{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"tool_thrivelink","slug":"thrivelink","name":"ThriveLink","type":"product","url":"https://www.thrivelink.ai","page_url":"https://unfragile.ai/thrivelink","categories":["data-analysis"],"tags":[],"pricing":{"model":"paid","free":false,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"tool_thrivelink__cap_0","uri":"capability://data.processing.analysis.real.time.engagement.metric.aggregation.and.dashboard.visualization","name":"real-time engagement metric aggregation and dashboard visualization","description":"Collects employee engagement signals from multiple sources (surveys, performance data, attendance patterns) and aggregates them into a unified real-time dashboard with low-latency metric updates. The system likely uses event-streaming architecture to ingest data from connected systems and materialized views to serve dashboard queries without expensive aggregations on read. Metrics are computed incrementally as new data arrives rather than batch-processed, enabling sub-minute visibility into engagement trends.","intents":["I need to see current engagement levels across my clinical teams without waiting for monthly reports","I want to identify which departments or shifts have declining engagement in real-time to intervene early","I need a single pane of glass for engagement metrics instead of pulling data from multiple HR systems"],"best_for":["Healthcare operations leaders managing 100-500 clinical staff","Nursing directors needing shift-level visibility into team morale","HR teams in fast-paced environments where monthly cadence is too slow"],"limitations":["Real-time updates depend on source system API availability — if EHR or HRIS is offline, metrics lag","Dashboard refresh rate likely 5-15 minutes, not true sub-second updates, due to data aggregation overhead","Limited to metrics available from connected data sources; custom engagement signals require manual integration"],"requires":["Active integration with at least one HRIS or data source (manual export as fallback)","Sufficient data volume to compute meaningful aggregates (typically 50+ employees minimum)","Modern web browser with WebSocket support for real-time updates"],"input_types":["structured HR data (employee records, attendance, performance ratings)","survey responses (JSON or CSV)","time-series metrics from connected systems"],"output_types":["interactive dashboard visualizations (charts, heatmaps, trend lines)","metric snapshots (JSON API)","alert notifications (email, in-app)"],"categories":["data-processing-analysis","healthcare-analytics"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_thrivelink__cap_1","uri":"capability://data.processing.analysis.pulse.survey.orchestration.with.fatigue.minimization","name":"pulse survey orchestration with fatigue minimization","description":"Manages lightweight, frequent engagement surveys (pulse surveys) with intelligent scheduling and question selection to reduce survey fatigue. The system likely implements a question bank with metadata about survey frequency caps, employee response history, and optimal timing windows. Surveys are distributed via multiple channels (email, in-app, SMS) with response tracking to avoid over-surveying the same cohorts. The platform may use adaptive sampling to target specific teams or roles based on engagement trends rather than surveying the entire population each cycle.","intents":["I want to gather feedback from clinical staff weekly without overwhelming them with survey requests","I need to understand why engagement is dropping in a specific unit without running a full company survey","I want to measure the impact of interventions (e.g., schedule changes) with targeted pulse surveys"],"best_for":["Healthcare HR teams managing survey fatigue in high-stress environments","Organizations running continuous improvement cycles that need frequent feedback loops","Teams wanting to replace annual engagement surveys with ongoing pulse measurement"],"limitations":["Pulse surveys capture snapshots, not longitudinal trends — requires 4+ weeks of data to identify meaningful patterns","Response rates typically 20-40% for optional pulse surveys, introducing selection bias toward more engaged employees","No built-in statistical significance testing — small sample sizes in department-level surveys may produce unreliable insights"],"requires":["Employee email or mobile app access for survey distribution","Minimum 50 employees to generate meaningful cohort-level insights","Survey question library or ability to define custom questions"],"input_types":["survey question templates (text)","employee roster with contact info and attributes (CSV, JSON)","historical survey responses (for fatigue tracking)"],"output_types":["survey response data (JSON, CSV export)","aggregated sentiment scores by team/role","trend visualizations (response rate over time, score changes)"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_thrivelink__cap_10","uri":"capability://data.processing.analysis.manager.performance.on.engagement.and.retention.metrics","name":"manager performance on engagement and retention metrics","description":"Tracks