders and your SCM policy and templates in SharePoint or your procurement system. Already use something else? We connect that too.
- OpenAI Frontier
- Your own AI platform or models
- Microsoft 365 (Teams, SharePoint, Outlook, Excel)
- Copilot Studio
- SharePoint SCM policy and tender libraries
- SAP Ariba and Coupa sourcing
- Oracle and SAP procurement modules
Runs on request in Teams, Word or OpenAI Frontier, using the models your organisation approves.
A draft specification or terms of reference in your template, with an evaluation criteria schedule and a policy alignment note.
Step by step
- 01
The end-user submits a need or request for a specification.
- 02
The agent gathers requirements, previous tenders and the relevant SCM policy.
- 03
It drafts the specification, terms of reference and evaluation criteria.
- 04
It flags restrictive wording and checks alignment to the PPPFA and your policy.
- 05
The bid specification committee reviews, amends and approves the document.
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.
"Draft the ICT support terms of reference"
- request
- ICT-2026-07
- policy
- SCM Policy 2025
On a model you host yourself
Run the agent on open-weight models in your data centre or private cloud. Your procurement documents 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 procurement documents stay yours.
The agent runs inside your tenancy, reads only what each task needs, and never trains on your procurement documents. Every step is logged so your auditors can see exactly what it touched.
Built for regulated work.
+YOUR PROCUREMENT DOCUMENTS 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
