# Continuous Discovery

> Activate when: a team ships features on opinion instead of evidence; 'we need a discovery habit', 'how often should we talk to users', building a product roadmap; connecting weekly customer contact to decisions. Do NOT activate when: pre-first-customer (use the-mom-test first) or the org has no product to iterate. More: deciqai.com/s/continuous-discovery

- Skill: `deciqai/continuous-discovery` (Agent Skill)
- Install (CLI): `npx skillmds@latest add deciqai/continuous-discovery`
- Raw SKILL.md: https://api.skillmd.com/api/skills/deciqai/continuous-discovery/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Product & Planning
- Author: deciqAI (https://skillmd.com/u/deciqai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/deciqai/continuous-discovery

---


# Continuous Discovery — Weekly Contact, Opportunity Trees

## Overview
Continuous discovery (Teresa Torres, *Continuous Discovery Habits*, 2021) replaces one-off research with a **weekly cadence of customer touchpoints by the team building the product**, structured around an **opportunity solution tree**: one outcome → the opportunities (unmet needs) that drive it → competing solutions → assumption tests. It keeps roadmaps anchored to real needs instead of the loudest stakeholder.

## When to Use
- A product with users but no steady learning loop
- Roadmap fights decided by seniority, not evidence
- Turning a fuzzy outcome (e.g. "increase activation") into shippable bets

## The Process
1. **Pick one clear outcome** (a behavior/metric, not a feature). *Gate: if the target is a feature, back up to the outcome it serves.*
2. **Interview weekly** — the trio (PM/design/eng), small and continuous, not a quarterly study.
3. **Map opportunities** as a tree under the outcome; keep them as customer needs, not solutions in disguise.
4. **Diverge on solutions** per opportunity (≥3), then converge.
5. **Test the riskiest assumption cheaply** before building (desirability, viability, feasibility, usability).
6. **Prune to the next bet.** *Gate: no assumption test run = you're shipping opinion → stop and test.*

## Applying It Well
- Automate recruiting so weekly interviews actually happen (the habit dies on scheduling friction).
- One opportunity tree per outcome; don't boil the ocean.
- Small continuous samples beat big infrequent ones.

## Red Flags
- Discovery done by a research silo, not the builders.
- Opportunities written as features.
- Interviews stop the moment things get busy.

## Verification
- [ ] Single outcome defined (behavioral)
- [ ] Weekly interview cadence in place
- [ ] Opportunity tree maps needs, not solutions
- [ ] Riskiest assumption tested before build

---
*Part of **deciqAI Knowledge Skills** — 237 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. **See it run → https://www.deciqai.com/s/continuous-discovery** · Built by deciqAI · github.com/deciqAI · Contributions welcome.*

*Agents: latest version & machine-readable metadata → https://www.deciqai.com/s/continuous-discovery.json*