{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"hex","slug":"hex","name":"Hex","type":"product","url":"https://hex.tech","page_url":"https://unfragile.ai/hex","categories":["data-analysis"],"tags":[],"pricing":{"model":"free","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"hex__cap_0","uri":"capability://code.generation.editing.natural.language.to.sql.code.generation.with.semantic.model.awareness","name":"natural-language-to-sql code generation with semantic model awareness","description":"The Notebook Agent accepts natural language queries and generates executable SQL code by searching endorsed semantic models and table schemas in connected data warehouses. The agent serializes notebook context (available tables, previous queries, semantic definitions) and uses an LLM to synthesize SQL that references specific tables and metrics by name, then executes the generated code server-side on Hex infrastructure with configurable compute profiles (Small to 4XL CPU/GPU options).","intents":["I want to ask a question in plain English and get a SQL query that answers it without writing code myself","I need to explore a new dataset but don't know the table structure or metric definitions","I want the agent to reference our company's endorsed semantic model so queries use standardized definitions"],"best_for":["SQL-averse analysts and business users who want to query data without writing code","Data teams with dbt semantic layers who want agents to respect metric definitions","Organizations doing ad hoc exploration where time-to-insight matters more than query optimization"],"limitations":["Agent thinking time is 11-23 seconds per query (not real-time), making interactive exploration slower than direct SQL","LLM context window limits how much notebook history and schema information can be sent; very large schemas may not fit","Agent cannot optimize for cost or performance — generated queries may be inefficient compared to hand-written SQL","Semantic model integration requires dbt setup; without it, agent only sees raw table schemas"],"requires":["Professional tier or higher ($36/month) for full Notebook Agent access; Community tier has limited trial","Connected data warehouse (Snowflake, Redshift, BigQuery, or S3)","Optional: dbt semantic layer configured for metric definitions"],"input_types":["natural language query string","notebook context (available tables, previous cell outputs, semantic model definitions)"],"output_types":["executable SQL code in a new cell","query results as tabular data","suggested follow-up analyses"],"categories":["code-generation-editing","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_1","uri":"capability://code.generation.editing.natural.language.to.python.code.generation.with.notebook.context","name":"natural-language-to-python code generation with notebook context","description":"The Notebook Agent generates executable Python code from natural language requests by analyzing the current notebook state (previous cell outputs, imported libraries, variable definitions) and synthesizing code that integrates with existing analysis. Generated code executes server-side on Hex compute infrastructure, with access to standard Python libraries and the ability to reference upstream cell outputs as DataFrames or other objects.","intents":["I want to ask the agent to write Python code for statistical analysis, transformation, or visualization without writing it myself","I need to build on previous analysis — the agent should understand what variables and DataFrames are already available","I want to generate exploratory code quickly to test hypotheses without context-switching to a local IDE"],"best_for":["Data scientists and analysts who know Python but want to accelerate exploratory coding","Teams mixing SQL and Python analysis in the same notebook who want agents to understand both contexts","Organizations where time-to-prototype matters more than production-grade code quality"],"limitations":["Agent cannot install arbitrary packages — limited to pre-installed libraries (exact list not disclosed)","Generated code may not follow production standards (error handling, type hints, documentation) and requires manual review","Agent thinking time is 11-23 seconds, making iterative refinement slower than local development","No access to local files or custom modules; code must be self-contained or reference upstream cell outputs"],"requires":["Professional tier or higher ($36/month) for full Notebook Agent access","Python cell type in notebook","Understanding of what libraries are available (documentation incomplete)"],"input_types":["natural language request","notebook context (previous cell outputs, variable definitions, imported libraries)"],"output_types":["executable Python code in a new cell","code execution results (printed output, DataFrames, plots)","generated visualizations"],"categories":["code-generation-editing","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_10","uri":"capability://search.retrieval.visual.data.exploration.with.drill.down.in.published.apps","name":"visual data exploration with drill-down in published apps","description":"Published apps (Team+ feature) support visual data exploration where users can drill down into underlying data