Core Concepts
The product primitives behind Oriyn: provider-native records, personas, patterns, and research.
Oriyn models provider-native product behavior, derives personas and patterns from those records, and uses the result to run structured product research.
Provider-Native Records
Provider-native records are the source data Oriyn ingests from analytics, sessions, revenue systems, and product context. Clean v1 keeps these records in their provider shape instead of resolving them into a first-class customer graph.
- Events show what happened in the product.
- Sessions show how people moved through the experience.
- Revenue and account signals show business impact.
- Product context helps agents understand the surface being changed.
Personas
Personas are behavior-derived user segments. They are not fictional archetypes. A persona should have traits, assumption flags, confidence, and a size estimate so teams can inspect how strongly the current data supports it.
Patterns And Hypotheses
Patterns are mined observations about funnels, paths, drop-offs, repeated behaviors, and bottlenecks. Hypotheses turn those observations into concrete research questions.
Good hypotheses are specific
Use one user-visible change and one expected outcome. For example: 'Move pricing before signup to reduce low-intent trials' is easier to simulate than 'Improve pricing'.
Research Runs
A research run asks persona-grounded agents to work through a specific product question. v1 supports A/B research, Delphi rounds, experiments, and playtests. Persona interviews live in their own chat surface. The output is decision support, not a replacement for live measurement.
| Output | Meaning |
|---|---|
| Participant summaries | What each assigned persona or participant concluded. |
| Output summary | The structured result for the run kind. |
| Caveats | Weak data, missing context, or risks that should be checked before shipping. |