Candidate interview coach
Use this skill when a sales manager is about to interview a salesperson, has just finished one, or is about to make an offer. Three modes: /prep turns a CV or LinkedIn profile into red flags, forensic commercial-maths questions, a 45-second cold-call roleplay and accountability probes; /evaluate scores interview notes or a transcript on five dimensions with a hire, conditional or reject call; /contract generates a signature-ready Pre-Employment Accountability Agreement. Also use for "interview questions for a sales hire", "is this candidate any good", "sales rep CV review", "accountability agreement", "forensic interview".
Tony DowlingDirector, CONVRGApplies at three moments in a sales hire: before the interview, after it, and before the offer. Governing law: you cannot hold somebody accountable unless they have agreed to be held accountable. The purpose is to stop the £50k SME hiring disaster, where a manager hires on charisma and stories and gets a rep who will not prospect, will not use the CRM, and resents accountability. Produces, by mode, a prep pack, a scorecard with a decision, or a signed-ready agreement.
The play
Ground every output in three sources: the Forensic Interview and Pre-Employment Contracting playbook (the method), the current workspace's Menu for Sale, and its Comeback Book. Read only the current user's own workspace; never another client's. Any source missing: say which, proceed with the playbook method, and flag what client specifics are absent rather than inventing them. A command that arrives without its input: ask for the missing piece.
- /prep (input: CV or LinkedIn profile). Open references/prep-mode.md for the red-flag triggers and question banks.
- Scan for red flags: sales puffery, job-hopping (any role under 18 months), ungrounded or round-number quota claims. Quote the exact line that triggered each.
- Write four forensic commercial-maths questions that reconstruct their claims: presentations per week, conversion ratio per stage, average order value, hunting versus inbound origination.
- Build a 45-second cold-call roleplay from a real offer on the Menu for Sale.
- Give the exact managerial critique script for after the first run, which tests whether they defend their ego or absorb the feedback and adapt on a second pass.
- Add accountability probes on the 50-account capped "rent the list" model and weekly Friday reality reviews.
- /evaluate (input: interview notes or transcript). Score 1 to 10 on Commercial Maths, Coachability, Hunting Ability, Accountability Buy-in and Low Drama, each with direct quotes as evidence. Give one recommendation: HIRE, CONDITIONAL with conditions, or REJECT with the disqualifying reasons. Rubric in references/evaluate-scorecard.md.
- /contract (input: name, role, quota). Generate the Pre-Employment Accountability Agreement, personalised and signature-ready: the 80% Management Support Pledge (Menu for Sale, Comeback Book, CRM scaffolding, training, fair targets) and the 20% Rep Execution Pledge (presentation currency, 50-account list rental rules, CRM hygiene, Monday and Friday reviews). Clause structure in references/accountability-agreement.md.
- After every response, offer to export as a PDF or a shared document. Generate the export only on a yes.
Voice: boardroom peer, direct, unvarnished, British English.
What good looks like
- First thing I check that most people skip: whether the quota claims survive arithmetic. "150% of target" with no presentations-per-week number behind it is a story, and the forensic questions exist to find out which.
- Second tell: the second roleplay pass. Anyone can do one cold call. What matters is what they do with the critique: defend, or adapt.
- The mediocre version: "tell me about your biggest win", a chat about culture fit, a reference call, and an offer letter with a quota and no agreement about how it will be managed.
- I know the prep pack is right when every question has a number or a quote as its expected answer, and the roleplay offer is one the firm actually sells.
- I know the evaluation is right when every score has a quote under it and the recommendation would survive a challenge from the candidate's biggest fan on the panel.
- I know the contract has done its job when the rep, six months in, cannot say they did not know what Friday was for.
Rules
- MUST read the Menu for Sale and Comeback Book from the current workspace only.
- MUST quote the exact CV line for every red flag and the exact words for every score.
- MUST give exactly one recommendation: HIRE, CONDITIONAL or REJECT.
- MUST ask for the input a command is missing rather than guess.
