{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"tool_nex","slug":"nex","name":"Nex","type":"product","url":"https://www.nexai.app","page_url":"https://unfragile.ai/nex","categories":["documentation"],"tags":[],"pricing":{"model":"paid","free":false,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"tool_nex__cap_0","uri":"capability://data.processing.analysis.multi.format.document.ingestion.and.parsing","name":"multi-format document ingestion and parsing","description":"Accepts documents in multiple formats (PDFs, images, potentially Word/Excel) and converts them into a unified internal representation for downstream processing. Uses format-specific parsers (likely PDF libraries for text extraction, OCR engines for image-based documents) that normalize content into a standardized token stream or document tree, enabling consistent analysis across heterogeneous input types without requiring users to pre-convert formats.","intents":["I need to upload a batch of mixed PDFs and scanned images without manually converting them first","I want to analyze contracts, financial reports, and handwritten notes in a single workflow","I need to extract structured data from documents regardless of whether they're born-digital or scanned"],"best_for":["legal teams processing discovery documents in mixed formats","financial analysts reviewing quarterly reports and earnings calls transcripts","business consultants aggregating client documentation across multiple sources"],"limitations":["OCR accuracy degrades on low-resolution scans or handwritten text with poor legibility","Large documents (>100 pages) may require pagination or chunking, affecting context window availability","Unsupported formats (e.g., proprietary CAD files, legacy binary formats) will fail silently or require manual conversion"],"requires":["Document file size under platform limits (likely 10-50MB per document)","Supported MIME types: application/pdf, image/jpeg, image/png, potentially application/vnd.openxmlformats-officedocument.wordprocessingml.document"],"input_types":["PDF (text-based and image-based)","JPEG/PNG images","potentially DOCX, XLSX"],"output_types":["normalized document representation (internal token stream or AST)","extracted text with layout metadata","structured metadata (page count, detected language, format confidence scores)"],"categories":["data-processing-analysis","document-intelligence"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_nex__cap_1","uri":"capability://memory.knowledge.ai.powered.semantic.document.question.answering","name":"ai-powered semantic document question-answering","description":"Implements a retrieval-augmented generation (RAG) pipeline where user questions are embedded into a vector space, matched against document chunks using semantic similarity, and then passed to an LLM with retrieved context to generate grounded answers. The system likely chunks documents into overlapping segments, embeds them during ingestion, stores embeddings in a vector database, and at query time retrieves top-k relevant chunks before feeding them to a language model with a prompt template that enforces citation or grounding in source material.","intents":["I want to ask natural language questions about a document without manually searching for relevant sections","I need answers that cite specific pages or sections where the information was found","I want to ask follow-up questions that maintain context across multiple documents in a conversation"],"best_for":["contract reviewers who need to quickly locate specific clauses or obligations across 50+ page agreements","financial analysts extracting key metrics and risk factors from earnings reports and SEC filings","compliance officers verifying adherence to regulatory requirements across policy documents"],"limitations":["Semantic search may fail on highly technical or domain-specific terminology if the embedding model lacks specialized training","Hallucination risk remains — LLM may generate plausible-sounding answers not grounded in source material despite RAG architecture","Context window limits (typically 4k-100k tokens) constrain how much document context can be passed per query, affecting accuracy on questions requiring synthesis across many sections","Chunking strategy (fixed-size vs semantic) affects retrieval quality; poor chunking can split relevant information across boundaries"],"requires":["Documents must be successfully parsed and indexed (see multi-format ingestion capability)","Minimum document length of ~100 tokens for meaningful semantic indexing","Active API connection to embedding model (likely OpenAI, Anthropic, or self-hosted) and LLM inference endpoint"],"input_types":["natural language question (text, 10-500 characters typical)","optional conversation history for multi-turn context"],"output_types":["natural language answer (text, 100-2000 characters typical)","source citations with document name and page/section reference","confidence scores or relevance indicators (if exposed)"],"categories":["memory-knowledge","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_nex__cap_10","uri":"capability://tool.use.integration.document.export.and.integration.with.external.systems","name":"document export and integration with external systems","description":"Enables export of documents, extracted data, and analysis results in multiple formats (PDF, CSV, JSON, API) and integration with external systems (CRM, contract management platforms, data warehouses). Implements export pipelines that transform internal representations into target formats, with optional data mapping and transformation rules. Supports both one-time exports and continuous synchronization via APIs or webhooks, enabling downstream systems to consume Nex insights without manual data transfer.","intents":["I need to export extracted contract metadata to our contract management system (e.g., Ironclad, Agiloft)","I want to sync compliance flags and risk assessments to our risk management dashboard in real-time","I need to generate PDF reports with summaries and analysis results for stakeholder