Workflow design · scope to your operationFrom trigger to finished work
- RFQ + scope
- collect bids
- extract inclusions/exclusions
- normalise units
- flag missing scope
- clarification drafts
- comparable total view
- approved supplier selection
The rules that matter
Retain original bids. Never silently impute excluded work or select a contractor on AI output. Use visible assumptions and approved adjustments.
When the normal path breaks
Different units; alternative specifications; excluded access costs; outdated bid; conditional price; non-comparable scope.
Uncertain inputs go to an assigned owner with the source, reason and next decision. Failed writes are reconciled before retrying, so a recovered connection does not create a duplicate order, payment or stock movement.
How we would measure it
Comparison hours/bid round; clarification cycles; omissions found; procurement cycle time.
Sample representative work before the build, including difficult cases. Compare the same task mix after launch; include review, exception handling and system upkeep in the time used.
Start with one accountable slice
Map the first input, the final accepted result and who can approve it. Agree source systems, read/write access, rules, exception ownership and acceptance checks. Run representative normal, failure and recovery cases before expanding across teams.
What makes this suitable for larger teams?
Role-based access, separation of preparation and approval, versioned rules, an action history, duplicate protection, reconciliation, alerts and a named recovery owner. Private deployment or customer-controlled infrastructure can be scoped where needed. These are design requirements to validate, not an unsupported promise of perfect source data or regulatory compliance.
Before you buildQuestions about this workflow
Specific answers to help you judge the fit, the information needed and the decisions your team keeps.
How can you compare bids that include different work?
Start with the same request-for-quote scope, then map each bid’s inclusions, exclusions and quantities against it. Missing scope remains visible. Any allowance used to make totals comparable must be an explicit approved assumption, with the original supplier figure preserved beside the adjusted comparison.
What bid formats and reference information do we need?
Bring the scope or bill of quantities, several representative bids and your usual clarification notes. PDFs, documents or spreadsheets can be assessed as inputs, but extraction depends on their structure and quality. Product alternatives, units, taxes and delivery terms need reviewable fields, not just one total.
Will the system pick the cheapest subcontractor for us?
It should present a comparable view and flag gaps, conditional prices or unusual exclusions for the procurement team. Selection also depends on capability, availability and your approved criteria. The decision stays with the authorised person rather than being inferred from the lowest extracted total.
What if a supplier revises only one part of its quote?
Keep the revision connected to the previous bid and show the changed lines, conditions and validity date. Do not combine an old scope with a new total unless the supplier confirms that basis. Unresolved differences can become specific clarification requests for a reviewer to approve.
How would we prove the comparison process is useful?
Replay a completed bid round against the team’s reviewed comparison, including an apparent low bid with exclusions. Measure preparation hours, clarification cycles and omissions found. Keep review time in the comparison, and do not claim procurement savings simply because the displayed headline total is lower.