manager-level metrics related to engagement and retention (e.g., team engagement scores, turnover rate, action completion rate) to measure manager effectiveness and accountability. The system likely aggregates team-level engagement metrics by manager, tracks manager actions taken in response to alerts, and correlates manager interventions with engagement outcomes. Manager scorecards may show engagement trends for their teams, action completion rates, and retention metrics. This enables HR to identify high-performing managers (whose teams have high engagement and low turnover) and provide coaching to struggling managers.","intents":["I want to measure which managers are most effective at keeping their teams engaged and reducing turnover","I need to track whether managers are actually taking actions on engagement alerts","I want to identify best-practice managers whose teams have high engagement so I can share their approaches"],"best_for":["Healthcare organizations with manager accountability for engagement and retention","HR leaders evaluating manager performance and providing coaching","Organizations using engagement as a key manager KPI"],"limitations":["Manager metrics are confounded by team composition, staffing levels, and unit acuity — a manager of a high-acuity ICU may have lower engagement scores despite excellent management","Correlation between manager actions and engagement outcomes is not causal — other factors (staffing, policy changes) may drive engagement changes","No statistical controls for confounding variables mentioned — may unfairly penalize managers of difficult units","Manager action tracking relies on self-reporting — managers may not log all actions taken","Turnover metrics require 6-12 months of data to be meaningful — not useful for new managers or rapid assessment"],"requires":["Clear manager-to-employee reporting structure in HRIS","Manager action tracking system (alerts, interventions logged)","Historical turnover and engagement data by manager (minimum 6 months)"],"input_types":["team-level engagement metrics (aggregated from employees reporting to each manager)","manager action logs (alerts acknowledged, interventions taken)","turnover data (departures by manager)","manager tenure and team size"],"output_types":["manager engagement scorecards (team engagement score, trend, action completion rate)","manager rankings (top/bottom performers on engagement and retention)","manager coaching recommendations (areas for improvement)","correlation analysis (manager actions vs. engagement outcomes)"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_thrivelink__cap_2","uri":"capability://data.processing.analysis.burnout.and.retention.risk.scoring.with.clinical.context","name":"burnout and retention risk scoring with clinical context","description":"Computes risk scores for individual employees or teams based on engagement data, attendance patterns, and clinical-specific indicators (e.g., consecutive shift length, overtime frequency, role-based stress factors). The scoring model likely uses a weighted combination of signals (survey sentiment, absenteeism, performance changes, tenure) with healthcare-specific calibration. Scores are updated incrementally as new data arrives and surfaced with contextual explanations (e.g., 'high overtime in past 4 weeks' or 'declining engagement score trend'). The system may flag high-risk individuals for manager intervention or HR outreach.","intents":["I need to identify which nurses are at highest risk of leaving before they resign","I want to understand what's driving burnout in my ICU team so I can address root causes","I need to prioritize retention interventions for the employees most likely to leave"],"best_for":["Healthcare HR leaders focused on clinical staff retention","Nursing directors managing burnout in high-acuity units","Organizations with high turnover seeking data-driven retention strategies"],"limitations":["Risk scores are correlational, not causal — high score doesn't guarantee departure, and interventions may not prevent turnover","Model accuracy depends on historical data quality; organizations with incomplete attendance or performance records will have unreliable scores","No predictive analytics for turnover forecasting mentioned in product description — scores are current-state risk, not forward-looking predictions","Risk scores may exhibit bias if training data reflects historical hiring/retention patterns that disadvantage certain demographics"],"requires":["At least 6 months of historical engagement and attendance data","Structured employee data including role, tenure, department, shift type","Baseline engagement survey responses or performance ratings"],"input_types":["employee engagement scores (numeric)","attendance/absence records (dates, duration)","performance ratings or manager feedback (numeric or text)","survey responses (sentiment, specific burnout questions)"],"output_types":["risk scores per employee (0-100 scale or similar)","risk category labels (low, medium, high)","contributing factor explanations (text)","cohort-level risk aggregates (team, department, role)"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_thrivelink__cap_3","uri":"capability://tool.use.integration.engagement.data.integration.with.manual.export.fallback","name":"engagement data integration with manual export fallback","description":"Connects to employee data sources (HRIS, EHR, attendance systems) via APIs or scheduled data imports to populate engagement dashboards and risk models. The system supports both real-time API integrations (for systems with available connectors) and batch imports (CSV, Excel) for systems without native connectors. Data mapping and transformation logic handles schema differences between source systems. A fallback mechanism allows manual CSV export/import when API connectivity is unavailable, ensuring data freshness is not blocked by integration failures.","intents":["I want to pull employee data from our HRIS without manual exports every week","Our EHR doesn't have a public API, but I need to import shift and staffing data somehow","I need to combine data from multiple systems (HRIS, payroll, EHR) into one engagement view"],"best_for":["Healthcare IT teams managing data pipelines across multiple legacy systems","Mid-sized health systems without dedicated data engineering resources","Organizations with fragmented HR tech stacks seeking a unified engagement view"],"limitations":["Limited integration ecosystem — product description notes lack of native Epic or Cerner connectors, requiring manual data exports","Manual CSV imports are error-prone and don't scale; requires ongoing operational overhead","Data freshness depends on import frequency — batch imports may lag real-time by hours or days","No ETL validation or data quality checks mentioned; garbage-in-garbage-out risk if source data is incomplete or malformed","Schema mapping is likely manual configuration, not automatic — requires technical setup for each new data source"],"requires":["API credentials or database access for connected systems (if available)","CSV/Excel export capability from source systems (minimum fallback requirement)","Data mapping documentation or technical support to configure field matching","Scheduled job runner or manual process for batch imports if using CSV fallback"],"input_types":["REST API responses (JSON) from HRIS or connected systems","CSV/Excel files with employee data (columns: employee ID, name, department, role, hire date, etc.)","structured data exports from EHR or payroll systems"],"output_types":["normalized employee records in ThriveLink data model","integration status and error logs","data freshness timestamps"],"categories":["tool-use-integration","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_thrivelink__cap_4","uri":"capability://automation.workflow.workflow.integrated.feedback.and.action.tracking","name":"workflow-integrated feedback and action tracking","description":"Embeds engagement feedback collection and action tracking directly into existing employee workflows (e.g., after shift handoff, during performance reviews, in manager dashboards) rather than requiring separate survey tools. The system likely uses webhooks or embedded widgets to surface surveys and feedback prompts at contextually relevant moments. Manager dashboards show flagged employees and recommended actions (e.g., 'schedule 1-on-1 with high-risk employee'). Action tracking logs manager responses and follow-ups, creating an audit trail of engagement interventions.","intents":["I want to collect feedback from nurses at the point of care, not via email surveys they ignore","I need my managers to see engagement alerts in their daily workflow and track what actions they've taken","I want to measure whether manager interventions actually improve engagement for at-risk employees"],"best_for":["Healthcare organizations with mobile-first or shift-based workflows","Managers who need engagement insights integrated into existing tools rather than new dashboards","Teams measuring the effectiveness of retention interventions"],"limitations":["Workflow integration requires custom development or pre-built connectors to specific systems (EHR, HRIS, scheduling tools) — not all systems are supported","Embedded feedback collection may have lower response rates than dedicated survey tools if poorly integrated","Action tracking relies on manager compliance — no enforcement mechanism if managers don't log interventions","Context-aware survey timing requires access to real-time workflow events, which may not be available from legacy systems"],"requires":["Access to workflow systems where feedback will be embedded (EHR, manager portal, mobile app)","API or webhook support from those systems for embedding widgets or triggering notifications","Manager adoption and training on using action tracking features"],"input_types":["workflow events (shift start/end, performance review completion, etc.)","manager actions and notes (text, timestamps)","contextual employee data (current role, tenure, recent performance)"],"output_types":["embedded survey prompts and feedback forms","manager action recommendations (text)","action logs with timestamps and outcomes","intervention effectiveness metrics (engagement change