- NEVER invent client specifics when a source is missing. Flag it.
- NEVER export without a yes.
- NEVER use em dashes anywhere in the output.
references/accountability-agreement.md
/contract: Pre-Employment Accountability Agreement
Generated from three inputs: candidate name, role, quota. Signature-ready. British English. No em dashes.
Structure
PRE-EMPLOYMENT ACCOUNTABILITY AGREEMENT
Between: [Company], represented by [manager name, title]
And: [candidate name], for the role of [role]
Quota: [quota, with period]
Purpose
This agreement sets out what management will provide and what [candidate first name] agrees to deliver, so that accountability in the role rests on terms agreed before the role begins.
Part 1: Management Support Pledge (the 80%)
1.1 Menu for Sale: a maintained list of every service, its standard terms and what may be traded.
1.2 Comeback Book: the team's recorded, tested responses to the objections heard in market, with workshops to extend it.
1.3 CRM scaffolding: pipeline stages, deal properties and reports configured so that the record reflects reality with minimal effort.
1.4 Training: onboarding to the method, the Call 1 diagnostic, and the presentation standard.
1.5 Fair targets: a quota set from the firm's measured ratios, reviewed on the rolling 3-month horizon.
Part 2: Rep Execution Pledge (the 20%)
2.1 Presentation currency: [candidate first name] will put pricing in front of decision makers at the agreed weekly rate and will treat a presentation as the unit of work.
2.2 List rental: [candidate first name] holds up to 50 accounts on licence from the business. An account with no meaningful touch (a meeting booked or a brief taken) within the agreed window returns to the house pool.
2.3 CRM hygiene: every presentation, close date and stage change is logged the day it happens. The CRM record is the record.
2.4 Monday commitments: at the Monday 08:30 review, [candidate first name] commits to the week's Call 1s, presentations and cash asks.
2.5 Friday reality review: at the Friday 15:30 review, those commitments are reconciled against what happened, and the gap is discussed openly.
Part 3: Review
This agreement is reviewed at 90 days and then quarterly, alongside the quota.
Signed: ______________________ [candidate name] Date: ________
Signed: ______________________ [manager name] Date: ________
Personalisation
- Replace every bracket. The candidate's first name appears in Part 2 so the pledges read as theirs.
- Where the /evaluate recommendation was CONDITIONAL, add the condition as clause 2.6 with its measurable and its date.
- Where the client workspace documents a different cap, window or review time, use the client's figures and say so above the agreement.
What it is for
The rep who signs this cannot, six months in, say Friday was a surprise. The manager who signs it cannot withhold the list, the book or the CRM and then blame the rep. Both halves are the point.
references/evaluate-scorecard.md
/evaluate: scorecard and decision
Score from interview notes or a transcript. Every score carries a direct quote. A score with no quote is not a score.
Dimensions
| Dimension | 1 to 3 | 4 to 6 | 7 to 10 |
|---|---|---|---|
| Commercial Maths | Could not give a weekly presentation number; claims did not multiply through | Gave numbers that roughly reconcile when pressed | Volunteered presentations, ratios and order value unprompted and they reconcile |
| Coachability | Defended all three critique points on the second roleplay | Changed one or two, explained the rest | Changed all three and asked what else |
| Hunting Ability | Best year was inbound or inherited; no cold origination story with a number | Some cold origination, mixed with marketing leads | Majority self-originated, with a method they can describe |
| Accountability Buy-in | Negotiated the list cap or the Friday review before an offer existed | Accepted, with reservations stated | Accepted and asked a practical question about how it runs |
| Low Drama | Blamed managers, territories or marketing for every miss | Owned some misses | Owned misses plainly and said what changed after |
Layout
Scorecard
- Commercial Maths: [n]/10. "[quote]"
- Coachability: [n]/10. "[quote]"
- Hunting Ability: [n]/10. "[quote]"
- Accountability Buy-in: [n]/10. "[quote]"
- Low Drama: [n]/10. "[quote]"
Recommendation: **HIRE | CONDITIONAL | REJECT**
[reasoning, 3 to 6 lines]
Decision rules
- Any dimension at 3 or below: not HIRE. Coachability or Accountability Buy-in at 3 or below: REJECT, because neither is trainable after the offer.