by clicking on chart elements or table rows. The system automatically generates drill-down queries based on the selected data point, enabling users to explore data hierarchies without manual query writing. Drill-down is only available in published apps, not in edit mode.","intents":["I want business users to click on a chart bar and see the underlying transactions that make up that bar","I need to enable data exploration without requiring users to write SQL or modify the notebook","I want to create self-service analytics where users can drill down to detail without analyst intervention"],"best_for":["Organizations building self-service analytics for non-technical users","Teams creating dashboards where drill-down exploration is critical","Companies reducing analyst workload by enabling self-service data exploration"],"limitations":["Drill-down only available on Team+ tier ($75/month), not Professional or free","Only available in published apps, not in notebook edit mode","Drill-down query generation mechanism not documented — unclear how it determines which fields to drill on","No mention of drill-down depth limits or performance implications for large datasets"],"requires":["Team+ tier ($75/month) or higher","Published app with charts or tables","Underlying data with hierarchical structure"],"input_types":["user clicks on chart elements or table rows","selected data points"],"output_types":["drill-down query results","detailed data view","navigation back to parent level"],"categories":["search-retrieval","image-visual"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_11","uri":"capability://automation.workflow.configurable.compute.profiles.with.pay.as.you.go.scaling","name":"configurable compute profiles with pay-as-you-go scaling","description":"Hex offers six compute tiers (Small: 2GB RAM/0.25 CPU through 4XL: 96GB RAM/24 CPU) plus optional GPU acceleration. Free tier limited to Small compute; Medium compute (8GB RAM/1 CPU) included on all paid plans; Large+ tiers incur per-minute charges ($0.32-$2.58/hr for CPU, $2.93-$4.06/hr for GPU). Users select compute profile per notebook, and costs are billed per-minute of execution time beyond included allowances.","intents":["I want to run small exploratory queries on free tier without paying for compute","I need to scale to larger compute for data science workloads without changing my plan","I want to use GPU acceleration for machine learning without committing to a fixed monthly cost"],"best_for":["Organizations with variable compute needs (exploratory analysis + occasional large jobs)","Teams doing data science where GPU acceleration is occasionally needed","Companies wanting to avoid fixed compute costs for unpredictable workloads"],"limitations":["Free tier limited to Small compute (2GB RAM, 0.25 CPU), making large data transformations slow or impossible","Pay-as-you-go pricing for Large+ tiers can be expensive for frequent large jobs ($0.32-$2.58/hr = $7.68-$61.92/day if running 24/7)","No reserved capacity or commitment discounts mentioned — all compute billed at per-minute rates","GPU compute expensive ($2.93-$4.06/hr = $70-97/day if running 24/7), making long-running ML jobs costly"],"requires":["Any Hex plan (free tier included with Small compute only)","Professional tier ($36/month) or higher for Medium compute included","Willingness to pay per-minute for Large+ or GPU compute"],"input_types":["compute profile selection (Small through 4XL, optional GPU)","notebook execution"],"output_types":["notebook execution on selected compute tier","usage charges for Large+ or GPU compute","execution time and resource utilization metrics"],"categories":["automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_12","uri":"capability://automation.workflow.git.based.project.export.and.package.import.for.code.reuse","name":"git-based project export and package import for code reuse","description":"Team+ tier enables exporting notebooks as Git projects and importing packages (shared components, templates) from other notebooks. This allows teams to version control notebooks in Git, share reusable components across projects, and maintain a library of analysis templates. Export format and Git integration details not fully documented.","intents":["I want to version control my notebooks in Git alongside my codebase","I need to share reusable analysis components across multiple notebooks without duplicating code","I want to maintain a library of analysis templates that teams can import and customize"],"best_for":["Organizations with mature Git workflows who want to include notebooks in version control","Data teams building reusable analysis libraries","Companies standardizing analysis patterns across teams"],"limitations":["Git export and package import only available on Team+ tier ($75/month), not Professional or free","Export format and Git integration details not documented — unclear how notebooks map to Git files","No mention of merge conflict resolution or Git workflow best practices","Package import mechanism not documented — unclear how dependencies are resolved"],"requires":["Team+ tier ($75/month) or higher","Git repository for project export","Understanding of Git workflows"],"input_types":["notebook projects","shared components and