distribution"],"best_for":["teams integrating Nex into existing document management or contract lifecycle management workflows","enterprises requiring data synchronization between Nex and downstream systems (CRM, data warehouse)","organizations needing standardized report generation for compliance or audit purposes"],"limitations":["Export format support depends on platform; not all formats may be available","Data mapping between Nex schema and external system schema requires configuration; complex mappings may require custom development","Real-time synchronization requires API availability and rate limits; high-volume exports may be throttled","Exported data may lose context or nuance from original analysis; consumers must understand data semantics"],"requires":["Document analysis must be completed before export","Target system credentials or API keys for integration","Optional: data mapping configuration or transformation rules"],"input_types":["analysis results (extracted data, summaries, flags, comparisons)","export configuration (format, target system, mapping rules)"],"output_types":["PDF reports (formatted with summaries, tables, visualizations)","CSV/Excel exports (tabular data with headers)","JSON exports (structured data for programmatic consumption)","API payloads (for real-time integration with external systems)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_nex__cap_11","uri":"capability://automation.workflow.document.annotation.and.collaborative.review","name":"document annotation and collaborative review","description":"Enables users to annotate documents with comments, highlights, and tags, and supports collaborative review workflows where multiple users can comment on the same document and track changes. Implements a comment threading system with user attribution, timestamps, and optional resolution tracking. Annotations are stored separately from the document, enabling non-destructive markup and version tracking. Supports role-based access control (read-only, comment, edit) to manage review workflows.","intents":["I need to highlight problematic clauses and add comments for legal review without modifying the original document","I want to collaborate with colleagues on contract review, with each person's comments visible and threaded","I need to track which comments have been addressed and which remain open for resolution"],"best_for":["legal teams conducting collaborative contract review and negotiation","compliance teams gathering feedback from multiple stakeholders on policy documents","procurement teams coordinating vendor agreement review across departments"],"limitations":["Annotation storage requires database infrastructure; large numbers of annotations may impact performance","Comment threading can become unwieldy on heavily annotated documents; requires UI/UX design for readability","Role-based access control requires upfront configuration; complex permission models may be difficult to manage","Annotations are not embedded in exported documents (e.g., PDF); consumers must access Nex UI to see comments"],"requires":["Document must be successfully ingested and indexed","User authentication and role management system","Annotation storage (database with versioning and audit trail)"],"input_types":["document (PDF, image, or other supported format)","user annotations (text comments, highlights, tags)","optional: role assignments for access control"],"output_types":["annotated document view (with comments and highlights visible)","comment export (CSV or JSON with user, timestamp, text)","annotation summary (count of comments, open issues, resolved items)","optional: annotated PDF export (with comments embedded)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_nex__cap_2","uri":"capability://data.processing.analysis.batch.document.analysis.and.insight.extraction","name":"batch document analysis and insight extraction","description":"Processes multiple documents in parallel through an analysis pipeline that extracts structured insights (key entities, relationships, summaries, risk flags) without requiring explicit user queries. Uses a combination of named entity recognition (NER), relationship extraction, and summarization models applied to document chunks, likely with configurable extraction templates or schemas that define which insights to extract. Results are aggregated across documents to enable comparative analysis and trend detection.","intents":["I need to extract key terms, dates, and obligations from 100 contracts without reading each one","I want to identify common risks or red flags across a portfolio of agreements","I need a structured summary table comparing terms across multiple documents"],"best_for":["legal teams conducting due diligence on multiple acquisition targets","procurement teams comparing vendor agreements for consistency and risk","compliance teams auditing policy adherence across departments"],"limitations":["Extraction accuracy depends on domain-specific training; generic NER models may miss industry jargon or context-dependent entities","Batch processing introduces latency (minutes to hours for large batches) compared to single-document analysis","Schema-based extraction requires upfront configuration; generic extraction may miss domain-specific insights","Cross-document aggregation assumes consistent terminology and structure; heterogeneous documents may produce noisy comparative results"],"requires":["Batch size typically limited by platform (likely 10-1000 documents per batch)","Documents must be successfully ingested and indexed","Optional: custom extraction schema or template definition for domain-specific insights"],"input_types":["collection of documents (PDFs, images, mixed formats)","optional extraction schema or configuration (JSON or UI-defined)"],"output_types":["structured extraction results (JSON, CSV, or table format)","comparative analysis across documents (similarity scores, variance reports)","aggregated insights (risk summaries, entity frequency tables, trend