euroconic
- 7 skills
- 0 followers
- 11 hours ago last updated
- ▌ AI Eval Scorer · euroconicTake an AI feature spec and produce a full eval harness - extracted behaviors, golden + edge + adversarial test cases, a judge rubric, and a scorecard. Use before shipping any LLM-powered feature, when "it works on my examples" isn't enough, or when stakeholders ask "how do you know it's good". Triggers on phrases like "build evals for this feature", "score this AI feature", "test cases for LLM feature", "eval rubric", "AI quality scorecard", "оцени AI-фичу", "сделай эвалы".
- ▌ Feedback Triage · euroconicCluster + score a raw pile of customer feedback (200+ items from Intercom, Zendesk, sales notes, support tickets, NPS comments) into ranked themes with a composite Volume × Severity × Strategic Fit × Customer Weight priority score. Scoring sub-scores stay visible so reviewers can challenge specific dimensions, not just the final number. Use instead of basic feature-request analyzers when you have multi-source feedback and need composite priority scoring with visible sub-scores, not just frequency counts. Triggers on phrases like "triage this feedback", "cluster these requests", "themes in this feedback", "synthesize Intercom export", "make sense of NPS dump", "quarterly feedback review", "process sales-team feedback", "разобрать обратную связь", "темы в фидбеке".
- ▌
- ▌ Product Trio Session · euroconicSimulate a Product Manager, Designer, and Engineer working a feature in real time, surfacing the disagreements and tradeoffs you'd discover in an actual trio call. Output is a transcript with 3 forced rounds (reactions, disagreement, convergence) plus structured meeting notes (agreed direction, open questions, deliberate cuts, risks accepted). Use instead of generic PM brainstorming when you want a real transcript with forced disagreement, not a flat idea list. Triggers on phrases like "run a product trio", "simulate a trio session", "PM designer engineer discussion on X", "product trio on X", "rehearse trio call on X", "продакт-трио на X", "разговор PM, дизайнера и разработчика про X".
- ▌ Synthetic User Interview · euroconicGenerate calibrated synthetic personas and run simulated discovery interviews to pressure-test a hypothesis before talking to real users. Use when warming up before real research, sanity-checking a problem statement, exploring low-volume or hard-to-reach segments, or stress-testing assumptions about a buyer. Triggers on phrases like "simulate user interview", "synthetic interview", "fake user research", "pretend to be my target customer", "interview a persona about X", "what would a [role] say about", "проинтервьюируй персону".
- ▌ Prd Critic · euroconicRed-team a PRD by simulating a skeptical PM, a senior engineer, and a target customer ripping it apart before you ship it for review. Use after drafting a PRD and before sharing with eng leads, exec reviewers, or other stakeholders. Triggers on phrases like "critique this PRD", "review my PRD", "find holes in this spec", "what's wrong with this PRD", "stress-test my spec", "PRD red team", "разнеси мой PRD", "найди дыры в спеке".
- ▌ Prd Builder · euroconicOpinionated PRD generator that forces a TL;DR, hypothesis + counter-hypothesis, explicit Out-of-scope cuts with reasoning, and a mandatory 3-question intake when the brief is a one-liner. Use instead of generic PRD generators when you want a doc that fights back against vague asks - the 3-question intake and counter-hypothesis are non-negotiable here. Triggers on phrases like "draft a PRD with hypothesis and metrics", "PRD that pushes back on vague asks", "structured product spec from fuzzy ask", "PRD for X", "feature spec for X", "turn this into a PRD I can react to", "напиши PRD по фиче X", "сделай спеку с гипотезой".