templates"],"output_types":["Git-compatible project files","imported packages and components","version-controlled notebook history"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_13","uri":"capability://safety.moderation.enterprise.authentication.and.compliance.with.oidc.sso.and.audit.logs","name":"enterprise authentication and compliance with oidc sso and audit logs","description":"Enterprise plan includes OIDC single sign-on (SSO) for centralized authentication, OAuth database connections for warehouse access, audit logs for compliance tracking, and HIPAA compliance certification. These features enable organizations to enforce authentication policies, track user actions, and meet regulatory requirements without managing credentials in Hex.","intents":["I want to enforce single sign-on so users authenticate through our corporate identity provider","I need audit logs to track who accessed and modified notebooks for compliance","I want to meet HIPAA requirements for healthcare data analysis"],"best_for":["Enterprise organizations with centralized identity management","Companies in regulated industries (healthcare, finance) requiring audit trails","Organizations with strict authentication and compliance requirements"],"limitations":["OIDC SSO and audit logs only available on Enterprise plan (custom pricing), not Professional or Team","HIPAA compliance requires Enterprise plan; no mention of other compliance certifications (SOC 2, FedRAMP, etc.)","OAuth database connections only on Enterprise; lower tiers use basic authentication","Audit log retention and export details not documented"],"requires":["Enterprise plan (custom pricing)","OIDC identity provider (Okta, Azure AD, etc.) for SSO","Compliance requirements justifying Enterprise cost"],"input_types":["OIDC provider configuration","OAuth database connection credentials","audit log queries"],"output_types":["centralized authentication via SSO","audit logs of user actions","compliance reports"],"categories":["safety-moderation","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_14","uri":"capability://tool.use.integration.embedded.analytics.and.custom.docker.images.for.enterprise.deployments","name":"embedded analytics and custom docker images for enterprise deployments","description":"Enterprise plan enables embedding Hex apps in external websites (embedded analytics) and deploying custom Docker images with pre-installed packages or custom runtime environments. Single-tenant deployment option available for organizations requiring isolated infrastructure.","intents":["I want to embed interactive dashboards in our customer-facing website without building a separate analytics platform","I need to deploy Hex with custom Python packages or runtime configurations","I require isolated infrastructure for data sovereignty or compliance"],"best_for":["SaaS companies building embedded analytics for customers","Organizations with custom runtime requirements (specific Python versions, packages)","Enterprises requiring single-tenant deployment for data sovereignty"],"limitations":["Embedded analytics and custom Docker images only available on Enterprise plan (custom pricing)","Single-tenant deployment likely has significant cost and operational overhead","Custom Docker image support details not documented — unclear what customization is allowed","Embedded analytics security model not documented — unclear how authentication and data access are controlled"],"requires":["Enterprise plan (custom pricing)","Docker knowledge for custom image deployment","Understanding of embedded analytics security requirements"],"input_types":["Hex apps for embedding","custom Docker image specifications"],"output_types":["embedded app iframes for external websites","custom runtime environment with pre-installed packages","isolated single-tenant infrastructure"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_15","uri":"capability://automation.workflow.single.tenant.enterprise.deployment.with.hipaa.compliance.and.custom.branding","name":"single-tenant enterprise deployment with hipaa compliance and custom branding","description":"Enterprise plan option for deploying Hex in a single-tenant environment with HIPAA compliance, custom branding (white-label), and dedicated support. Enables embedding Hex analytics in customer-facing applications without Hex branding. Requires custom contract and pricing.","intents":["I want to embed Hex analytics in my SaaS product without showing Hex branding","I need HIPAA-compliant deployment for healthcare data","I want a dedicated Hex instance for my organization with custom support"],"best_for":["SaaS companies embedding analytics in customer-facing products","healthcare organizations requiring HIPAA compliance","enterprises with strict data residency or isolation requirements"],"limitations":["Enterprise plan only; custom pricing (estimated $5k-20k+/month based on feature set)","Requires custom contract and sales engagement; no self-serve option","Single-tenant deployment adds operational overhead; unclear if Hex manages infrastructure or customer does","Custom branding scope is unclear; unclear what elements can be customized (logos, colors, domain, etc.)","HIPAA compliance scope is unclear; unclear if Hex provides BAA or