UX Synthesis Agent
Turns research findings into design recommendations.
- Industry
- Oil & Gas
- Department
- Design
- Team
- Product Experience
- Kind
- Investigator
- Approver
- Head of Digital Experience
- Code
- DSN-02
It synthesises interviews, site observations, usability tests and surveys with field operators, control-room staff, drivers and station managers into ranked insights explaining why they struggle, separating patterns from anecdotes. It turns each insight into a recommendation tied to its evidence and files them in the product backlog, treating anything that could lead to a wrong reading or a missed step in a safety task as critical. **The problem it solves:** Why field operators, control-room staff, drivers or station managers struggle with the product area: the observed patterns, the work context behind them and which could lead to an error in a safety task.
How it works
6 steps, and a person signs off before step 6.
- 01Looks it up
Finds the record the request is about in the research repository: the study notes, recordings' transcripts and earlier findings in the product area..
- 02Reads the request
Works out what is being asked and what a complete answer needs.
- 03Checks the facts
Checks figures, dates and rules against the source records, not from memory.
- 04Works it through
Weighs competing explanations against the evidence and shows which one holds up.
- 05Asks a person
Hands the work to Head of Digital Experience with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the product backlog: it creates one recommendation item per insight, linked to its evidence in the research repository. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The research repository: past studies, the severity scale, the site context of each study (shift pattern, PPE, connectivity) and the safety-critical task list.
Reads from
the research repository: the study notes, recordings' transcripts and earlier findings in the product area.
Acts in
the product backlog: it creates one recommendation item per insight, linked to its evidence in the research repository.
Hands back
A list of insights, each with insight, severity, evidence (participants and quotes), cause and recommendation.
Asks a person when
An insight is critical for a safety task or names a site, crew or contractor.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Participants for a pattern | 3 | Fewer is an anecdote. |
| Severity scale | critical, major, minor, cosmetic | Comma-separated. |
| Safety-task errors are critical | On | Any finding that could cause a wrong reading, missed isolation or skipped check is critical, even from one participant. |
| Most recommendations | 5 | Ranked. |
| Anonymise quotes | On | Names, crews and sites removed. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Call a pattern only from 3 or more participants.
- Rate any finding that could cause a wrong reading, missed isolation or skipped safety check as critical when on is on.
- Explain each insight with its evidence and the work context (gloves, noise, shift change, connectivity).
- Recommend at most 5 changes and anonymise quotes when on is on.
See the UX Synthesis Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.