post-action)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_thrivelink__cap_5","uri":"capability://data.processing.analysis.role.based.and.shift.aware.engagement.segmentation","name":"role-based and shift-aware engagement segmentation","description":"Segments employees and engagement metrics by clinical role (nurse, physician, technician, administrative) and shift type (day, night, rotating) to surface role-specific insights and trends. The system likely maintains a role taxonomy and shift classification schema, then groups all metrics (engagement scores, survey responses, risk scores) by these dimensions. Dashboards and reports can be filtered by role or shift to show that 'night shift nurses have 15% lower engagement than day shift' or 'ICU staff have higher burnout indicators than med-surg.' This enables targeted interventions rather than one-size-fits-all engagement strategies.","intents":["I need to understand if engagement problems are specific to night shift staff or organization-wide","I want to compare engagement across clinical roles to identify which groups need the most support","I need to tailor retention strategies for nurses vs. physicians vs. administrative staff based on their specific drivers"],"best_for":["Healthcare organizations with diverse clinical and non-clinical staff","Nursing leaders managing multiple shifts and units","HR teams designing role-specific engagement and retention programs"],"limitations":["Segmentation accuracy depends on accurate role and shift data in source systems — misclassified employees skew segment metrics","Small segment sizes (e.g., 5 night shift ICU nurses) produce unreliable metrics due to low sample size","No cross-segment comparison statistics (e.g., statistical significance testing) mentioned — may lead to false conclusions about role differences","Requires manual configuration of role taxonomy and shift definitions; not automatically inferred from data"],"requires":["Structured employee data with role and shift type fields","Minimum 10-20 employees per segment to generate meaningful metrics","Role taxonomy or classification scheme defined in the system"],"input_types":["employee role classification (nurse, physician, technician, etc.)","shift assignment data (day, night, rotating, on-call)","engagement metrics and survey responses"],"output_types":["segmented dashboards (metrics filtered by role/shift)","comparative reports (engagement by role, shift, unit)","segment-specific risk scores and recommendations"],"categories":["data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_thrivelink__cap_6","uri":"capability://planning.reasoning.manager.alert.and.intervention.recommendation.system","name":"manager alert and intervention recommendation system","description":"Identifies high-risk employees or teams and sends alerts to managers with recommended interventions (e.g., 'Schedule 1-on-1 with Sarah (nurse, ICU) — engagement down 20% in past 2 weeks, overtime 15+ hours'). The system likely uses rule-based logic or simple ML models to flag employees exceeding risk thresholds, then generates contextual recommendations based on the risk drivers. Alerts are delivered via email, in-app notifications, or manager dashboards. The system tracks whether managers acknowledge alerts and take actions, creating accountability for engagement management.","intents":["I want my managers to be proactively notified when an employee is at risk of leaving","I need to give managers specific, actionable recommendations on how to support at-risk employees","I want to track whether managers are actually following up on engagement alerts"],"best_for":["Healthcare organizations with distributed management (multiple unit managers)","Nursing leaders seeking to embed engagement ownership into manager responsibilities","Teams measuring manager effectiveness on retention and engagement"],"limitations":["Alert fatigue risk — if thresholds are too sensitive, managers may ignore alerts or disable notifications","Recommendations are generic templates, not personalized to individual circumstances — manager judgment still required","No enforcement mechanism if managers ignore alerts or don't take recommended actions","Alert accuracy depends on underlying risk model quality — false positives waste manager time, false negatives miss real risks"],"requires":["Manager email or app access for receiving alerts","Risk scoring model configured with appropriate thresholds","Manager training on how to interpret alerts and take recommended actions"],"input_types":["employee risk scores and risk drivers (from risk scoring capability)","manager contact information and preferences","historical manager actions and outcomes (for learning)"],"output_types":["alert notifications (email, in-app, SMS)","recommended action templates (text)","alert acknowledgment and action tracking logs"],"categories":["planning-reasoning","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_thrivelink__cap_7","uri":"capability://data.processing.analysis.engagement.trend.analysis.and.anomaly.detection","name":"engagement trend analysis and anomaly detection","description":"Tracks engagement metrics over time and identifies