Product Research Planning and Evidence Synthesis
Choose research methods, set defensible sample targets, and turn participant evidence into traceable product findings.
Before & after
Same prompt, same agent — the only difference is the skill.
That's a great question. User research is really important for understanding your customers. You'll want to talk to potential users, maybe run some surveys, and gather feedback on your ideas. Some teams do interviews, others prefer online questionnaires. The key is to get a representative sample and document what you learn. You might also consider running a small pilot or beta to see how real users interact with your product. It's helpful to take notes and look for patterns across your conversations. Let me know if you'd like suggestions on specific research methods.
RESEARCH PLAN FOR SAAS LAUNCH STEP 1: METHOD SELECTION • Generative interviews (5-8 users) → understand problem space • Usability test (6 users, 45 min each) → validate core flow • Concept test (20 users, survey) → validate pricing/positioning Timing: Week 1-2 interviews, Week 3 usability, Week 4 concept test STEP 2: SAMPLE SIZE & SATURATION • Generative: 5-8 interviews reach saturation on problem themes (~85% confidence) • Usability: 6 users catch 85% of task-blocking issues (Nielsen curve) • Concept: 20 responses give ±22% margin of error at 95% confidence STEP 3: INSIGHT SYNTHESIS • Code observations by theme (not opinions—count across participants) • Flag single-source anecdotes separately (do not treat as insights) • Threshold: insight requires recurrence across 2+ independent participants OUTPUT: Insight spreadsheet with method, participant count, confidence, action
About this skill
Six interviews can produce six opinions, but which findings should change the product? This skill connects the decision to the right research method, sets defensible sampling and stopping rules, and separates recurring evidence from memorable anecdotes.
What it does
- Chooses interviews, usability tests, concept tests, surveys, or behavioral validation based on the decision and uncertainty.
- Distinguishes qualitative coverage from statistical confidence, with sample calculations when the assumptions support them.
- Builds recruitment criteria, neutral questions, realistic tasks, and explicit stopping rules.
- Codes participant observations before grouping patterns, preserving contradictions and source references.
- Counts independent participants or accounts without inflating evidence through repeated quotes.
- Produces repository-ready findings with supporting evidence, limits, implications, and the next verification step.
What you get
A study plan sized to your decision, or an evidence synthesis tied to the material you provide. Findings distinguish recurring patterns, single-source observations, researcher interpretations, and unanswered questions.
Best for
Product managers, designers, founders, and research teams planning participant studies or turning interview notes and usability sessions into defensible product decisions.
SKILL.md preview
---
name: product-research-planning-and-evidence-synthesis
description: Plans product and user research by matching decisions to methods, setting defensible sampling and stopping rules, and synthesizing coded participant evidence into traceable findings. Use when the user says "how many users should we interview", "interviews or usability tests", "plan research for this feature", "synthesize these interview notes", "are these findings actually supported", "our research keeps turning into opinions", "we keep hearing conflicting feedback", or "build a research repository".
---
# Product Research Planning and Evidence Synthesis
… (sign up to view the full skill)More research & data skills
View all Research & Data skills →Source-Reconciled Research Brief
Turn supplied links into a concise brief with claim-level citations, reconciled source conflicts, and explicit evidence gaps.
Source-Traced Research Bundle
Compile many sources into one bundle where every claim is atomic, sourced, dated, tiered, and conflict-checked, in Markdown or JSON.
A/B Test Power and Validity Designer
Exact A/B sample sizes and MDE with math shown, plus the traps: unit mismatch, multiple variants, peeking, guardrail power, and SRM.
Research Routing and Cited Briefings
Route research to the right method, then produce a cited briefing with evidence gaps, disagreements, and a source audit.