---
name: proposal-assumption-check
description: Audits a sales proposal for hidden assumptions, scope gaps, inconsistent promises, pricing mismatches, dependencies, and unsupported claims. Use before commercial review for proposal QA, quote review, scope validation, or deal risk reduction.
license: Apache-2.0
metadata:
  adlass.categories: "sales-crm/quotes-proposals, sales-crm/pipeline"
  adlass.industries: ""
  adlass.tags: "proposal-review, assumptions, scope, pricing, commercial-risk, quality"
  adlass.adaptation: "reference-doc"
  adlass.source: "original"
  adlass.version: "1"
---

# Proposal assumption check

## Purpose

Inspect a proposal against its requirements, approved commercial sources, and internal consistency so reviewers can resolve risks before a customer sees it.

## Scope

Requirements coverage, scope, deliverables, dependencies, exclusions, dates, pricing, discounts, claims, service levels, customer responsibilities, and open approvals.

**Excluded:** rewriting the proposal, approving terms, sending it, or providing legal advice.

## Data basis

- Proposal document supplied as a run input.
- Requirements, pricing policy, offer catalogue, and approved claims in scope.

## Result

A finding sheet and decision memo with severity, citation, and correction suggestion.

## Quality criteria

- Every finding cites proposal section and source rule.
- Arithmetic and repeated values reconcile.
- Missing requirements are recorded explicitly.
- Severity uses the configured vocabulary.
- No issue is introduced without evidence.

## Instructions

Check material customer commitments before style. Distinguish contradiction, omission, unsupported claim, and review preference. Use approved thresholds and terms only. Quote decisive wording where a reviewer needs to locate the issue. Do not silently fix the source document.

## Adapt before use
Keep a clear audit trail throughout the run. Use the source wording and field values that support each material conclusion, and retain uncertainty when the evidence does not decide the issue. Separate a missing record from a negative result and a contradictory record from an exception. Prefer a short, prioritised result over unsupported completeness. Check that counts, identifiers, dates, and labels agree across the written result and the structured output. When a rule, source, or mapping is unavailable, name the limitation and explain how it affects interpretation. Do not silently infer ownership, approval, timing, or business intent. Keep commercial risk separate from editorial preference.

- Add approved proposal template, claims, pricing and commercial rules.
- Define severity and mandatory-review criteria.
- Map required sections and customer requirements.