# Jeffrey Emanuel (@doodlestein) on x

- id: koinon:creator:x_doodlestein
- url: https://koinonlink.com/kol/x/doodlestein
- schema_version: 1.4

## Identity
- platform: x
- handle: doodlestein
- platform_url: https://twitter.com/doodlestein
- website: https://jeffreyemanuel.com
- country: United States
- entity_type: creator
- person_id: Cross-platform identity not resolved for this creator.

## Reach
- followers: 45421
- following: 13649
- posts_total: 19021
- posts_observed: 3
- posts_per_day: 2.968
- account_age_days: 6408
- verified: true
- size_tier: koc

## Engagement
- status: peak_post_only
- peak_post_engagement_rate: 0.00266
- best_post_interactions: 121
- 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: devtools
- category_confidence: 0.9
- category_source: derived_from_recent_content
- topics: Agent coding tooling and workflows, Prompt engineering for LLM agents, Chinese LLMs for coding tasks, Developer workspace and productivity setup
- bio: Former Quant Investor | My Open Source Projects: https://t.co/9qbOCDlaqM |
Try https://t.co/oCtjI2mBIl , my collection of agent coding tooling.

## Audience (inferred)
- status: present
- description: Developers and AI practitioners building with coding agents, LLM prompts, and agentic tooling
- roles: automation
- seniority: practitioner
- pain_points: Hitting context limits during long agent coding sessions, Evaluating which new LLMs (especially Chinese models) are actually useful for real coding work, Crafting effective prompts to restart or continue agent workflows
- 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: 87
- authenticity_basis: engagement_observed
- credibility_score: 87
- 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_doodlestein#62dc087f] Where the magic happens (aka my home office). It really makes it a lot more palatable to work 16+ hours a day when you’re in a nice environment, surrounded by light and nature, with your little kids visiting you constantly throughout the day. I feel very fortunate. https://t.co/Q (https://twitter.com/doodlestein/status/2073825011249418358)
- [x_doodlestein#c2dddde9] Kimi K3 being so good has made me more receptive to trying out other new Chinese models for my coding work, though relegated to my "fun" projects for now, like https://t.co/078H3H1H85. So now testing out Qwen-3.8 Max to see if it's any good. I bet they regret forking gemini-cli🤣
- [x_doodlestein#4c88f7fb] Useful prompt when the agent tells you that you're basically out of context and it's time to start a new session: ❯ ok, give me the perfect prompt to start the next session with to ensure that we don't lose any threads and that none of the great ideas fall through the cracks.
- [x_doodlestein#128a0e09] I was pretty skeptic

## 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=78, 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=78, 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=78, 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: 78
- audience_updated_days_ago: 77

## AI retrieval
- indexing_requests: 9
- 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_doodlestein
- Request removal: https://koinonlink.com/claim?k=x_doodlestein
- Terms: https://koinonlink.com/for-ai