analysis)"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_nex__cap_3","uri":"capability://text.generation.language.conversational.document.interaction.with.multi.turn.context","name":"conversational document interaction with multi-turn context","description":"Implements a stateful chat interface where user questions and system responses are maintained in a conversation history, enabling follow-up questions that reference prior context without requiring re-specification of the document or prior answers. The system likely maintains a session state (conversation ID, document context, embedding cache) that persists across turns, allowing the LLM to understand pronouns, implicit references, and cumulative context. Each turn retrieves relevant document chunks based on the current question and conversation history, then generates responses that can reference both the document and prior exchanges.","intents":["I want to ask a follow-up question about a specific clause without re-stating the document or prior answer","I need to drill down into details mentioned in a previous answer without losing context","I want to compare information across multiple prior answers in a single conversation"],"best_for":["legal reviewers conducting iterative clause analysis and negotiation preparation","financial analysts exploring multiple dimensions of a report (revenue, margins, risks) in sequence","consultants synthesizing insights from documents through exploratory questioning"],"limitations":["Conversation history grows with each turn, eventually exceeding LLM context windows; requires summarization or pruning strategies","Multi-turn context can amplify hallucination if early turns contain errors that subsequent turns build upon","Session state must be persisted (database, cache) — loss of state resets conversation context","Implicit references (pronouns, 'the previous point') may be misinterpreted if conversation history is not properly summarized before passing to LLM"],"requires":["Active session management (server-side state or client-side state sync)","Document must remain indexed and accessible throughout conversation session","Conversation history storage (database or cache with TTL, typically 24-48 hours)"],"input_types":["natural language question (text, 10-500 characters)","implicit reference to prior conversation context"],"output_types":["natural language response (text, 100-2000 characters)","source citations with document reference","optional: conversation history export or summary"],"categories":["text-generation-language","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_nex__cap_4","uri":"capability://text.generation.language.document.summarization.with.configurable.detail.levels","name":"document summarization with configurable detail levels","description":"Generates abstractive summaries of documents at multiple granularity levels (executive summary, section-level summaries, key points) using a hierarchical summarization approach. The system likely chunks documents into sections, generates summaries at each level, then synthesizes section summaries into a document-level summary. Users can configure summary length, focus areas (e.g., 'risks only', 'financial metrics'), and output format (bullet points, prose, structured outline). The implementation likely uses prompt engineering or fine-tuned summarization models to enforce consistency and relevance.","intents":["I need a 1-page executive summary of a 50-page report without reading the full document","I want section-level summaries so I can quickly scan and drill into relevant areas","I need summaries focused on specific aspects (e.g., risks, financial impact) rather than generic overviews"],"best_for":["executives and decision-makers who need rapid document digestion for strategic decisions","legal teams preparing deal summaries for partner review and negotiation","compliance teams creating audit summaries for regulatory reporting"],"limitations":["Abstractive summarization may lose nuance or misrepresent complex technical details","Configurable focus areas require upfront specification; generic summaries may miss domain-specific priorities","Summary quality degrades on poorly structured documents or those with inconsistent formatting","Length constraints (e.g., 'one page') may force omission of important details; trade-off between brevity and completeness"],"requires":["Document must be successfully parsed and indexed","Minimum document length of ~500 tokens for meaningful summarization","Optional: summary configuration (length, focus areas, format preferences)"],"input_types":["document (PDF, image, or other supported format)","optional configuration (summary length, focus areas, output format)"],"output_types":["executive summary (text, typically 200-500 words)","section-level summaries (text, typically 50-200 words per section)","key points list (bullet points or structured outline)","optional: summary with source citations"],"categories":["text-generation-language","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_nex__cap_5","uri":"capability://data.processing.analysis.document.comparison.and.delta.analysis","name":"document comparison and delta analysis","description":"Compares two or more documents to identify differences, similarities, and changes across versions or related documents. Uses a combination of text alignment algorithms (likely sequence matching or diff-based approaches) and semantic similarity to detect substantive changes (clause modifications, term variations) versus formatting differences. Results highlight additions, deletions, and modifications with context, enabling users to quickly identify what changed between contract versions or how similar agreements differ in key terms.","intents":["I need to see what changed between version 1 and version 2 of a contract without manually comparing them","I want to identify how our standard agreement differs from a vendor's proposed terms","I need to track modifications across multiple rounds of negotiation"],"best_for":["contract negotiators tracking changes across redline rounds","legal teams comparing standard agreements against counterparty proposals","compliance