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 is opportunity forecasting?

Assigning a probability of closing to each open deal, usually a default percentage tied to its pipeline stage — 25% at qualification, 50% at proposal, and so on — then multiplying that percentage by deal size to build a weighted forecast.

How is opportunity forecasting different from pipeline forecasting?

Opportunity forecasting works one deal at a time; pipeline forecasting sums the results across every open deal into one number for the team. The stage-based percentage problem shows up at the opportunity level first, then rides straight through to the total.

Why do two deals at the same stage deserve different forecast numbers?

Because the stage measures where a deal sits in a process, not what's actually true about it. A proposal with a named economic buyer and a forcing deadline is a different bet than a proposal still waiting on someone to reply — the stage percentage treats them as identical.

FIELD NOTES

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.

2026-09-11 · SARA — KEEL'S AI DEAL ASSISTANT · GETKEEL.IO

Two rows in the CRM, both "Proposal — 50%."

One of them has a signed timeline and a name in the economic-buyer field. The other hasn't replied to an email in eleven days.

Both get forecast the same way.

What opportunity forecasting usually does

Assigns a percentage by stage.

Qualification is 25%. Proposal is 50%. Negotiation is 75%.

Multiply that percentage by deal size, and the model has its number.

The stage moved.

The percentage followed it automatically — no one had to look at the actual deal to produce it.

The number the stage can't see

A stage is a step in a process. It says where a deal sits, not what's true about it.

Sales forecasting techniques makes the broader case: the formula is only as honest as its input. Opportunity forecasting is where that input gets manufactured — one stage-average percentage standing in for a read the rep already has and the CRM field never asked for.

The rep on that second deal already suspects it's closer to 20% than 50%. Nobody wrote that number down anywhere the forecast could use it.

Where the real number actually lives

Not in a better stage-scoring model. In the rep's own private read, captured before it gets rounded up to a stage default.

Pipeline forecasting covers the aggregate version of this same gap — a total built from inputs nobody checked. Sales forecasting vs pipeline management draws the line between a deal's health and what it closes at, which is exactly the distinction a single stage percentage is built to erase.

The fix isn't a sixth pipeline stage. It's asking, deal by deal: does this one actually deserve the number the stage just handed it?

Where Sara sits

Sara's built for that question, asked privately, deal by deal — not a smarter stage model, just somewhere to put the read a rep already has before it gets averaged away. Founders Club is invite-reviewed: apply at getkeel.io/founders.

The eleven-day deal

The rep flagged it before the forecast call, not during it. "Proposal — 50%" became "Proposal — stalled, no reply in eleven days" in his own notes.

His manager moved it to 15% on the spot.

The signed-timeline deal stayed at 50%, closed three weeks later at that number. The stage had been right about one of them the whole time — just not both.

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

How to Improve Sales Forecast Accuracy: The Lag No Formula Fixes

Weighted pipelines and historical win rates already do the math correctly. The forecast still misses because of what happens before a number reaches the field.

SaaS Sales Forecasting: One Number, Two Different Kinds of Unsure

SaaS sales forecasting blends new-logo ARR and expansion revenue into one line. They're not the same bet, and treating them alike hides which risk you're actually carrying.

Sales Forecasting vs Pipeline Management: Two Different Questions, One Report Trying to Answer Both

Pipeline management asks if a deal is healthy. Forecasting asks what closes and when. Clean up the pipeline and the forecast can still be wrong.