CtrlK
BlogDocsLog inGet started
Tessl Logo

oh-my-ai/discovery-interview

Interactive discovery interview → structured product spec. Triggers: spec, PRD, requirements, scoping, brainstorming, new project. Uses AskUserQuestion; WebSearch/WebFetch when user wants research. Outputs user stories, acceptance criteria, constraints.

99

2.28x
Quality

100%

Does it follow best practices?

Impact

96%

2.28x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

task.mdevals/scenario-2/

Discovery Interview: Real-Time Collaboration Tool

Problem/Feature Description

A product manager named Jordan is scoping a new internal tool for a 200-person engineering organization. The tool needs to allow multiple engineers to collaborate on architecture decision records (ADRs) in real time. Jordan has a few constraints that create obvious tensions: the company is on a tight budget (wants the cheapest possible infrastructure), but engineers have complained that existing async tools are too slow and they want live updates. Jordan also mentions compliance concerns (they handle some financial data) while simultaneously wanting frictionless onboarding with no extra login steps.

Conduct a complete discovery interview with Jordan, simulating Jordan's responses. Jordan is technically literate but not an infrastructure expert. Jordan will sometimes pick conflicting goals without realizing it.

To complete this task, play both roles: conduct the interview as the interviewer and provide Jordan's responses. Jordan should naturally express the tensions described above across different questions (not all at once). Conduct the full interview process and document everything.

Output Specification

Produce the following files:

  1. interview_log.md — Full transcript of the interview. Label each question/answer exchange (Q1, Q2, etc.). Show all options presented for each question.

  2. The final spec file saved in docs/specs/ with appropriate naming. The spec should reflect the resolved decisions from the interview.

evals

CATEGORIES.md

SKILL.md

SPEC_TEMPLATE.md

tile.json