Forecast-Accuracy & Deal-Slippage Tracker

The problem this kills

Every week your reps submit a forecast - commit, best-case, deals they swear will land. Then the quarter closes and nobody remembers who was right. The same deal slips from March to April to "definitely Q2," and the same rep who sandbags every period gets treated the same as the one who calls it straight. Leadership runs forecast reviews on gut feel because there's no scorecard.

The data to fix this already exists - it's just never captured and compared. You need to freeze each week's forecast, line it up against what actually closed, and keep a running history of which deals keep moving their close date. That's a measurement problem, and measurement problems are exactly what a small internal tool solves.

What you'll build

A private, login-protected web app for your revenue ops team that:

• Ingests weekly forecast snapshots (each deal's commit / best-case as submitted) and the actual closed results for each period.
• Scores forecast accuracy by rep and team - commit hit-rate, and how much each person over- or under-called.
• Tracks deal slippage - for every deal, a history of how many times its close date moved, and by how long.
• Surfaces the patterns leadership cares about - chronic sandbaggers, habitual over-callers, and the deals that are perpetually "next month."
• Routes everything through an ops approval gate before the report is published and used in a forecast review - including any reclassification of edge cases like split or reassigned deals.
• Exports a clean CSV in the exact columns your existing tools expect.

What's inside the Implementation Plan

• It interviews you first. Before writing a line of code, the plan has the AI agent interview you about your business - your forecast categories, your CRM and spreadsheets, your deal-ID and rep-naming conventions, your period cadence, your real approval rules, and your messy edge cases. It reads back a short tailored spec and waits for your thumbs-up. You get a tool shaped to how you forecast, not a generic template.
• A step-by-step build, each step ending with a ready-to-paste prompt for your AI coding agent.
• The full data model for snapshots, actuals, accuracy scores, and slippage history - with the dedupe keys that stop double-counting (rep + period for accuracy, deal ID for slippage).
• A snapshot-capture path for teams who aren't storing weekly forecasts yet, so you can start building history from day one.
• A "No API yet?" fallback that runs entirely on spreadsheet imports and CSV exports.
• A verification checklist so you know it actually works.

The governance it includes (this is the point)

This isn't a throwaway script - it's an accountable system, because forecast accuracy is something leadership will act on:

• Login so only your team can open it.
• Row-level security so people only ever see their own organization's data.
• A complete audit trail - who imported what, who edited a classification, who approved the report, and when.
• A hard human-in-the-loop approval gate - the tool computes the accuracy report and any edge-case reclassification, then an ops reviewer must approve before anything is published.
• Duplicate guards so the same snapshot or actual can't be loaded twice and quietly skew the numbers.

Who it's for

Revenue operations and sales leaders who want to hold forecasts accountable over time - to stop relitigating who called what, to coach reps with data instead of vibes, and to walk into every forecast review knowing whose commits have earned trust.

You've got this - paste the first prompt and let the agent interview you.