significant changes or anomalies (e.g., 'engagement dropped 25% in the ICU this week' or 'night shift survey response rate is 3x higher than usual'). The system likely uses time-series analysis to compute baselines and detect deviations, flagging unusual patterns for investigation. Trend visualizations show engagement trajectories by team, role, or unit. Anomalies may trigger alerts to managers or HR teams. The system may correlate anomalies with known events (e.g., staffing changes, policy updates) to help explain trends.","intents":["I want to know if engagement is improving or declining over time, not just current snapshots","I need to detect sudden engagement drops (e.g., after a staffing change) so I can investigate and respond quickly","I want to understand what events or changes correlate with engagement shifts"],"best_for":["Healthcare leaders tracking engagement trends over quarters or years","Teams investigating root causes of engagement changes","Organizations running continuous improvement cycles that need to measure impact"],"limitations":["Trend analysis requires historical data — minimum 3-6 months of baseline data needed to establish meaningful trends","Anomaly detection may produce false positives if baselines are not adjusted for seasonal patterns (e.g., summer staffing changes, holiday periods)","Correlation with events is manual — system doesn't automatically infer causation, requires human interpretation","Small sample sizes in early periods may produce unstable baselines and unreliable anomaly detection"],"requires":["At least 3-6 months of historical engagement data","Consistent data collection methodology (same surveys, metrics) over time","Event log or annotations of known organizational changes (staffing, policy, etc.)"],"input_types":["time-series engagement metrics (daily, weekly, or monthly aggregates)","event annotations (staffing changes, policy updates, etc.)","historical survey responses and scores"],"output_types":["trend visualizations (line charts, heatmaps over time)","anomaly alerts (significant deviations from baseline)","trend summaries (engagement improving/declining, rate of change)","correlation analysis (events vs. engagement changes)"],"categories":["data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_thrivelink__cap_8","uri":"capability://data.processing.analysis.engagement.survey.response.analytics.and.sentiment.extraction","name":"engagement survey response analytics and sentiment extraction","description":"Analyzes survey responses to extract sentiment, themes, and actionable insights from free-text feedback. The system likely uses natural language processing (NLP) to classify sentiment (positive, neutral, negative), extract key topics (workload, scheduling, management, compensation), and identify recurring themes across responses. Aggregated sentiment scores are computed by team, role, or survey question. The system may surface representative quotes or themes to managers (e.g., 'Top concern: scheduling inflexibility mentioned in 40% of night shift responses'). Structured data (Likert scale responses) is aggregated into summary statistics.","intents":["I want to understand not just engagement scores, but why employees feel the way they do","I need to identify the top concerns or pain points from survey feedback without reading hundreds of responses","I want to see if sentiment is improving after we implement changes (e.g., new scheduling policy)"],"best_for":["HR teams analyzing pulse survey feedback at scale","Managers seeking to understand employee concerns without manual review","Organizations running intervention pilots and measuring sentiment impact"],"limitations":["NLP sentiment analysis is imperfect — sarcasm, context-dependent language, and clinical jargon may be misclassified","Topic extraction is unsupervised and may identify spurious or overlapping themes","Free-text responses have lower response rates than structured questions — sentiment analysis may be biased toward more engaged respondents","No multi-language support mentioned — limits applicability in diverse healthcare settings","Sentiment scores are relative, not absolute — 'positive' sentiment in healthcare may still reflect high stress compared to other industries"],"requires":["Survey responses with free-text fields (minimum 50-100 responses for meaningful theme extraction)","Structured survey data (Likert scales, multiple choice) for aggregation","Language: English (likely only, based on product description)"],"input_types":["free-text survey responses (open-ended questions)","structured survey responses (Likert scales, multiple choice)","survey metadata (respondent role, shift, department)"],"output_types":["sentiment scores (positive/neutral/negative, 0-100 scale)","theme/topic tags (workload, scheduling, management, etc.)","representative quotes or themes by segment","sentiment trend over time"],"categories":["data-processing-analysis","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_thrivelink__cap_9","uri":"capability://data.processing.analysis.department.and.unit.level.engagement.benchmarking","name":"department and unit-level engagement