if customer is responsible for compliance"],"requires":["Enterprise plan (custom pricing, contact sales)","HIPAA compliance requirements (for healthcare deployments)","Custom branding requirements (logos, colors, domain)"],"input_types":["Custom branding assets (logos, color schemes, domain)","HIPAA compliance requirements and documentation"],"output_types":["Single-tenant Hex instance","White-labeled analytics interface","HIPAA-compliant audit logs and data handling"],"categories":["automation-workflow","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_2","uri":"capability://automation.workflow.reactive.multi.language.cell.execution.with.dependency.tracking","name":"reactive multi-language cell execution with dependency tracking","description":"Hex notebooks use a reactive execution model where cells (SQL, Python, or no-code) automatically re-execute when their dependencies change, rather than executing sequentially top-to-bottom like Jupyter. The system tracks data flow between cells and intelligently re-runs only affected downstream cells when an upstream cell is modified, enabling fast iteration without manual re-execution. Execution happens server-side on configurable compute profiles (Small: 2GB RAM / 0.25 CPU through 4XL: 96GB RAM / 24 CPU, with optional GPU).","intents":["I want to modify a SQL query and see downstream visualizations update automatically without manually re-running cells","I need to understand which cells depend on each other so I can safely edit without breaking downstream analysis","I want to iterate quickly on parameters and see results propagate through the notebook without manual orchestration"],"best_for":["Analysts doing exploratory analysis who need fast feedback loops","Teams collaborating on shared notebooks where manual re-execution coordination is error-prone","Organizations building interactive dashboards where parameter changes should trigger automatic updates"],"limitations":["Reactive execution adds complexity to debugging — it may not be obvious which cell triggered a re-execution","Large notebooks with many interdependent cells may experience cascading re-executions that slow iteration","No explicit cell ordering control — users must understand implicit dependencies rather than explicit sequence","Free tier limited to Small compute (2GB RAM, 0.25 CPU), making large data transformations slow or impossible"],"requires":["Any Hex plan (free tier included)","Connected data source for SQL cells","Understanding of data dependencies between cells"],"input_types":["SQL code in SQL cells","Python code in Python cells","no-code cell configurations (charts, pivot tables, input controls)"],"output_types":["query results","code execution results","rendered visualizations","updated downstream cells"],"categories":["automation-workflow","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_3","uri":"capability://image.visual.automatic.chart.generation.and.visualization.from.query.results","name":"automatic chart generation and visualization from query results","description":"When a SQL or Python cell produces tabular results, Hex automatically generates visualizations (bar, line, pie, scatter charts inferred from data types and cardinality) without requiring explicit chart configuration. Users can customize chart type, axes, colors, and aggregations through a visual editor. The system also supports pivot tables, summary statistics, and drill-down exploration in published apps, with all visualizations rendered client-side for fast interaction.","intents":["I want to see my query results as a chart immediately without manually configuring axes and chart type","I need to switch between different chart types (bar, line, pie) to find the best visualization for my data","I want to create a dashboard with multiple charts without writing visualization code"],"best_for":["Analysts and business users who want fast visualization without learning charting libraries","Teams building dashboards where time-to-publication matters more than custom styling","Organizations where non-technical users need to explore data visually without coding"],"limitations":["Chart customization is limited to built-in types and styling options; custom visualizations or D3.js-style control not available","Auto-generated chart type selection may not match user intent (e.g., choosing pie chart for high-cardinality data)","No support for advanced visualizations (maps, 3D charts, network diagrams) mentioned in documentation","Drill-down exploration only available in published apps, not in edit mode"],"requires":["Any Hex plan (free tier included)","Query or code that produces tabular results (DataFrame, SQL result set)"],"input_types":["tabular data (SQL results, Python DataFrames)","chart configuration (type, axes, colors, aggregations)"],"output_types":["rendered interactive charts","pivot tables","summary statistics","drill-down data exploration (in published apps)"],"categories":["image-visual","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_4","uri":"capability://automation.workflow.drag.and.drop.interactive.app.builder.for.dashboards.and.reports","name":"drag-and-drop interactive app builder for dashboards and reports","description":"Hex provides a no-code app builder that allows