Decision 01
Don’t confuse agent failure with customer friction.
Agent constraint UX finding
An automated browser failing does not prove a human customer experiences the same problem.
UX Scout
Understand the journey beyond your product
Overview
UX Scout is an AI-powered customer journey tool that investigates how goals can be accomplished across the public web. Give Scout a goal, not a predefined path. It independently navigates the web and returns the journey, evidence, constraints, and defensible UX findings.
Role
Product Strategy, UX, and Development
Timeline
48-hour sprint · August 2026
Tools
React/Vite, Node/TypeScript, OpenAI Agents SDK, Playwright MCP
Opportunity
The customer journey doesn’t begin at your website.
Product and UX teams evaluate the experiences they own. However, customer journeys extend far beyond them, revealing friction and decisions product analytics can’t see. What if AI could discover those paths autonomously?
Prototype
Give Scout the goal. Not the route.
-
01
Define
Describe what the customer is trying to accomplish.
-
02
Explore
Scout controls a real browser and independently determines how to pursue the goal.
-
03
Investigate
Scout returns the path, evidence, constraints, and defensible UX findings.
System
The challenge wasn’t browsing. It was judgment.
Decision 02
Finding nothing is a valid finding.
0 UX findings
Scout isn’t rewarded for manufacturing criticism when the evidence doesn’t support it.
Decision 03
Verify meaning, not just facts.
“Newest”
Newest released?
Newest announced?
Scout checks ambiguous qualifiers before claiming completion. If meaning can’t be verified, it returns a partial result instead.
Decision 04
More autonomy isn’t always better.
Keep exploring? Stop with what’s verified?
Stopping rules and turn limits keep Scout from wandering indefinitely while preserving useful partial results.
User testing
Real journeys changed the system.
Testing exposed problems I couldn’t anticipate from the initial prototype. Each failure became an input to the next iteration.
Iteration 01
Authenticated journey
Tried
An account-based journey with login.
Learned
2FA authentication introduced dependencies Scout couldn’t safely resolve.
Changed
Narrowed the prototype to public journeys.
Iteration 02
Open-ended exploration
Tried
Letting Scout determine how long to explore.
Learned
More autonomy led to long, expensive wandering.
Changed
Added turn limits and bounded exploration.
Iteration 03
Goal interpretation
Tried
Verifying that Scout found the requested facts.
Learned
A fact could be correct while answering the wrong interpretation.
Changed
Required Scout to verify ambiguous qualifiers before claiming completion.
Iteration 04
Incomplete journeys
Tried
Returning results only after Scout completed the journey.
Learned
An incomplete journey could still contain useful, verified information.
Changed
Preserved and returned verified partial results when Scout couldn’t complete the goal.
Metrics
Testing the concept against real journeys.
6
Runs
3
Usable
1
Complete
2
Evidence-backed UX findings
| Journey | Result | Usable | Runtime | UX findings |
|---|---|---|---|---|
| Product information | Complete | Yes | 1:47 | 0 |
| Local service comparison | Partial | Yes | 2:18 | 1 |
| Airline policy: open start | Partial | No | 1:50 | 0 |
| Airline policy: supplied start | Partial | No | 2:10 | 0 |
| Entertainment / ticketing | Partial | Yes | 2:39 | 1 |
| Product recommendation | Partial | No | 2:05 | 0 |
- Complete
- Answered the requested goal.
- Partial
- Answered only part of the requested goal.
- Usable
- Despite incompleteness, returned enough verified information to be useful.
Workflow
Under the hood.
User goal
UX Scout
OpenAI agent
Playwright MCP
Chromium
Public web
Structured evidence
Journey report
Technology
- React + Vite
- Node.js + TypeScript
- OpenAI Agents SDK
- Playwright MCP
- Chromium
Outcome
The idea outgrew the approach.
What I learned
Playwright MCP could investigate individual experiences, but it couldn’t reliably follow a customer journey wherever that journey led.
Scout worked when browser automation could access the experience. But real journeys crossed sites that blocked, challenged, or otherwise prevented automated navigation, leaving gaps Scout couldn’t resolve.
What that means
The opportunity still exists. This just isn’t the right approach to solve it end to end.
The original problem remains: product teams have limited visibility into customer journeys that extend beyond the experiences they own. UX Scout showed me that browser automation alone isn’t enough to document those journeys reliably. Solving that problem would require a different approach, or a combination of approaches.