teams identifying deviations from policy templates across departments"],"limitations":["Text-based diff algorithms may produce noisy results if documents have different formatting or structure","Semantic comparison requires embedding models that may not capture domain-specific significance of changes","Large documents with many changes may produce overwhelming diff output; requires filtering or summarization","Formatting-only changes (page breaks, font) may be flagged as differences, creating noise"],"requires":["Two or more documents successfully ingested and indexed","Documents should be in similar format or domain for meaningful comparison"],"input_types":["two or more documents (PDFs, images, or mixed formats)","optional comparison configuration (focus areas, ignore formatting)"],"output_types":["side-by-side diff view (text with additions/deletions highlighted)","summary of changes (count of additions/deletions, modified sections)","semantic change analysis (substantive vs formatting changes)","optional: change impact assessment (risk flags for significant modifications)"],"categories":["data-processing-analysis","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_nex__cap_6","uri":"capability://data.processing.analysis.document.classification.and.tagging","name":"document classification and tagging","description":"Automatically categorizes documents into predefined classes (e.g., 'NDA', 'Service Agreement', 'Purchase Order') and applies tags based on detected content, metadata, or user-defined rules. Uses a combination of text classification models (likely fine-tuned on domain-specific corpora) and rule-based heuristics (keyword matching, structural patterns) to assign categories with confidence scores. Results enable filtering, organization, and routing of documents without manual categorization.","intents":["I need to automatically sort a batch of 500 mixed documents into contract types without manual review","I want to tag documents with risk levels or compliance categories based on detected content","I need to route documents to appropriate teams based on classification (legal, finance, procurement)"],"best_for":["legal teams organizing large document repositories for discovery or due diligence","compliance teams categorizing documents for regulatory reporting and audit trails","procurement teams routing vendor agreements to appropriate stakeholders"],"limitations":["Classification accuracy depends on training data; poor performance on novel or hybrid document types","Confidence scores may be misleading if model is poorly calibrated; high confidence doesn't guarantee accuracy","Rule-based heuristics require upfront configuration and maintenance; difficult to scale to new document types","Ambiguous documents (e.g., hybrid NDA+Service Agreement) may be misclassified or require manual review"],"requires":["Predefined classification schema (document types, tag categories)","Documents must be successfully parsed and indexed","Optional: training data or examples for custom classification models"],"input_types":["document (PDF, image, or other supported format)","optional classification schema or rules"],"output_types":["primary document class (text, with confidence score)","secondary tags or categories (list of strings with confidence scores)","classification reasoning or explanation (optional)"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_nex__cap_7","uri":"capability://data.processing.analysis.document.metadata.extraction.and.structuring","name":"document metadata extraction and structuring","description":"Automatically extracts structured metadata from documents (dates, parties, amounts, effective periods, renewal terms) and normalizes it into a queryable schema. Uses a combination of named entity recognition (NER) for entity detection, relation extraction to link entities (e.g., 'Party A is XYZ Corp'), and domain-specific pattern matching (regex for dates, amounts) to populate structured fields. Results are stored in a database or knowledge graph, enabling filtering, sorting, and aggregation across documents.","intents":["I need to extract contract dates, parties, and renewal terms from 100 agreements into a spreadsheet","I want to find all contracts expiring in the next 90 days without manually reviewing each one","I need to aggregate financial terms (amounts, payment schedules) across a portfolio of agreements"],"best_for":["contract lifecycle management teams tracking renewal dates and key terms","financial teams extracting payment terms and amounts for cash flow forecasting","procurement teams maintaining a master database of vendor agreements and terms"],"limitations":["Extraction accuracy varies by field; dates and amounts are more reliable than complex relationships","Domain-specific terminology or non-standard formatting reduces extraction accuracy","Ambiguous references (e.g., 'the Agreement' without clear antecedent) may produce incorrect extractions","Structured schema must be predefined; extraction of unexpected fields requires schema updates"],"requires":["Document must be successfully parsed and indexed","Predefined metadata schema (field names, types, validation rules)","Optional: training examples or patterns for custom field extraction"],"input_types":["document (PDF, image, or other supported format)","metadata schema definition (JSON or UI-defined)"],"output_types":["structured metadata (JSON, CSV, or database record)","extraction confidence scores per field","optional: extraction reasoning or source citations"],"categories":["data-processing-analysis","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_nex__cap_8","uri":"capability://search.retrieval.document.search.and.retrieval.with.semantic.ranking","name":"document search and retrieval with semantic ranking","description":"Enables full-text and semantic search across a document corpus, returning results ranked by relevance to the query. Implements a hybrid search approach combining keyword matching (BM25 or TF-IDF) with semantic similarity (embedding-based retrieval) to balance lexical and semantic relevance. Users