users to drag components (charts, tables, input controls, text) onto a canvas to create interactive dashboards without writing HTML/CSS/JavaScript. Apps support parameterization through input controls (dropdowns, date pickers, text inputs) that filter underlying queries, and can be published with permission controls (view-only or edit-restricted). Published apps render in a browser and support drill-down data exploration (Team+ feature) and email/Slack alerts (Team+ feature).","intents":["I want to create a dashboard by dragging charts and tables onto a canvas without writing code","I need to add filters and parameters so business users can explore data without editing the notebook","I want to publish a polished report that non-technical stakeholders can view and interact with"],"best_for":["Business analysts and non-technical users building dashboards","Data teams creating self-service analytics for stakeholders","Organizations where dashboard creation speed matters more than custom styling"],"limitations":["Free tier limited to 5 published apps; Professional tier allows up to 5; Team+ tier allows unlimited","Custom styling and branding options not mentioned — apps may look generic","No embedded analytics (embedding apps in external websites) except on Enterprise plan","Drill-down exploration only available on Team+ tier, limiting data exploration in lower-tier published apps"],"requires":["Professional tier ($36/month) or higher to publish apps","Underlying SQL/Python cells that produce data for app components"],"input_types":["charts, tables, and visualizations from notebook cells","input control configurations (dropdowns, date pickers, text inputs)","text and layout components"],"output_types":["interactive published dashboard/app","parameterized query results based on user input","drill-down data exploration (Team+ only)","email/Slack alerts (Team+ only)"],"categories":["automation-workflow","image-visual"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_5","uri":"capability://automation.workflow.scheduled.notebook.execution.with.email.and.slack.notifications","name":"scheduled notebook execution with email and slack notifications","description":"Team+ tier enables scheduling notebooks to run on a recurring basis (daily, weekly, monthly, or custom cron schedules) and send results via email or Slack. When a notebook runs on schedule, all cells execute in dependency order, and results can be formatted as email summaries or Slack messages. Scheduled runs use the same compute infrastructure as manual execution, with costs billed per-minute for compute usage beyond the included Medium tier.","intents":["I want to run a report every morning and email results to stakeholders automatically","I need to send daily metrics to a Slack channel without manually running the notebook","I want to schedule data refreshes so dashboards always show current data"],"best_for":["Data teams automating report generation and distribution","Organizations with recurring analysis needs (daily dashboards, weekly reports)","Teams replacing manual reporting workflows with automated notebook execution"],"limitations":["Scheduling only available on Team+ tier ($75/month), not Professional or free","No conditional execution (e.g., run only if data changed) — notebooks execute on fixed schedule","Email/Slack formatting is basic (text + links); no rich HTML formatting or embedded charts mentioned","Compute costs apply to scheduled runs beyond included Medium tier, making large daily jobs expensive"],"requires":["Team+ tier ($75/month) or higher","Slack or email integration configured","Notebook with cells that produce reportable output"],"input_types":["notebook cells (SQL, Python, visualizations)","schedule configuration (frequency, time, timezone)","email/Slack recipient configuration"],"output_types":["scheduled notebook execution","email summaries with results","Slack messages with metrics and links","compute usage charges (if exceeding included Medium tier)"],"categories":["automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_6","uri":"capability://automation.workflow.real.time.collaborative.editing.with.version.history.and.comments","name":"real-time collaborative editing with version history and comments","description":"Hex notebooks support multiplayer real-time editing where multiple users can edit cells simultaneously (conflict resolution mechanism not specified). Comments can be attached to individual cells or published app outputs, creating separate discussion threads. Version history is retained for 7 days (free), 30 days (Professional), or unlimited (Team+), allowing users to revert to previous notebook states. Shared components and collections (Team+ feature) enable code reuse across notebooks.","intents":["I want to collaborate with teammates on the same notebook without overwriting each other's work","I need to leave comments on specific cells to discuss analysis approach or results","I want to revert to a previous version of the notebook if something breaks"],"best_for":["Data teams collaborating on shared analyses","Organizations where multiple analysts work on the same project","Teams using notebooks as living documentation that evolves over time"],"limitations":["Real-time multiplayer