Accuracy

Accuracy you can defend.

Every vendor claims their AI understands sales calls. Ask how they know and the answer is usually a demo. Ours is the number, how it was tested, and the evidence behind both.

98.2%
accuracy — 214 of 218 checks
50
deliberately difficult sales conversations
218
checks, against answer keys written in advance
117
times it declined to state something the call did not support

Measured 23 August 2026

98.2% accuracy — 214 of 218 checks across 50 deliberately difficult sales conversations, scored against answer keys written before the test was run; two were corrected on review, and the ledger names them. The analysis has changed since the run. When the test is re-run and the number moves, this page moves with it — including downward.

Zero invented figures and zero invented commitments remain after review. Of the four misses still counted, three said too little and one filed a real reversal under the wrong heading. The failure that would reach your forecast as agreed money is the one we do not have.

How it was tested.

  • On the calls that actually go badly. Buyers who interrupt mid-sentence. Hedged answers that sound like commitments. A price said once, then revised ten minutes later. Danish, Swedish and Norwegian dropped into English mid-thought. Threads that start and never finish. And the "we’ll see" ending that every rep has mistaken for a yes. A test built on tidy calls tells you nothing, because your calls are not tidy.
  • Answer keys written in advance. What each conversation actually established was written down before the test was run. Two keys were corrected on review, when re-reading showed the product was right and the sheet was wrong; the ledger names both.
  • Against the product, not a raw model. Every conversation went through the same system your calls go through — same processing, same conservative judgements — as it stood on the day of the run. Testing a raw model instead would measure something we do not sell.
  • Both directions counted. Missing something a call established costs a rep a few minutes. Stating something it did not establish travels into a forecast, into a board pack, out of the building. Those are not the same failure and they are not scored as though they were.

Where the checks land.

The 218 checks are four kinds of question, and they are not equally hard. The table is generated from the score file; a test fails the build if any cell drifts from the measurement.

What was checkedChecksCorrect
The deal value — right figure, or correctly none5050100%
The acceptance state — confirmed, likely, or none504794%
Declined to state what the call did not support111111100%
Caught a buyer reversing themselves, on the right fact7686%
All checks21821498.2%

Who wrote the test.

We did, and that is worth being plain about. The conversations and the answer keys are ours; the keys are written before every run, two have been corrected on review, and the ledger names them. Every conversation is then read back by the founder — ten years selling B2B — and judged against one question: does a real salesperson behave this way? Conversations that fail that reading are removed from the test entirely, with their names and the reasoning on the record in our repository. Six have been.

117 times

Where the number really comes from

Most of this test is less "did it catch the fact" than "did it stay quiet when a careless reader would not have". 117 times it declined to state something the conversation did not support: a buyer’s off-hand guess at their own costs ("that’s a feeling, not a number"); a price revised down later in the same call; an unnarrowed 350–450k range; a procurement threshold that looked like a deal size; a competitor’s spend offered as a comparison; a rep’s own delivery promise; and every "we’ll see" ending. Across all 50 conversations it never once recorded a commitment the buyer had not made.

A whole messy call, and everything Talqo said about it.

The transcript below is one of the fifty — the hardest kind: a procurement conversation that circles, a budget thread interrupted by someone walking into the room and never picked up again, and an ending where both people say out loud that nothing has been agreed. On the right is Talqo’s output, unedited, including the fields it left empty.

