Once you're in — yes. Text or call anytime. Access itself is application-reviewed, not self-serve overnight.

Will my manager see what I tell Sara?

No. Sara reports to you. Nothing goes up the org chart unless you choose to share it.

Does she record my customer calls?

Never. No bot in the meeting. You reach out after — by text or call.

How is this different from Gong or Chorus?

Gong owns the recorded call — for your manager. Sara owns what happens after you hang up — for you.

What does a sales forecast calculator actually calculate?

Probability times deal size, per open opportunity, added into one total. A rep's confidence percentage multiplies against the deal's dollar value, and every deal's result gets summed into the quarter's weighted forecast number.

Why can a small high-probability deal and a large low-probability deal produce the same forecast number?

Because the math is symmetric. A $200K deal at 90% and a $1M deal at 18% both weight out to roughly $180K, and the calculator has no field for how different those two bets actually are — one close to certain, the other closer to a coin flip stacked against it.

How do you account for deal risk that a forecast calculator misses?

Track each deal's own odds and size next to each other instead of only the blended total. A forecast meeting that can point at the one specific deal carrying the risk catches a problem the summed number hides until that deal is already gone.

FIELD NOTES

Sales Forecast Calculator: Two Different Bets, One Identical Number

A sales forecast calculator multiplies probability by deal size into one number. A $200K deal at 90% and a $1M deal at 18% land on the same total.

2026-09-14 · SARA — KEEL'S AI DEAL ASSISTANT · GETKEEL.IO

Priya opens the calculator template. Two deals, same forecast meeting.

Deal one: $200K, 90% confidence. Deal two: $1M, 18% confidence.

The calculator multiplies each, then adds them. Both land at $180K.

The formula underneath the number

A sales forecast calculator does one thing. Probability times deal size, per opportunity, summed into a total.

Type in a percentage and an amount. Get back a number that looks precise.

The percentage is the part nobody checks. It's a stage default, a rep's gut, or last quarter's average — dressed up as math the moment it gets multiplied.

Two bets, one weighted number

$200K at 90% weights to $180K. $1M at 18% weights to $180K too.

Same output.

Nothing about the calculator distinguishes them.

One is a deal Priya would bet her quota on. The other is a long shot that pays out big if it lands, and costs nothing if it doesn't.

The weighted number treats both like the same $180K sitting in pipeline.

Why the two bets aren't the same bet

A 90% deal is close to a sure thing. Losing it is the surprise.

An 18% deal is close to a coin flip stacked five to one against it. Winning it is the surprise.

Opportunity forecasting covers a version of this one level down — two deals at the same pipeline stage getting the same default percentage, when their actual odds have nothing in common. The calculator's output has the same blind spot, just later: it can't tell a near-certainty from a lottery ticket once they're both converted into a dollar figure and added to the pile.

What the calculator can't show you

Concentration risk, for one.

A quarter built on one $1M deal at 18% is a very different bet than a quarter built on five $200K deals at 90%, even when both weighted totals land at the same number.

The calculator can't see that difference.

It was never built to.

Forecast accuracy formula picks up the next stage of the same problem — what happens once this weighted number gets checked against what the quarter actually closed. Sales forecasting techniques is the wider case: every technique, this one included, inherits whatever the input already hid.

Where Sara sits

Sara keeps each deal's own odds next to the rep's own words about it — the $200K Priya would bet on, the $1M long shot she's chasing anyway — so a forecast conversation can talk about the bet, not just the blended number it collapsed into. Founders Club is invite-reviewed: apply at getkeel.io/founders.

Priya's second pass

The calculator still said $360K for the quarter. Same number as last week.

This time Priya added a line the template never asked for: which deal was the sure thing, and which was the swing.

Her manager spent ten seconds on the total.

He spent the rest of the meeting on the swing deal.

By the team at Keel. We're building Sara, an AI deal assistant for the moments that don't get recorded.

MORE IN THIS SERIES

Forecast Accuracy Formula: A 98% Score That Was Wrong About Every Deal

The standard forecast accuracy formula compares two totals, not two deals. Two guesses that are wrong in opposite directions can still score as a near-perfect quarter.

Account-Based Forecasting: The Rollup That Hides Its Weakest Deal

Account-based forecasting sums every open deal in an account into one number. A single shaky deal can vanish the moment it's added to two healthy ones.

Opportunity Forecasting: One Percentage Covering Two Different Guesses

Opportunity forecasting assigns one probability per pipeline stage. Two deals sitting at the same stage rarely deserve the same number.