conflict resolution mechanism not documented — unclear how simultaneous edits to the same cell are handled","Comments are separate from code (cell comments vs. app output comments), potentially fragmenting discussion","Version history limited to 7 days on free tier, making long-term audit trails unavailable for non-paying users","Shared components and collections only available on Team+ tier, limiting code reuse on lower tiers"],"requires":["Any Hex plan (free tier included for basic collaboration)","Team+ tier ($75/month) for shared components and unlimited version history","Shared notebook link or explicit permission grant"],"input_types":["notebook edits (cell code, configurations)","comments on cells or published outputs","version history queries"],"output_types":["real-time synchronized notebook state","comment threads","version history with revert capability","shared component library (Team+ only)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_7","uri":"capability://memory.knowledge.semantic.model.integration.with.dbt.metrics.and.standardized.definitions","name":"semantic model integration with dbt metrics and standardized definitions","description":"Hex integrates with dbt semantic models, allowing notebooks to reference endorsed metrics and standardized table definitions. The Semantic Model Agent (Team+ feature) can answer questions about metrics and generate queries that use pre-calculated metrics rather than raw tables. SQL cells can reference semantic model metrics directly, and the agent is aware of metric definitions when generating code, ensuring queries use business logic rather than raw calculations.","intents":["I want to query metrics that are defined in our dbt semantic model without manually writing the calculation","I need the agent to understand our company's metric definitions so generated queries are consistent with business logic","I want to ensure all analyses use the same definition of 'revenue' or 'customer' across the organization"],"best_for":["Organizations with dbt semantic layers who want to enforce metric consistency","Data teams where metric definitions are critical to analysis accuracy","Companies building self-service analytics on top of standardized metrics"],"limitations":["Semantic Model Agent only available on Team+ tier ($75/month), not Professional or free","Requires dbt semantic layer to be configured and deployed; organizations without dbt cannot use this feature","Integration details not documented — unclear how Hex queries the semantic model or handles metric dependencies","No support for custom metric calculations beyond what dbt semantic layer provides"],"requires":["Team+ tier ($75/month) or higher","dbt semantic layer configured and deployed","dbt metrics defined in semantic model"],"input_types":["dbt semantic model definitions","natural language queries to Semantic Model Agent","SQL cells referencing semantic model metrics"],"output_types":["queries using pre-calculated metrics","metric definitions and documentation","consistent metric values across analyses"],"categories":["memory-knowledge","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_8","uri":"capability://data.processing.analysis.multi.warehouse.data.source.connectivity.with.query.pushdown","name":"multi-warehouse data source connectivity with query pushdown","description":"Hex supports connections to major cloud data warehouses (Snowflake, Redshift, BigQuery) and object storage (S3), with SQL queries executed server-side on the warehouse infrastructure rather than pulling data into Hex. The system supports parameterized queries where input controls (filters, date ranges) are passed to the warehouse, enabling efficient filtering at the source. Large datasets are handled through 'query mode' (details not specified) rather than loading entire tables into memory.","intents":["I want to query my Snowflake/Redshift/BigQuery data without moving it to Hex","I need to add filters to queries so users can explore data without loading the entire dataset","I want to work with datasets larger than available memory by pushing computation to the warehouse"],"best_for":["Organizations with existing cloud data warehouses who want to avoid data movement","Teams working with large datasets that exceed local memory","Companies with data governance requirements that prohibit moving data outside the warehouse"],"limitations":["Limited to Snowflake, Redshift, BigQuery, and S3; other data sources not mentioned","Query pushdown details not documented — unclear how complex transformations are handled","No support for real-time streaming data (Kafka, Kinesis) mentioned","Connection setup and authentication details not fully documented (OAuth mentioned for Enterprise only)"],"requires":["Any Hex plan (free tier included)","Active account and credentials for Snowflake, Redshift, BigQuery, or S3","Network access from Hex infrastructure to data warehouse"],"input_types":["warehouse connection credentials","SQL queries","parameterized filter values"],"output_types":["query results from warehouse","filtered datasets based on input parameters","support for datasets of any size (via query