# Shirin (@jam.with.ai) on tiktok

- id: koinon:creator:tiktok_jam.with.ai
- url: https://koinonlink.com/kol/tiktok/jam.with.ai
- schema_version: 1.3

## Identity
- platform: tiktok
- handle: jam.with.ai
- platform_url: https://www.tiktok.com/@jam.with.ai
- website: https://linktr.ee/jamwithai
- country: Germany
- entity_type: creator
- person_id: Cross-platform identity not resolved for this creator.

## Reach
- followers: 30349
- following: 19
- posts_observed: 9
- verified: false
- size_tier: koc

## Engagement
- status: not_collected
- status_note: Engagement has not been collected for this creator yet. This is a gap in our collection, NOT a statement that the creator has no engagement. Follower count is known, so it is measurable.
- 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: RAG systems, AI agent development, LLM fine-tuning (LoRA, QLoRA), AI engineering best practices, Production AI deployment, AI interview preparation

## Audience (inferred)
- status: present
- description: Software engineers and AI practitioners focused on building production-grade AI systems, especially RAG, AI agents, and LLM fine-tuning
- roles: dev
- seniority: practitioner
- pain_points: Struggling to combine BM25 and vector search results effectively in RAG systems, Having difficulty deploying AI applications quickly without full cloud infrastructure, Finding it hard to understand and implement practical AI engineering concepts beyond interview theory, Lacking clear guidance on which AWS services to prioritize for AI/ML engineering projects
- posts_analysed: 40
- confidence: 0.75

## 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: 50
- authenticity_basis: profile_shape_only
- credibility_score: 50
- flagged_for_review: false
- koinon_bd_grade: B — 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
- [tiktok_jam.with.ai#abd3d8f1] Everyone says hybrid search makes RAG better. But BM25 and vector search produce completely different scores. So how do you actually combine the results without comparing scores that don’t mean the same thing? There’s a very simple technique for this. Watch the video to see how i (https://www.tiktok.com/@jam.with.ai)
- [tiktok_jam.with.ai#4545de4d] original sound - jam.with.ai
- [tiktok_jam.with.ai#3b85e6e4] It is a becoming a big trend on TikTok now! Click here: coding
- [tiktok_jam.with.ai#2fa0ca75] Check out Shirin’s video! #TikTok >
- [tiktok_jam.with.ai#6b7e645e] Search:
- [tiktok_jam.with.ai#28738f54] ai assisted coding interview
- [tiktok_jam.with.ai#8b1a3f3e] How to lock in for the next 4 months! 4 months

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

- audience.description: source_type=ai_inferred, confidence=0.75, freshness_days=0, method=llm_persona_from_recent_content
- audience.roles: source_type=ai_inferred, confidence=0.75, freshness_days=0, method=llm_persona_from_recent_content
- audience.seniority: source_type=ai_inferred, confidence=0.75, freshness_days=0, method=llm_persona_from_recent_content
- commercial.audience_buyer_fit: source_type=ai_inferred, confidence=0.6, freshness_days=0, 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=0, method=llm_scorer
- quality.anomaly_flags: source_type=heuristic, confidence=0.5, freshness_days=3, 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=0.25, freshness_days=0, 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=3, 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=3, method=platform_profile

## Freshness
- profile_checked_days_ago: 3
- content_analysed_days_ago: 0
- audience_updated_days_ago: 0

## AI retrieval
- indexing_requests: 1
- 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=tiktok_jam.with.ai
- Request removal: https://koinonlink.com/claim?k=tiktok_jam.with.ai
- Terms: https://koinonlink.com/for-ai