opportunity-solution-tree

Opportunity Solution Tree (OST)

Structures product discovery by connecting a desired outcome → customer opportunities → solutions → experiments. Prevents jumping to solutions before validating the problem space.

Based on Teresa Torres, Continuous Discovery Habits (2021).

---

The 4-level structure

                    ┌─────────────────────┐
                    │   DESIRED OUTCOME   │  ← single measurable metric
                    └──────────┬──────────┘
               ┌───────────────┼────────────────┐
        ┌──────┴─────┐  ┌──────┴─────┐  ┌──────┴─────┐
        │Opportunity │  │Opportunity │  │Opportunity │  ← customer pain/need
        │     A      │  │     B      │  │     C      │
        └──────┬─────┘  └──────┬─────┘  └────────────┘
        ┌──────┴───┐    ┌──────┴───┐
    ┌───┴──┐ ┌───┴──┐ ┌───┴──┐ ┌───┴──┐
    │Sol 1 │ │Sol 2 │ │Sol 3 │ │Sol 4 │  ← possible solutions
    └───┬──┘ └──────┘ └───┬──┘ └──────┘
  ┌────┴────┐         ┌───┴────┐
  │ Exp 1   │         │ Exp 2  │          ← fast experiments
  └─────────┘         └────────┘

Key principles:

• One desired outcome at a time — don't try to solve everything
• Opportunities are customer problems/needs, never solutions
• Generate ≥3 solutions per opportunity before choosing one
• Experiments are the cheapest way to validate an assumption
• The tree is a living document — update weekly as you learn

---

How to build an OST

Step 1 — Define the desired outcome

Confirm or help the user articulate one measurable outcome at the top of the tree.

Good outcomes:

• "Increase 7-day retention from 20% to 35%"
• "Reduce time-to-first-value from 3 days to 1 day"
• "Increase conversion from free to paid from 2% to 5%"

Bad outcomes (reject these):

• "Build a better onboarding" — that's a solution
• "Improve the product" — unmeasurable
• "Launch feature X" — that's an output

If the user can't state a metric: ask "What would need to be true for you to consider this effort a success?"

Step 2 — Map opportunities from research