What you are looking at. The call is constructed to be representative — it is not a customer call, and nobody in it is real. The analysis is real: it is the unedited output of Talqo as it ran on 11 August 2026, with nothing removed and nothing tidied. Talqo’s screens have moved on since — items now read Confirmed, Weak, Missing or Taken back — and the output is shown as it was.
The call · Værnes Industriservice · synthetic
Rep (Talqo): — can you hear me now? Kjell Værnes: Now I can, yes. Sorry, this room is — the video thing is new and nobody has — Rep: It's fine. Shall I start again? Kjell: No, no. You said fourteen sites. Rep: Fifteen, but one is closing. Kjell: One is closing. Right. That's Orkanger, is it? Rep: I don't know which one, you'd — Kjell: It'll be Orkanger. It's always Orkanger. [laughs] Sorry. Go on. Rep: So across the fifteen — fourteen — you've got service engineers who are also, functionally, selling. Kjell: They're not selling. They're not supposed to be selling. Rep: But they're quoting. Kjell: They're quoting. That's different. Is that different? I think procurement would say that's different. Rep: Commercially it's the same conversation with a customer about money. Kjell: [pause] Yes. Alright, yes. Don't tell procurement. Rep: I won't. How many of them? Kjell: Sixty? Seventy? It depends whether you count the — hva heter det på engelsk — the ones who do the yearly service contracts, they quote but it's a fixed — Rep: A price list. Kjell: A price list, yes. They don't negotiate. They read the number off the sheet. Rep: Then I'd leave them out for now. Kjell: Then it's forty. Forty-something. Rep: Forty-something. And the thing you described at the start — a customer says something on site and it never reaches the office — Kjell: That is exactly it. That IS the problem. A customer says "we're looking at replacing the whole line next year" and the engineer says "oh, right" and drives home, and nobody knows. And then eighteen months later somebody else has replaced the line. Rep: And you find out from the invoice you didn't get. Kjell: You find out from the invoice you didn't get. That is — yes. That's the sentence. Rep: So the value is in what's said in the van park, not what's typed in the CRM. Kjell: We don't really have a CRM. We have — there's a system. Nobody uses it. Ingrid puts things in it. Rep: Just Ingrid? Kjell: Mostly Ingrid. [laughs] Ingrid is the CRM. Rep: Then let me ask the money question, because I'd rather ask it early — Kjell: Go on. Rep: If this worked, and you could see every commitment your engineers heard — Kjell: How much. Rep: For forty seats you'd be looking at — [knock; door opens] Voice (off): Kjell, sorry — the Stavanger thing, they need you, it's the — Kjell: Now? Voice: They've been holding. Kjell: Åh, for helvete. Two minutes. [to rep] Two minutes, I'm sorry. Don't go. Rep: I'll wait. [four minutes of hold tone] Kjell: Sorry. Sorry sorry sorry. Where were we. Rep: I was about to give you a number. Kjell: Right. Yes. Actually — hold on, before you do. Is that useful right now? Because I can't do anything with a number today. Rep: Why not? Kjell: Because procurement have a process, and the process starts with a requirement document, and the requirement document has to come from the business, and the business is me, and I haven't written it. Rep: So the number arrives after the requirement document. Kjell: The number arrives after the requirement document. Otherwise it looks like I've picked you first and then written the document to fit, which is — well. That's exactly what everyone does, but you can't look like you're doing it. Rep: Understood. Then I won't quote you today. Kjell: You're the first person who's said that. Everyone else quotes anyway. Rep: It'd only make your life harder. Kjell: It would. It genuinely would. Rep: What would help is if I gave you the shape of what a requirement document for this normally covers. Not written for us — just the categories. Kjell: That WOULD help. Rep: I'll do that. Kjell: If you do that I'll actually read it. Rep: And on timing — when does the requirement document need to exist? Kjell: Before the budget round. Rep: Which is when? Kjell: [pause] Good question. Normally October. This year they've said something about moving it. I'd have to ask Solveig. Rep: Would you? Kjell: I'll ask her. I'm not promising anything comes back quickly, she's — everyone's flat out. Rep: I know the feeling. Kjell: So. You send the categories thing. I'll look at it. And then we'll see. Rep: We'll see. Kjell: We'll see. That's not a no. Rep: I didn't take it as one. Kjell: Good. It's not a yes either, mind. Rep: I didn't take it as that either. Kjell: [laughs] Fine. Send it.
Talqo’s output · unedited · 11 Aug 2026
Deal value
Not stated — no price was quoted on this call, so none was recorded.
Price acceptance
None — nothing to accept.
Expected close date
Not stated — the budget round "is normally October" and may have moved. That is not a date.
Stage
Needs Analysis
Summary
Rep spoke with Kjell Værnes about ~40 field service engineers who informally quote customers but whose on-site intelligence never reaches the business — a clear revenue leakage problem. No price was given at Kjell's request because procurement requires a formal requirement document before any number can be introduced. Rep agreed to send a template of requirement-document categories instead, and Kjell committed to checking the budget-round timeline with a colleague named Solveig.
Next steps
Rep sends Kjell a requirement document category framework (not vendor-specific). Kjell reads it and asks Solveig about the revised budget round date, then feeds that back to the rep.
Qualification
budget Unknown
validated: false
No budget figure discussed; Kjell stopped the rep before pricing and explained procurement process gates any spend.
authority Medium Kjell owns the requirement document and is clearly the business sponsor, but procurement and Solveig are involved in budget approval.
need High Kjell explicitly confirmed the core problem — field intelligence lost in transit — as 'exactly it' and 'that's the sentence'.
timeline Low Budget round is normally October but may have moved; Kjell needs to check with Solveig and has made no firm commitment.

