Deal Qualification Scorecard

The problem this kills

Your forecast is built on vibes. A rep marks a deal "Commit," the manager nods, and three weeks later it slips - because nobody had actually confirmed there was an economic buyer, a real timeline, or a budget. Every rep "qualifies" differently, the criteria live in someone's head, and the only record of why a deal was trusted is a hopeful note in the CRM.

A qualification framework like MEDDIC or BANT is supposed to fix this, but a PDF of criteria doesn't enforce anything. Reps skip the hard questions, managers can't see the gaps, and weak deals sail straight into the forecast.

This tool turns your framework into a live checklist that scores each deal, refuses to hide the gaps, and puts a human approval gate between "the rep is optimistic" and "this is officially Commit."

What you'll build

A simple internal web app where:

• Reps open a deal and complete a guided scorecard - your exact criteria, prompts, and scoring scale.
• The app computes a qualification score and a gap list automatically (e.g., "No economic buyer identified," "No confirmed timeline").
• Key criteria require evidence or notes - no checking a box without saying why.
• A manager reviews the score and either approves the deal into a higher forecast category (like Commit) or sends it back.
• Everything is logged: who scored, who approved, what changed, and when.
• You export a scored CSV - deal, score, gaps, forecast category - in the exact columns your CRM or board expects.

What's inside the Implementation Plan

The plan is a complete, paste-and-go runbook for an AI coding agent (Claude Code). You don't write code - you paste, answer questions, and approve.

It opens by interviewing you about your business. Before a single line is built, the plan makes the agent ask about your actual sales process: which framework you use (or your homegrown one), your real forecast categories and the score thresholds that should gate each one, the exact criteria names and prompts, your deal field names and ID convention, your typical and peak deal volumes, who scores versus who approves, and your messy edge cases. Then it reflects a short tailored spec back to you for a thumbs-up - so you get a tool shaped around how your team actually sells, not a generic template.

From there it walks the agent step by step: the data model, login, the scorecard screens, automatic scoring and gap detection, the manager approval gate, email notifications, the audit trail, and the CSV export - each step ending in a ready-to-copy prompt.

The governance it includes (this is the point)

This isn't a toy. The plan bakes in the controls a sales leader actually needs:

• Login so only your team can use it.
• Row-level security so reps and managers only ever see their own organization's deals.
• A human approval gate - the rep's score is a draft; a deal cannot enter a higher forecast category until a manager reviews and approves it.
• Versioned frameworks - an admin publishes framework versions, and every scorecard records which version it was scored against, so changing the rules later never quietly rewrites history.
• A complete audit trail - who scored, who approved, what the gaps were, and exactly when.
• Duplicate guards - one active scorecard per deal, keyed on deal ID, so the same deal can't be double-processed.

Who it's for

• Sales managers who want every rep to qualify the same way and want the forecast to mean something.
• Reps who want a clear checklist that catches the gap before the deal slips - and improves their win rate.
• RevOps and sales ops standardizing qualification across the team without buying yet another platform.

You don't need to be a developer. If you can describe how your team sells and copy-paste, you can build this.

You've got this - paste the first prompt and let's build it.