mode)"],"categories":["data-processing-analysis","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__cap_9","uri":"capability://text.generation.language.threads.agent.for.multi.turn.conversational.analysis","name":"threads agent for multi-turn conversational analysis","description":"The Threads Agent (Team+ feature) enables multi-turn conversations where users ask follow-up questions and the agent maintains context across the conversation. Unlike the Notebook Agent which generates code cells, the Threads Agent appears to provide conversational analysis and insights. The exact implementation (whether it generates cells, maintains separate conversation state, or uses RAG over notebook history) is not documented.","intents":["I want to have a conversation with an AI assistant about my data analysis without explicitly generating code","I need to ask follow-up questions and have the agent remember previous context in the conversation","I want insights and recommendations based on my data without manually writing queries"],"best_for":["Analysts who prefer conversational exploration over code generation","Teams wanting AI-assisted insights without explicit code cell creation","Organizations exploring data through dialogue rather than structured queries"],"limitations":["Threads Agent only available on Team+ tier ($75/month), not Professional or free","Implementation details not documented — unclear how it differs from Notebook Agent or what it generates","No information on conversation history retention or export","Unclear whether Threads Agent can modify notebook state or only provide insights"],"requires":["Team+ tier ($75/month) or higher","Notebook with data sources configured"],"input_types":["natural language questions","follow-up questions in conversation"],"output_types":["conversational responses","insights and recommendations","unknown: possibly generated code or visualizations"],"categories":["text-generation-language","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hex__headline","uri":"capability://data.processing.analysis.collaborative.data.analysis.platform.with.ai.assistance","name":"collaborative data analysis platform with ai assistance","description":"Hex is a collaborative data workspace that combines SQL, Python, and AI-powered analysis in shareable notebooks, enabling data teams to explore data, build visualizations, and create interactive dashboards.","intents":["best collaborative data analysis tool","data analysis platform for teams","AI-assisted data visualization software","SQL and Python data workspace","interactive dashboard creation tool"],"best_for":["data analysts","data scientists","business analysts"],"limitations":["may not support advanced machine learning","performance may degrade with large datasets"],"requires":["basic understanding of SQL and Python"],"input_types":["SQL queries","Python code","no-code inputs"],"output_types":["data visualizations","interactive dashboards"],"categories":["data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":54,"verified":false,"data_access_risk":"high","permissions":["Professional tier or higher ($36/month) for full Notebook Agent access; Community tier has limited trial","Connected data warehouse (Snowflake, Redshift, BigQuery, or S3)","Optional: dbt semantic layer configured for metric definitions","Professional tier or higher ($36/month) for full Notebook Agent access","Python cell type in notebook","Understanding of what libraries are available (documentation incomplete)","Team+ tier ($75/month) or higher","Published app with charts or tables","Underlying data with hierarchical structure","Any Hex plan (free tier included with Small compute only)"],"failure_modes":["Agent thinking time is 11-23 seconds per query (not real-time), making interactive exploration slower than direct SQL","LLM context window limits how much notebook history and schema information can be sent; very large schemas may not fit","Agent cannot optimize for cost or performance — generated queries may be inefficient compared to hand-written SQL","Semantic model integration requires dbt setup; without it, agent only sees raw table schemas","Agent cannot install arbitrary packages — limited to pre-installed libraries (exact list not disclosed)","Generated code may not follow production standards (error handling, type hints, documentation) and requires manual review","Agent thinking time is 11-23 seconds, making iterative refinement slower than local development","No access to local files or custom modules; code must be self-contained or reference upstream cell outputs","Drill-down only available on Team+ tier ($75/month), not Professional or free","Only available in published apps, not in notebook edit mode","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.7,"quality":0.9,"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":"2026-05-24T12:16:22.066Z","last_scraped_at":null,"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=hex","compare_url":"https://unfragile.ai/compare?artifact=hex"}},"signature":"zRmR4SOyDzlux6CWAf2wgkN5hi/Bb6LO7BVDczCFpL85M2AAGhCt46IhJBYr+NsmGkLLxMH1Mxd//8fYaAHkCg==","signedAt":"2026-06-21T00:40:24.033Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/hex","artifact":"https://unfragile.ai/hex","verify":"https://unfragile.ai/api/v1/verify?slug=hex","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"}}