Why it prefers to be cautious.

A false "unproven" costs a rep two minutes: they look at the deal, see we did not score something, and either supply the fact or ignore it. A false "validated" costs a sales leader their credibility, because it travels — and the first anyone hears of it is when a defended number turns out not to have been said by anybody.

So every ambiguous case resolves downward, and that rule lives in the code rather than in a prompt: an acceptance we cannot quote back to you is not an acceptance; a price met with silence is not a price agreed; an answer we do not recognise resolves to the least claiming state, never the friendliest. Across all 50 conversations it never once recorded a commitment the buyer had not made — no invented figure, no agreement nobody gave. That is worth more than the percentage, because it is the failure that reaches your forecast.

Two states, precisely

Contradicted. Not a worse grade of agreement — off the scale entirely. The buyer accepted a price and then took it back, in their own words. Talqo keeps both quotes and shows the reversal beside the thing it reversed, because a fact that quietly disappears is worse than one never captured.

Not asked. The four words run strongest claim to weakest. “Not asked” means no price has been put to the buyer — it is not where Talqo puts a deal it is unsure about. A deal the buyer pushed back on reads not agreed, which is a different fact and ranks differently.

No score without a source.

A Talqo claim is the item, the reason, and the passage from the call with the cited sentence marked in place. This one is from the call above, so nobody in it is real; the analysis is.

Exhibit A 11 Aug 2026
Need · High — confirmed by the buyer
Kjell confirmed in his own words that lost on-site customer intelligence is the exact problem, with a vivid example of a missed line-replacement opportunity.
The passage, as recorded
Rep: … And the thing you described at the start — a customer says something on site and it never reaches the office —
Kjell: That is exactly it. That IS the problem. …
Rep: And you find out from the invoice you didn't get.
Kjell: You find out from the invoice you didn't get. That is — yes. That's the sentence.
Værnes Industriservice·11 Aug 2026·Kjell Værnes·our benchmark call, nobody in it is real Confirmed on the call See the whole call→

Four words, and it earns each one.

A price is not “agreed” because a rep felt good about the call. Every deal’s price sits in one of these, and the sentence beside it is the one Talqo prints.

  • agreed

    The customer said yes on a call.

  • not agreed

    Talked about, no yes yet.

  • contradicted

    A yes, then taken back. The bar is deliberately high: an explicit reversal, a verbatim quote, and a named fact. Hesitation is not reversal.

  • not asked

    No price has been put to the buyer.

Absent, never invented. An item nobody discussed reads Missing, with the question to ask next. Talqo would rather show you a gap than fill it.

Every figure opens to this
Exhibit B
Buyer-accepted price — the buyer accepted it out loud
The passage, as recorded
Buyer: one seventy-six, yes — even at that number it clears our budget
Ribe Foods·from the call record·demo dataset Agreed on the call

No score without a source. If we cannot show you the sentence, we do not say the buyer said it.

Run it on your own call.

Want this run against your own call instead? That is the offer on the front page — send one, and you get the same output, including everything it declines to state.

Full methodology and test data — the conversations, the answer keys and the scorer — are available for review on request.