Prompts to Analyse Competitor Mentions in Sales Calls

A search index answers a question about four thousand calls. A model answers a question about the twenty you put in front of it, and the two outputs are written in the same voice. Nothing in a summary says which one you are reading.

That matters because of how the twenty were chosen. Almost always by searching the archive for a competitor’s name, so the set arrives already picked for the conclusion. An output saying a competitor is raised more than any other, about calls gathered by searching for that competitor, carries no information at all. And it reads exactly like a finding.

The fix is not a cleverer instruction. Put the query in the brief, so the model can qualify its own answer: twenty calls, from a search on these terms, over this date range, out of this many the search returned. One sentence, and the output stops claiming something it was never in a position to know. What the recordings can support and what they cannot is set out source by source under Gong and its peers, and the export format decides most of it.

Three prompts, and the third one comes first in practice. That is why they sit above the input contract rather than below it. Building the spelling list is a five-minute job, and it is unusual for one prompt to produce an input that another one needs.

Notice what the second prompt is forbidden from doing. It may not judge whether a claim is accurate, and it may not draft a response. Both are useful, and both belong later, with a person and a source in the room. A model asked to sort evidence and rebut it in one pass will quietly start sorting the evidence to suit the rebuttal. Rebutting is its own job with its own first step, and answering a competitor objection starts by deciding whether the buyer is right.

Three inputs, and only the first is a document. The other two are what make the first one readable, and both usually stay in somebody’s head: the spelling list the prompt above produces, and the query that decided which calls you are holding.

Paste whole calls rather than the lines containing the competitor. What was being discussed in the two minutes before a name is raised is most of what the mention means. A competitor named while a buyer talks about budget, and the same name raised while they talk about a missing feature, are different events. An extract of the naming line alone has thrown that away before the model sees it.

The buyer sentence below was written for this run rather than lifted from a real recording. It is the shape a transcript search returns every day. What is measured here is what the model did with it, and the packaging it gets checked against is a live page anyone can open.

The correction is not the useful part

It would be easy to read the second output as fact-checking the buyer, and that is the least valuable thing in it. The buyer’s belief is a fact about the deal whether or not the page agrees. Somebody compared your price against a package they think exists, and that comparison is what priced you. Correcting them changes nothing about how the deal went.

What changes is the next conversation. A rep holding “they include it in Starter” will tell the buyer they are wrong, and that is an argument nobody wins in front of a prospect. A rep holding “the buyer believes it is in the entry tier, the page lists it two tiers up” asks what they were shown instead. The answer is often a bundle, a discount, or a version of the page that has since changed. How many of your contested deals get a call read at all is competitive deal coverage, and it is usually lower than anybody assumes.

Two sentences, same competitor, same six words of substance. A seller says “unlike them, we handle this natively”. A buyer says “they handle this natively”. One is your talk track. The other is a rival’s argument reaching a buyer. An export that has flattened the speaker labels puts both in the same count.

The error always runs the same way, which is what makes it worth naming. Sellers raise competitors more often than buyers do, because raising one first is a standard technique. So an unlabelled archive always overstates how much buyers are thinking about your competitors. The number quoted in a quarterly review then measures your own positioning rather than theirs.

Count accounts, and say so in the output

The other correction is arithmetic. One buyer returning to a concern four times across a negotiation is one buyer. Four unrelated buyers raising it once each is a pattern. Both produce the number four, and only the second is a reason to change anything. Make the prompt report distinct accounts, and say that is what it counted. That is the difference between a chart somebody argues with usefully and one they dismiss.

Where this lands is a rep’s preparation rather than a report. A claim recorded verbatim, with the deal and the date beside it, belongs on the sales call prep sheet, and the same claims collected across a quarter are what a win/loss synthesis is trying to explain after the fact. Calls catch it while the deal is still open. That is the one real advantage this source has over every other one.

Everything on this page depends on a set of transcripts somebody put together, on whatever day they remembered to do it. A competitor appearing in a segment for the first time is the event worth knowing about. A quarterly sweep cannot see it, because a quarterly sweep only reports what is already common.

Most call platforms will alert on a term. That is the cheap half of the answer, and worth setting up for every competitor you can name. It does not solve the competitor you cannot name yet, arriving under a spelling nobody has added, in a segment nobody is watching. An alert list is a list of the rivals you already know about.

The other half of the problem is on the outside. A buyer’s account of a competitor can only be checked against what that competitor publishes now. By the time somebody opens the pricing page, it may have moved. A claim and a dated page belong together, or neither is much use.

Flares keeps competitor pricing, packaging and messaging current and dated. The claim a buyer repeats on a call can then be read against what that competitor actually published that week. Hearing the claim in the first place still depends on your own recordings, and on somebody searching them for the right spelling. The same claims, heard from customers who already left, are what churn reason analysis reads, and the two corpora rarely agree.