win-loss-review

name	win-loss-review
description	Review win/loss evidence; avoid weak causal claims.
metadata	{"short-description":"Analyze win-loss evidence and learning"}

Win-Loss Review

Outcome

A balanced review of outcomes, reported reasons, customer evidence, patterns, and actions for improvement.

CRM-neutral operating contract

• Discover available CRM, communication, calendar, knowledge, and file capabilities before choosing a retrieval plan. If no live CRM is available, use user-supplied exports when that still satisfies the request; never imply a live write is possible.
• Map records by meaning, not vendor labels: organization, person, lead, opportunity, activity, product, service record, user or team, and knowledge item. Inspect schemas and custom fields, preserve native IDs, stages, currencies, timezones, and fiscal periods.
• Keep observed facts, derived conclusions, and missing information distinct. Anchor consequential claims to record IDs, fields, timestamps, or named sources, and state access or freshness limits.
• Start read-only. Before creating, updating, assigning, sending, or scheduling, show the exact proposed action and obtain confirmation unless the current request already authorized that exact mutation.
• Obey connected-system permissions, resolve ambiguous records or people instead of guessing, check for duplicates before creation, and report partial failures without repeated retries.

Workflow

1. Resolve the user, target records, requested scope, reporting window, timezone, and business objective. Ask only for missing details that materially change the result.
2. Retrieve the minimum authorized evidence needed from the following inputs: Closed opportunities, values, segments, stages, cycle times, reported reasons, activities, stakeholders, transcripts, feedback, competition, and outcome dates.
3. Normalize relevant entities and fields while retaining native record identifiers and source timestamps.
4. Apply the analysis rules below. When evidence conflicts, show the conflict rather than averaging it away.
5. Deliver the required output in a compact form suited to the scope. Put urgent or decision-relevant items first.

Analysis rules

1. Define cohort, time window, segments, inclusion rules, currency treatment, and data completeness before comparing outcomes.
2. Separate reported reason, observed evidence, inference, and unknown; multiple contributing factors may coexist.
3. Compare like with like and show sample sizes, missingness, and survivorship or response bias.
4. Treat correlations as hypotheses unless stronger evidence supports causality and include positive and disconfirming examples.

Required output

• Cohort and data-quality note
• Outcome metrics
• Win and loss themes
• Stage and process patterns
• Representative evidence
• Recommended experiments or process changes

Actions and boundaries

Remain read-only; taxonomy or record corrections require review and confirmation.