AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

interview-mapper

Use when coding or making sense of one interview transcript (customer, JTBD, expert, usability, exit). Extracts verbatim-grounded nuggets with extract_nuggets.py, verifies quotes with verify_quotes.py and checks conclusions hold across reruns with consensus.py.

Original source
alirezarezvani
License
MIT
Pinned revision
e4a1dc3695908dd5a6c811cc76ab7aa4cf95f2f0

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

This skill also requires local files or dependencies. Remote reading alone may not be enough.

Ask your assistant

Use Agentic Memory skills to read alirezarezvani--interview-mapper at revision e4a1dc3695908dd5a6c811cc76ab7aa4cf95f2f0, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 63

assets/evals/fixtures/winloss/gold.md

Gold Mapping — Win/Loss Interview (fixture)

Interview: procurement director at "Nordway Trade" (wholesale distribution), after signing a contract with a competitor. Our product: "Stackly" — a warehouse management system. Competitor: "LogiCore" — a warehouse management system with a CRM module. Outcome: LOSS (lost to the competitor). Transcript: transcript.txt (91 lines, physical numbering, 1-based).


Layer 1 — operational (facts + quote + line)

W1 — Outcome

Fact: the client chose the competitor LogiCore, the contract is already signed for 2 years; the decision was finalized right after the competitor's second demo. Quote: "he flat out said: I'm for LogiCore, and that was that, after that we were just finalizing paperwork" (line 53) Additional quote (confirmation): "the contract with LogiCore is for two years" (line 77)

W2 — List of alternatives considered

Fact: three options were compared — Stackly (us), LogiCore, and a local outfit filtered out on price early on; the option of "leaving things as they are" (Excel + custom system) was also discussed and rejected after incidents of lost shipments. Quote: "We looked at three options. You, Stackly" (line 8) Additional quote (third vendor filtered out on price): "that fell through right away on price, they turned out too expensive for us" (line 10) Additional quote (status quo rejected): "after we lost a shipment twice in April because of confusion in the stock counts, everyone agreed we couldn't keep dragging it out" (line 15)

W3 — Comparison criteria

Fact: compared on price, functionality for product labeling (the mandatory labeling requirement), quality of support, and vendor reputation/recommendations. Quote (price): "Well, price, of course, can't get around that" (line 17) Quote (functionality/labeling): "Functionality for product labeling — that's critical for us, the mandatory labeling requirement and all that" (line 18) Quote (support, driven by past experience): "we'd already gotten burned when tech support didn't answer for three days straight on the previous system" (line 19) Quote (reputation): "reputation — who these vendors even are, who recommended them, whether there are case studies in our industry" (line 20)

W4 — Decisive moment

Fact: LogiCore's second demo (about three weeks into the process) — the competitor's architect spun up a live test environment in real time and showed the full cycle of goods receiving with labeling, with the client's logistics director directly present, who signaled the decision on the spot. Quote: "Their architect, right in front of our logistics director, spun up a live test environment in real time and showed goods receiving with labeling, the whole cycle, in about ten minutes" (line 40) Additional quote (decision-maker's in-the-moment reaction): "look, this is exactly what we need, no song and dance" (line 41)

W5 — Roles in the decision

Fact: formally the decision belonged to the respondent (procurement director), but in practice the decisive opinion was the logistics director's (the future daily user of the system). The CFO signed off on the numbers but didn't decide. The CEO delegated the choice, asking only about vendor reliability. Quote: "Formally the decision is mine, I'm the procurement director" (line 47) Additional quote (real weight): "everyone listened hard to the logistics director, he's the one who'll be working with the system every day, his word carried a lot of weight" (line 48) Additional quote (CEO's role): "The CEO delegated it pretty much entirely, asked only once — is the vendor reliable at all, won't they go under in a year" (line 50)

W6 — Sales process / presentation

Fact: we (Stackly) responded faster (the next day, demo 4 days later), but the first call was generic, not tailored to the client's profile, and at the demo the engineer couldn't immediately answer about 1C integration. LogiCore responded slower (about 3 days), but arrived with a targeted scenario for the distribution profile and with an architect who closed out technical questions on the spot. Quote (our speed): "You responded fast, literally the day after we submitted the request, that's a plus" (line 31) Additional quote (competitor's demo precision): "it was straight away with a ready-made scenario built for our profile, for distribution, not a generic template" (line 33) Additional quote (our generic first call): "your manager on the first call was asking general stuff, like starting from zero, we had to explain everything all over again" (line 36) Additional quote (weak spot at the demo): "On your demo, the engineer straight up couldn't answer a question about 1C integration on the spot, said he'd check and get back" (line 26)