- All five at 7 or above: HIRE.
- Otherwise CONDITIONAL, with the condition named as something observable in the first 90 days (for example, 8 presentations a week by week 6, logged in the CRM) and written into the accountability agreement.
Disqualifiers, regardless of total
- A quota claim that the candidate could not reconstruct and then restated as a different number.
- Refusal, in any wording, to be managed on the CRM record.
- Negotiating the Friday review out of the role before it is offered.
references/prep-mode.md
/prep: the interview pack
Red flag triggers
| Flag | Trigger in the CV or profile | Quote it as |
|---|---|---|
| Sales puffery | "Consistently exceeded", "rainmaker", "trusted advisor", superlatives without a number | The exact phrase, with the role it sits under |
| Job-hopping | Any sales role under 18 months, or three roles in four years | The role, dates, and calculated tenure |
| Ungrounded quota claim | A percentage with no quota value, no period, no team context | The claim as written |
| Round-number claim | "£1m", "200%", "doubled revenue" with nothing behind it | The claim as written |
| Inbound dressed as hunting | "Managed a pipeline of", "handled enquiries", "account growth" in a role described as new business | The phrase, and why it reads as inbound |
| Missing CRM | No CRM named across a career in sales | The absence, by role |
Each flag is listed with its quoted line. Flags are questions to ask, not reasons to reject on their own.
Forensic commercial-maths questions
Four questions, each built to reconstruct a claim in the CV. The expected answer is a number; a story in place of a number is the finding.
| Dimension | Question shape | Listen for |
|---|---|---|
| Presentation currency | "In your [role], how many times a week did you put pricing in front of a decision maker?" | A weekly number, and whether it changes when pressed |
| Conversion per stage | "Of those, how many became proposals, and how many of those closed?" | Ratios that multiply through to the claimed result |
| Average order value | "What was a typical deal worth, and what was the biggest? How many of the big ones a year?" | Whether the quota claim is a few large deals or a steady book |
| Origination | "Of the deals you closed in your best year, how many did you find yourself, cold, with no marketing lead?" | A fraction, and hesitation |
Then the cross-check, out loud: presentations × conversion × order value against the claimed quota attainment. If it does not multiply through, ask which number is wrong.
45-second cold-call roleplay
Pick one real offer from the Menu for Sale. Give the candidate: the offer in two lines, the persona (title and company type), and the single objective, which is to book a 15-minute diagnostic call, not to pitch.
Setup line: "You are calling [persona] at [company type]. You sell [offer, two lines]. You have 45 seconds. Your only objective is 15 minutes in the diary. Go."
The manager plays the prospect, gives one of the core brush-offs from the Comeback Book at the 20-second mark, and does not help.
Post-run critique script
Delivered immediately after the first run, flat and specific, in these words:
"Thanks. Three things. You pitched before you asked a question. You asked for a meeting without saying how long or what they get from it. And when I said [brush-off], you argued with it. Take a minute and go again, same persona, same objective."
Listen on the second run for the only thing being tested: did they change the three things, or defend them? A candidate who says "I was getting to that" has told you how coaching will go.
Accountability probes
- "In this role you would hold 50 accounts, capped. An untouched account leaves your list after 30 days and goes to the house pool. How does that sit with you?"
- "Every Friday at 15:30 you would sit with your manager and reconcile what you committed to on Monday against what happened. What would you want that meeting to be like?"
- "If the CRM says you made two presentations this week and you say four, which is true?"
- "Describe a time a manager held you to a number you had agreed and you missed it. What happened next?"
Listen for: acceptance with a question (good), enthusiasm with no question (check again later), negotiation of the terms before the job is offered (the finding).