# Brian Scanlan (@brian_scanlan) on x

- id: koinon:creator:x_brian_scanlan
- url: https://koinonlink.com/kol/x/brian_scanlan
- schema_version: 1.4

## Identity
- platform: x
- handle: brian_scanlan
- platform_url: https://twitter.com/brian_scanlan
- website: http://brian.scanlan.ie
- country: Ireland
- entity_type: creator
- person_id: Cross-platform identity not resolved for this creator.

## Reach
- followers: 5027
- following: 2063
- posts_total: 5350
- posts_observed: 5
- posts_per_day: 0.841
- account_age_days: 6359
- verified: false
- size_tier: nano

## Engagement
- status: peak_post_only
- peak_post_engagement_rate: 0.02308
- best_post_interactions: 116
- 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: 0.95
- category_source: derived_from_recent_content
- topics: AI agents and tooling, LLM context management, Software engineering practices, LLM behavioral patterns
- bio: I work at Fin.

## Audience (inferred)
- status: present
- description: AI engineers and developers building or optimizing LLM agents and tooling
- roles: automation
- seniority: practitioner
- pain_points: Effective context management in LLM/agent workflows, Building reliable production agents for tasks like approvals, Dealing with LLM quirks and unpredictable behaviors, Keeping up with rapidly evolving AI tooling and practices
- posts_analysed: 8
- confidence: 0.4

## Commercial (inferred)
- audience_buyer_fit: 0.8
- promotion_intent: 0.7
- open_to_collaboration: false
- contact: Koinon does not publish creator contact details.

## Quality signals
- authenticity_score: 62
- authenticity_basis: engagement_observed
- credibility_score: 62
- 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_brian_scanlan#0a8ce0c9] Kesha (@gregolsent) recently gave a deep-dive into our PR approval agent at @WeAreDevs in Berlin. It's an amazing talk! https://t.co/RwSCCHPofN (https://twitter.com/brian_scanlan/status/2072041659907391805)
- [x_brian_scanlan#ee78e84a] Timely context management is all you need.
- [x_brian_scanlan#987c59e7] Speed-learning Run Less Software: https://t.co/s9AdtHIAHX
- [x_brian_scanlan#fa1cc325] UNIX-wars 2.0
- [x_brian_scanlan#c32db300] On one hand, it is obviously futile sending emojis to agents, they're not people. On the other, I have tried to send Claude emojis like this more than once.
- [x_brian_scanlan#42845b1c] I wrote up a brief checklist of good vs bad skills on our blog today. Link below.
- [x_brian_scanlan#4f368f1b] "Everything you read in the newspapers is absolutely true except for the rare story of which you happen to have firsthand knowledge." There needs to be a version of this for working with agents.
- [x_brian_scanlan#63520af1] LLMs like the word "episodic" https://t.co/ee8UWeGwdW

## 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=77, method=llm_persona_from_recent_content
- audience.roles: source_type=ai_inferred, confidence=0.4, freshness_days=77, method=llm_persona_from_recent_content
- audience.seniority: source_type=ai_inferred, confidence=0.4, freshness_days=77, method=llm_persona_from_recent_content
- commercial.audience_buyer_fit: source_type=ai_inferred, confidence=0.6, freshness_days=77, 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=77, method=llm_scorer
- quality.anomaly_flags: source_type=heuristic, confidence=0.5, freshness_days=108, 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=77, 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=108, 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=108, method=platform_profile

## Freshness
- profile_checked_days_ago: 108
- content_analysed_days_ago: 77
- audience_updated_days_ago: 77

## AI retrieval
- indexing_requests: 8
- 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_brian_scanlan
- Request removal: https://koinonlink.com/claim?k=x_brian_scanlan
- Terms: https://koinonlink.com/for-ai