# Rouzbeh (@JustRouzbeh) on x

- id: koinon:creator:x_justrouzbeh
- url: https://koinonlink.com/kol/x/JustRouzbeh
- schema_version: 1.4

## Identity
- platform: x
- handle: JustRouzbeh
- platform_url: https://twitter.com/JustRouzbeh
- website: http://rouzbeh.dev
- entity_type: creator
- person_id: Cross-platform identity not resolved for this creator.

## Reach
- followers: 1391
- following: 528
- posts_total: 8237
- posts_observed: 2
- posts_per_day: 1.433
- account_age_days: 5750
- verified: true
- size_tier: nano

## Engagement
- status: peak_post_only
- peak_post_engagement_rate: 0.00288
- best_post_interactions: 4
- measurement_source: x_post_interactions
- measurement_formula: interactions on one post — likes, or likes + reposts + replies depending on the discovery path (the two are not distinguishable in the stored data)
- comparable_pool: peak_interactions
- status_note: We have only the single best observed post, so no mean exists. peak_post_engagement_rate is an UPPER BOUND, systematically higher than an average — never compare it against an average rate.
- unit_note: engagement_rate and peak_post_engagement_rate are ratios (0-1); avg_interactions_per_post and best_post_interactions are absolute counts. Read status before reading any number: a null rate has several different causes and status says which one applies here.

## Content
- category: software
- subcategory: ai_tools
- category_confidence: 0.9
- category_source: derived_from_recent_content
- topics: AI model leaderboards and evaluation, Agent testing frameworks with live environments, Local AI practicality for real work, AI performance consistency vs personality
- bio: iOS dev shipping indie apps, I share how to build & get paid
@Spaceport_build · iOS boilerplate
@Lighthouse_app_ · Validate your idea
@sprintKitApp · PM copilot

## Audience (inferred)
- status: present
- description: Indie iOS developers and solo app builders who ship apps and integrate AI tools
- roles: dev
- seniority: practitioner
- pain_points: Choosing AI models based on hype instead of reliable benchmarks, Building proper agent evaluations that work in real environments, Determining if local AI is production-ready or still demo-only, Getting consistent output quality over flashy personality features
- posts_analysed: 4
- confidence: 0.4

## Commercial (inferred)
- audience_buyer_fit: 0.9
- promotion_intent: 0.8
- open_to_collaboration: false
- contact: Koinon does not publish creator contact details.

## Quality signals
- authenticity_score: 60
- authenticity_basis: engagement_observed
- credibility_score: 60
- flagged_for_review: false
- koinon_bd_grade: A — measures Koinon partner-outreach fit, not creator quality
- interpretation: Signals for triage, not verdicts. A flag means the profile is worth a manual check.

## Evidence
- [x_justrouzbeh#046f940f] Picking a model on vibes is always a costly bet. These 3 leaderboards actually give you signal: 1. Arena Leaderboard Human preference across text, code, vision -> https://t.co/1g479HTBJx 2. Artificial Analysis Speed, cost, latency, context window -> https://t.co/8tj1UQpHWL 3. SWE (https://twitter.com/JustRouzbeh)
- [x_justrouzbeh#8964a627] This is the right direction for agent evals. Running against a live Supabase environment with MCP + CLI, then scoring with deterministic checks + LLM judge, is much more useful than synthetic coding benchmarks that never touch real infrastructure.
- [x_justrouzbeh#9acaa9a7] Is local AI actually usable for real work in 2026, or are we still mostly playing with demos?
- [x_justrouzbeh#8788b5a2] Personality is nice, but I’ll take consistent performance over a “trusted friend” vibe any day. With Opus 5 I’m still optimizing for fewer

## Provenance
Every inferred field below carries how it was produced. Facts stay facts; inferences stay inferences.

- audience.description: source_type=ai_inferred, confidence=0.4, freshness_days=76, method=llm_persona_from_recent_content
- audience.roles: source_type=ai_inferred, confidence=0.4, freshness_days=76, method=llm_persona_from_recent_content
- audience.seniority: source_type=ai_inferred, confidence=0.4, freshness_days=76, method=llm_persona_from_recent_content
- commercial.audience_buyer_fit: source_type=ai_inferred, confidence=0.6, freshness_days=80, method=llm_scorer — Relative signal within Koinon indexing, not a market-wide score.
- commercial.promotion_intent: source_type=ai_inferred, confidence=0.6, freshness_days=80, method=llm_scorer
- quality.anomaly_flags: source_type=heuristic, confidence=0.5, freshness_days=110, method=profile_snapshot_and_engagement_ratio_heuristic — Means "worth a manual check", NOT confirmed fraud. Flags can be wrong and are not a verdict about the person.
- quality.authenticity_score: source_type=heuristic, confidence=0.5, freshness_days=80, method=Profile-shape heuristic from a single snapshot (follower count, following ratio, account age, posting volume, verification), reduced for engagement red flags where post engagement was collected. Where only a follower count is available the score saturates at 58. — The input set differs by platform; do not compare this score across platforms.
- quality.koinon_bd_grade: source_type=ai_inferred, confidence=0.5, freshness_days=110, method=llm_partner_fit_classifier + fit_score >= 0.6 AND authenticity >= 60 => A; fit_score >= 0.4 AND authenticity >= 45 => B; else C. authenticity < 30 or a promotional-pattern flag => quarantine. — Koinon partner-outreach fit, not creator quality.
- reach.followers: source_type=observed, confidence=0.95, freshness_days=110, method=platform_profile

## Freshness
- profile_checked_days_ago: 110
- content_analysed_days_ago: 80
- audience_updated_days_ago: 76

## AI retrieval
- indexing_requests: 7
- user_triggered_requests: 0
- note: Being indexed in bulk is not the same as being retrieved to answer a question.

## This profile
- Claim or correct: https://koinonlink.com/claim?k=x_justrouzbeh
- Request removal: https://koinonlink.com/claim?k=x_justrouzbeh
- Terms: https://koinonlink.com/for-ai