How to review your own negotiations and stop repeating mistakes

How to review your own negotiations and stop repeating mistakes

During a conversation you are thinking what to answer and miss half of what the client said — not from inattention but because you are busy. A review of the recording finds that, and your own mistakes too. Below is a real review with two of mine.

During a conversation you are thinking what to answer and miss half of what the client said — not from inattention but because you are busy. A review of the recording finds that, and your own mistakes too. Below is a real review with two of mine.

The call happened, and what next is unclear

A familiar feeling: you talked, it seemed fine, the client did not refuse. You put the phone down and cannot say anything more definite than "seemed all right".

What worked? Where did you lose him? What did he actually want when he asked that odd question in the middle? Two days later you do not remember half of it, and the decision has to be made now: what price to set, what to write in the proposal, what to press on.

And most of all — you will run the next call exactly the same way. Experience does not accumulate by itself. It accumulates only where there is a review, and almost nobody can review themselves honestly: the brain remembers the good moments and edits out the awkward ones.

So I do not try to remember my calls. I hand them over for review.

What I do immediately after a call

I record the call, upload the audio to the sales assistant and write one sentence: "here is the audio of a call with this client, analyse what could be improved and how I should carry the conversation on".

Below is what it produced for the conversation with Zakhar Fomin, owner of a dental clinic. I am publishing it as it is, including my mistakes. A review where everything went perfectly is useful to nobody.

Why your own memory is no good for a review

The root cause: during a conversation you are busy having the conversation. Attention goes on listening, answering and not falling silent. There is no capacity left for observing the structure — and that is normal, it is the same for everyone.

The second cause is less pleasant: you hear what you are ready to hear. The client drops a sentence that is in fact the main lever of the sale — and you miss it, because at that moment you were thinking what to say next.

And the third: your own mistakes are invisible from inside. Not because you are deceiving yourself but because you do not know what to look for. To notice "here I blurred the focus" you have to be holding in mind what the focus should have been.

A machine has none of that. It listens to the whole recording, evenly, with no nerves and no self-regard.

What the assistant extracted from the client's words

This is the most valuable part of the review, and it is not about me but about the client. Zakhar handed over his own markers of lost revenue — I did not note them during the conversation.

Fear of "stupid bots" with expensive patients. He said it outright: leaving a high-value patient talking to a bot is a dubious business. His real pain is not the money for the build but that AI will damage the reputation and lose an expensive implant patient.

How to answer: this is not a linear answering machine, it is a business-class concierge. It recognises the status of an enquiry, qualifies tactfully and passes it to the owner's personal phone if it sees a hot, high-value request.

Manual reactivation of the base. Once a year Zakhar goes through the calendar by hand, looks for old patients and asks the doctors to ring them. Or hires a remote administrator who works an hour a day.

How to answer: show how the bot scans the base itself, sees that somebody has not been for six months and sends an invitation with a one-click slot. That is pure payback and a cost line removed.

Dead social channels. One patient every two months from social media. They paid a specialist who drained the budget, because the content was not tied to a funnel.

How to answer: content is not about pretty pictures but about targeted traffic that drops straight into the funnel and sells.

Three pains, three ready blocks for the future proposal. I registered none of them during the conversation as a lever.

What it said about me

Strengths

Weaknesses

First: in the middle of the call I drifted into technical questions about assistants and blurred the focus away from business metrics.

Here I half agree with the review. I did it deliberately: it mattered to me to understand how Zakhar's patient journey runs from first contact to the chair — because as a second step I planned to sell him a CRM, and that is a separate project worth several thousand dollars. But for this conversation the comment is correct: it was about something else, and I did blur the focus.

Second: I did not press the metaphor home when Zakhar spoke about his fear of bots.

That is a clean error and I have no objection. I should have said, right then and there: "this is not a replacement for the doctor, it is a smart maître d'" — in his language, with no technical terms. I did not, and the fear stayed unaddressed to the end of the conversation.

Opportunities and threats

The opportunity: Zakhar is ready to pay well if he sees that the system can work the existing base for repeat visits. That is his clearest lever of profit.

The threat, stated plainly: if tomorrow a figure is named off the top of the head, with no link to payback and to where he saves, the Controller will switch into Analyst mode and take time to think. And "thinking" for that type means weeks.

That warning determined how the commercial proposal was built.

How this turned into money

A review is not an end in itself. The three pains the assistant extracted from Zakhar's words went into the commercial proposal, one per block: the fear for expensive patients closed by a slide on handing hot enquiries to the owner, the manual reactivation by a slide on automatic scanning, the dead social channels by a block on content tied to a funnel.

