Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
ai-persona-building - Skill - OpenSmartRoute
Skillv1.0.0
ai-persona-building
See `content/06-decision-tree.xml`. The tree starts from the question "Do we have N >= 8 interviews and behavioral data?" and routes observable input signals to a concrete action, each leaf referencin
Imported from faionfaion/faion-network (skills/faion/knowledge/research/ai-persona-building/AGENTS.md). Install upstream with npx skills add faionfaion/faion-network --skill ai-persona-building. Copyright stays with the author.
AI Persona Building Workflow
Summary
One-sentence: Builds research-grounded personas from interview transcripts + behavioral data using staged LLM passes with explicit segment criteria and human verification.
One-paragraph: Builds research-grounded personas from interview transcripts + behavioral data using staged LLM passes with explicit segment criteria and human verification. The methodology is testable end-to-end: each artefact it produces conforms to the JSON Schema in content/02-output-contract.xml, every claim in the body resolves to a rule in content/01-core-rules.xml, and the decision-tree in content/06-decision-tree.xml routes observable inputs to the right rule.
Ефективно для:
Швидкий перший draft персон з 8-20 інтерв'ю замість 5-day workshop.
Behavioral-data fusion: інтерв'ю + survey + product signals в одну особу.
Explicit segment criteria — кожна персона має сегмент-membership rules.
Verification gate: researcher підписує перед використанням у roadmap.
Applies If (ALL must hold)
≥8 інтерв'ю + behavioral data на ту ж cohort.
Існує сегментація гіпотеза, яку треба підтвердити/спростувати.
Researcher доступний для верифікації результату.
Skip If (ANY kills it)
< 8 інтерв'ю — недостатньо для статистично значущих сегментів.
Marketing fluff personas без data backing — це не цей workflow.
Бренди без segmentation — single-persona shortcut кращий.
Routing tree on observable signals → rule in 01-core-rules.xml
600
Task Routing
Sub-task
Model
Rationale
classify-input
sonnet
Light judgment; identifies branch in decision tree.
draft-output
sonnet
Drafting the output artefact per schema.
validate-output
haiku
Mechanical schema validation via script.
Templates
File
Purpose
templates/persona-spec.md.j2
Persona spec skeleton
templates/persona-spec.md
Persona spec skeleton Generated from templates/persona-spec.md.j2 by tpl-jinja --migrate; do not hand-edit.
templates/personas.json
Machine-readable personas matching schema
Scripts
File
Purpose
When to call
scripts/validate-ai-persona-building.py
Validate output artefact against schema in 02-output-contract.xml
CI on each artefact change; pre-commit
Related
[[ai-interview-analysis]]
[[interview-note-synthesis-ai]]
[[ai-coding-of-qualitative-data-protocol]]
Decision tree
See content/06-decision-tree.xml. The tree starts from the question "Do we have N >= 8 interviews and behavioral data?" and routes observable input signals to a concrete action, each leaf referencing a rule from 01-core-rules.xml. Apply it whenever the input shape changes or before scaling a pilot run.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
yaml
targets:
- https://api.opensmartroute.ai/api/v1/registry/faionfaion-faion-network-ai-persona-building/manifest # or paste the manifest below
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "faionfaion-faion-network-ai-persona-building",
"kind": "skill",
"name": "ai-persona-building",
"description": "See `content/06-decision-tree.xml`. The tree starts from the question \"Do we have N >= 8 interviews and behavioral data?\" and routes observable input signals to a concrete action, each leaf referencing a rule from `01-core-rules.xml`. Apply it whenever the input shape changes or before scaling a pilot run.",
"publisher": "faionfaion",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"github-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"See `content/06-decision-tree.xml`. The tree starts from the question \"Do we have N >= 8 interviews and behavioral data?\" and routes observable input signals to a concrete action, each leaf referencing a rule from `01-core-rules.xml`. Apply it whenever the input shape changes or before scaling a pilot run."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-agents",
"repository": "https://github.com/faionfaion/faion-network",
"path": "skills/faion/knowledge/research/ai-persona-building/AGENTS.md",
"ref": "8e31684537e64d45c75264b1e0a2384f9b024a34",
"url": "https://github.com/faionfaion/faion-network/blob/8e31684537e64d45c75264b1e0a2384f9b024a34/skills/faion/knowledge/research/ai-persona-building/AGENTS.md",
"key": "faionfaion/faion-network/skills/faion/knowledge/research/ai-persona-building/AGENTS.md"
}
},
"instructions": "# AI Persona Building Workflow\n\n## Summary\n\n**One-sentence:** Builds research-grounded personas from interview transcripts + behavioral data using staged LLM passes with explicit segment criteria and human verification.\n\n**One-paragraph:** Builds research-grounded personas from interview transcripts + behavioral data using staged LLM passes with explicit segment criteria and human verification. The methodology is testable end-to-end: each artefact it produces conforms to the JSON Schema in `content/02-output-contract.xml`, every claim in the body resolves to a rule in `content/01-core-rules.xm",
"cost": {
"context_tokens": 1019
}
}
Fetch it by URL: GET /api/v1/registry/faionfaion-faion-network-ai-persona-building/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