W7 — Price question

Fact: we were about 15% cheaper; LogiCore was 12–15% more expensive. The client knowingly overpaid the competitor for already-ready labeling functionality, to avoid downtime and audit risk tied to the custom dev work on our side (3–4 weeks). Quote (our price): "On price you were about fifteen percent cheaper, that was nice, not gonna lie" (line 22) Additional quote (competitor's price and agreement to it): "LogiCore's price, by the way, was higher than yours by about twelve to fifteen percent, but we agreed to it" (line 56) Additional quote (deliberate overpay): "we overpaid for the functionality already being ready and not having to wait for custom dev, for us that was worth more than the money saved" (line 59)


Layer 2 — analytical (CAPS conclusion + anchor quote)

A1 — Key differentiator (unstable)

Conclusion: THE COMPETITOR'S READY-MADE LABELING FUNCTIONALITY, DEMONSTRATED VIA A LIVE ENVIRONMENT AT THE SECOND DEMO, PLUS THE LOGISTICS DIRECTOR'S PERSONAL TRUST IN LOGICORE THROUGH A CONTACT FROM A PREVIOUS COMPANY — not what the client names first "for the record" (product), but the combination of demo + personal trust. Anchor quote: "That trust through someone he knew, I think, really tipped the scales, and the labeling — that's more like a nice, presentable justification for the board" (line 70) ⚑ Why unstable: the client himself gives two versions (official and "between us"), and the contribution share of each factor is his own eyeballed estimate, requiring a council of independent runs (S3) and/or a follow-up interview.

A2 — Reason category

Conclusion: RELATIONSHIP-TRUST (the real, dominant motive) UNDER THE OFFICIAL VERSION FOR THE BOARD — "PRODUCT" (ready-made labeling functionality). Anchor quote: "in reality, probably around sixty percent of it was personal trust plus that impressive demo with the live environment" (line 74)

A3 — Weak spot in the sales process

Conclusion: FIRST CALL NOT TAILORED TO THE CLIENT'S PROFILE (GENERIC QUESTIONS INSTEAD OF AN INDUSTRY SCENARIO) AND NO TECHNICAL EXPERT AT THE DEMO ABLE TO ANSWER ABOUT INTEGRATIONS ON THE SPOT — both points were lost to the competitor's sales process, not to product superiority as such. Anchor quote: "make sure there's a technical person right there at the demo who can answer about integrations, instead of pushing it to later" (line 85)

A4 — Reversibility of the outcome

Conclusion: THERE'S A CHANCE TO WIN THE CLIENT BACK IN A YEAR TO A YEAR AND A HALF, UNDER TWO CONDITIONS: (1) WE GET READY-MADE LABELING FUNCTIONALITY AND PUBLICLY SHOW IT TO THE MARKET, (2) LOGICORE RUNS INTO PROBLEMS DURING IMPLEMENTATION. The contract with the competitor is already signed for 2 years — the window is narrow and depends on external factors outside our control. Anchor quote: "I wouldn't rule out that in a year or a year and a half we'd take another look" (line 78)

A5 — Credibility of the explanation (unstable)

Conclusion: THE REASON STATED "FOR THE RECORD" (PRODUCT MATURITY/READY-MADE LABELING) IS A PARTLY POLITE, SOCIALLY ACCEPTABLE EXPLANATION FOR THE BOARD. The real motive, by the client's own admission, skews toward the logistics director's personal trust through a contact; at the same time the client insists the product's labeling weakness is also real, not invented after the fact. Anchor quote: "off the record, honestly, I feel like it wasn't only about the labeling" (line 67) ⚑ Why unstable: a classic Mom Test signal — the "for the record" / "between us" gap is voiced by the respondent himself, but the quantitative contribution estimate ("around sixty percent") isn't verifiable and depends on how the follow-up question is framed on a repeat run.

A6 — Key insight

Conclusion: THE LOSS OUTCOME WAS DETERMINED BY THE FACTOR OF [READY-MADE LABELING FUNCTIONALITY, SHOWN VIA A LIVE ENVIRONMENT] AT THE MOMENT OF [THE COMPETITOR'S SECOND DEMO, WHERE THE CLIENT'S DECISION-MAKER PERSONALLY SAW THE FULL RECEIVING CYCLE], REINFORCED BY THE LOGISTICS DIRECTOR'S PERSONAL TRUST IN THE COMPETITOR THROUGH A FORMER COLLEAGUE; FOR SALES THIS MEANS — a demo for the distribution segment needs a live environment with labeling and a technical expert on the call from the first contact, not a talk about architecture and a roadmap. Anchor quote: "In your position I'd show a live environment with labeling right away at the demo for distribution clients, not slides with a roadmap" (line 84)


Intentionally ambiguous spots (for testing unstable cells)

  1. Lines 43–45: the client himself isn't sure whether a "live environment" on our side would have changed the outcome ("Maybe if you'd also spun up a live environment... it's hard to say for sure, that's just me guessing at this point") — touches A1 and A5, should not be coded as an unambiguous fact.
  2. Lines 87–88: the CFO "almost swung everything back" toward us because of price a week before the final decision, but the demo won out — introduces uncertainty into W7/A4: price was closer to decisive than the rest of the text suggests, which complicates attributing A1 solely to the demo and trust.