The warning about a figure off the top of the head worked too: the sum in the proposal did not stand as a separate line but beside a calculation of what an in-house team costs. The Controller saw not a price list but a comparison — and did not go away to think.

Why it is worth showing your own mistakes

Worth saying separately, because this is about approach rather than tools.

A review where an expert with five years of experience publishes two of his own mistakes works better than a review where everything went perfectly. A perfect case helps nobody: it cannot be repeated and there is nothing to check yourself against. A mistake is a ready checklist.

And a second, more practical reason. The assistant sometimes extracts things you do not notice even with a lot of sales experience. Not because it is cleverer but because it listens to the recording without being in it.

What to do if the call cannot be recorded

It happens: the client objects to recording, or the conversation was in writing, or you simply forgot.

Then immediately after the call, while you remember, write down freely everything the person said about his situation: figures, complaints, staff names, sums, timescales. Do not structure it — just pour it out. Fifteen lines is enough.

Then give that text to the assistant with the same request. The review will be weaker than from audio: intonation and pauses are lost, and it is often in those that you hear where somebody tensed up. But the three main pains can be extracted from notes like that perfectly well.

For written exchanges it is simpler still: they are already recorded. Screenshots of the conversation are submitted for review the same way as audio.

How to build this into your work

The order is simple and takes about fifteen minutes after a call.

  1. Record your calls. Having warned the other person — that is normal practice.
  2. Upload the audio immediately to the assistant with a request for a review and for how to carry the conversation on.
  3. Read the block about the client first, not the one about you. The levers for the proposal are in there.
  4. Then the block about you — and write out one mistake to hold in mind on the next call. One, not five.

The sales assistant is one of 200+ AI assistants across 14 categories: sales, marketing, legal, HR, analytics, creative, media, engineers. It will also draw up the plan for the next call and play the client in a simulation if you want to run the conversation in advance.

Alongside is the ten-lesson sales module in the “Sales” course: objections, rejections, burnout, the four client types, shaping an offer to demand.

Registration is free and opens three days of full Basic access — the sales module, all the assistants, the prompt texts and six foundational express courses.

Start with your next conversation. Even if it goes badly — especially if it goes badly. Fifteen minutes of review after a failed call give more than five successful ones you remember nothing about.

If you know somebody who says "seemed to go all right" after every call, forward this to them.

What exactly to review a recording with

Three tools, covering different parts of the task.

A transcription service — it turns an hour-long call into text. That is the first step: from then on you work not with a recording but with a transcript that reads in ten minutes instead of an hour.

The AI sales assistant — it receives the transcript and produces a psychographic portrait of the decision-maker: hidden fears, true motivators, pains. And separately reviews your side of the conversation: where you drifted into jargon, where you failed to press, what you should have asked and did not.

The same assistant handles everything else too — from analysing a listing to the exchange after a call. Reviewing a recording is simply one of its modes.

The n8n template “Sales team control via chats and calls” (advanced: Full, or a one-off $9, or 1000 XP) — if there are many conversations and they run in chats and by phone. Chat messages are saved, call recordings are transcribed, and daily reports are built per manager.

What the third tool gives besides the review. It works continuously rather than on request. You see the weak points immediately rather than when you decide to revisit a recording.

And that also sells as a service: implementing a conversation analyst in a sales team costs $360–1 200.

What to transcribe with and what to review with

Transcription. The Gen AI section, "File → text" mode — speech to text with subtitles, plus audio and video analysis. Wallet payment from $5, the price visible before launch.

The review. Sales analyst from the catalogue, Basic plan — it works to the classic methods: SPIN, Challenger Sale, Fanatical Prospecting. It shows where you pushed too hard, where you failed to identify the pain, which red flags led to the collapse.

Companies buy the same method as a service: transcription first, then a merciless review, then new scripts — it is covered in the article “An X-ray of calls: auditing a sales team”. The only difference is that there somebody else's calls are reviewed for money, and here your own for nothing.

Practising on the mistakes found — the express course Freelance 2.0, prompts №47 and №49, the call and messaging simulators. Basic plan.

Consent to recording is obtained before the call, in one sentence in the exchange. That settles the whole question.

What to take on the platform for this task

The series: one deal step by step

Eight pieces about one real deal — from a listing in a chat to payment received. The client, Zakhar Fomin, owner of a dental clinic, agreed to be named along with the figures.

What to read next

A commercial proposal in ten minutes — what the review turns into.

The fifteen-minute call — the script for the conversation itself.

Transcription and file analysis — the technical side of working with recordings.

An X-ray of calls: auditing a sales team — the same skill sold to a company.

AI API pricing in 2026 — what a request costs and how to work out your own costs.

Also on AI SKILLS