benchmarking","description":"Compares engagement metrics across departments, units, or teams to identify relative performance and highlight outliers. The system likely maintains a benchmark database of engagement scores by unit type (ICU, med-surg, emergency, administrative) and compares each unit's current metrics against internal benchmarks and potentially industry averages. Benchmarking reports show which units are above/below average and highlight units with declining trends. The system may flag units for targeted support or best-practice sharing (e.g., 'ICU A has 20% higher engagement than ICU B — consider sharing their scheduling practices').","intents":["I want to know how my ICU's engagement compares to other ICUs in our health system","I need to identify which units are struggling so I can allocate resources and support","I want to share best practices from high-engagement units with struggling units"],"best_for":["Health system leaders managing multiple hospitals or units","Nursing directors comparing performance across similar units","Organizations seeking to identify and replicate engagement best practices"],"limitations":["Internal benchmarks are only meaningful with 3+ similar units — smaller organizations lack comparison groups","Industry benchmarks are not mentioned in product description — likely limited to internal comparisons only","Benchmarking can create unhealthy competition between units if not managed carefully","Unit-level metrics may be confounded by staffing levels, acuity, or other factors not accounted for in benchmarking","No statistical significance testing mentioned — differences may be due to random variation, not real performance gaps"],"requires":["Minimum 3-5 similar units (same type, size) for meaningful benchmarking","Consistent engagement data collection across all units","Unit classification or taxonomy (ICU, med-surg, emergency, etc.)"],"input_types":["unit-level engagement metrics (aggregated from employees in each unit)","unit metadata (type, size, staffing levels, acuity)","historical unit performance data"],"output_types":["benchmark comparison reports (unit vs. average, unit vs. peer units)","unit rankings (top/bottom performers)","outlier alerts (units significantly above/below average)","best-practice recommendations (practices from high-performing units)"],"categories":["data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":43,"verified":false,"data_access_risk":"high","permissions":["Active integration with at least one HRIS or data source (manual export as fallback)","Sufficient data volume to compute meaningful aggregates (typically 50+ employees minimum)","Modern web browser with WebSocket support for real-time updates","Employee email or mobile app access for survey distribution","Minimum 50 employees to generate meaningful cohort-level insights","Survey question library or ability to define custom questions","Clear manager-to-employee reporting structure in HRIS","Manager action tracking system (alerts, interventions logged)","Historical turnover and engagement data by manager (minimum 6 months)","At least 6 months of historical engagement and attendance data"],"failure_modes":["Real-time updates depend on source system API availability — if EHR or HRIS is offline, metrics lag","Dashboard refresh rate likely 5-15 minutes, not true sub-second updates, due to data aggregation overhead","Limited to metrics available from connected data sources; custom engagement signals require manual integration","Pulse surveys capture snapshots, not longitudinal trends — requires 4+ weeks of data to identify meaningful patterns","Response rates typically 20-40% for optional pulse surveys, introducing selection bias toward more engaged employees","No built-in statistical significance testing — small sample sizes in department-level surveys may produce unreliable insights","Manager metrics are confounded by team composition, staffing levels, and unit acuity — a manager of a high-acuity ICU may have lower engagement scores despite excellent management","Correlation between manager actions and engagement outcomes is not causal — other factors (staffing, policy changes) may drive engagement changes","No statistical controls for confounding variables mentioned — may unfairly penalize managers of difficult units","Manager action tracking relies on self-reporting — managers may not log all actions taken","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.36666666666666664,"quality":0.78,"ecosystem":0.15000000000000002,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.35,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:33.648Z","last_scraped_at":"2026-04-05T13:23:42.551Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=thrivelink","compare_url":"https://unfragile.ai/compare?artifact=thrivelink"}},"signature":"Yxba81sPquVowwHd4wSUZjijA7pH2ePj94ElR454yinKcxVbJUdOocJYmK9bggx8s3mViWeUwM5OWEBzsVFcCQ==","signedAt":"2026-06-21T10:42:45.235Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/thrivelink","artifact":"https://unfragile.ai/thrivelink","verify":"https://unfragile.ai/api/v1/verify?slug=thrivelink","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}