can search across document titles, content, extracted metadata, and tags. Results include snippets with query terms highlighted and relevance scores, enabling rapid document discovery without manual browsing.","intents":["I need to find all documents mentioning 'indemnification' or related concepts across a 1000-document repository","I want to search for documents similar to a reference agreement without knowing exact keywords","I need to filter documents by metadata (date range, party name, document type) and then search within results"],"best_for":["legal teams searching large document repositories for precedents or similar agreements","compliance teams finding documents relevant to specific regulations or policies","knowledge workers discovering related documents during research or analysis"],"limitations":["Semantic search quality depends on embedding model; domain-specific terminology may not be well-represented","Hybrid search requires tuning weights between keyword and semantic components; suboptimal tuning reduces relevance","Large result sets (1000+ documents) may overwhelm users; requires pagination or result filtering","Search performance degrades with corpus size; may require indexing optimization or caching strategies"],"requires":["Documents must be successfully ingested and indexed","Vector index for semantic search (likely using FAISS, Pinecone, or similar)","Full-text index for keyword search (likely using Elasticsearch or similar)"],"input_types":["search query (text, 5-100 characters typical)","optional filters (date range, document type, party name, tags)"],"output_types":["ranked list of documents (with relevance scores)","snippets with query terms highlighted","metadata summary per result (date, parties, document type)","optional: search explanation or relevance reasoning"],"categories":["search-retrieval","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_nex__cap_9","uri":"capability://safety.moderation.document.compliance.checking.and.risk.flagging","name":"document compliance checking and risk flagging","description":"Automatically scans documents against compliance rules, regulatory requirements, or risk criteria to identify potential issues. Uses a combination of pattern matching (regex for prohibited terms), rule-based logic (if-then conditions), and ML-based risk detection (trained on labeled examples of risky clauses) to flag problematic content. Results highlight specific clauses or sections with risk severity levels and remediation suggestions, enabling compliance teams to prioritize review efforts.","intents":["I need to flag contracts with non-standard liability caps or indemnification terms that deviate from our policy","I want to identify documents that may violate data privacy regulations (GDPR, CCPA) based on data handling clauses","I need to detect high-risk terms (unlimited liability, unilateral termination rights) across a portfolio of agreements"],"best_for":["compliance teams conducting regulatory audits and risk assessments","legal teams enforcing contract standards and identifying deviations","risk management teams monitoring portfolio-level compliance and exposure"],"limitations":["Rule-based compliance checking requires upfront rule definition; difficult to scale to new regulations","ML-based risk detection requires labeled training data; performance varies by risk type","False positives (flagging benign content as risky) can create alert fatigue and reduce effectiveness","Context-dependent risks (e.g., liability caps appropriate for some contracts but not others) may be misclassified"],"requires":["Document must be successfully parsed and indexed","Predefined compliance rules or risk criteria (rule definitions, ML models, or both)","Optional: labeled training data for custom risk models"],"input_types":["document (PDF, image, or other supported format)","compliance rules or risk criteria (rule definitions, ML models)"],"output_types":["risk flags with severity levels (high/medium/low)","flagged clauses or sections with source citations","remediation suggestions or policy guidance","compliance score or risk summary"],"categories":["safety-moderation","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":43,"verified":false,"data_access_risk":"high","permissions":["Document file size under platform limits (likely 10-50MB per document)","Supported MIME types: application/pdf, image/jpeg, image/png, potentially application/vnd.openxmlformats-officedocument.wordprocessingml.document","Documents must be successfully parsed and indexed (see multi-format ingestion capability)","Minimum document length of ~100 tokens for meaningful semantic indexing","Active API connection to embedding model (likely OpenAI, Anthropic, or self-hosted) and LLM inference endpoint","Document analysis must be completed before export","Target system credentials or API keys for integration","Optional: data mapping configuration or transformation rules","Document must be successfully ingested and indexed","User authentication and role management system"],"failure_modes":["OCR accuracy degrades on low-resolution scans or handwritten text with poor legibility","Large documents (>100 pages) may require pagination or chunking, affecting context window availability","Unsupported formats (e.g., proprietary CAD files, legacy binary formats) will fail silently or require manual conversion","Semantic search may fail on highly technical or domain-specific terminology if the embedding model lacks specialized training","Hallucination risk remains — LLM may generate plausible-sounding answers not grounded in source material despite RAG architecture","Context window limits (typically 4k-100k tokens) constrain how much document context can be passed per query, affecting accuracy on questions requiring synthesis across many sections","Chunking strategy (fixed-size vs semantic) affects retrieval quality; poor chunking can split relevant information across boundaries","Export format support depends on platform; not all formats may be available","Data mapping between Nex schema and external system schema requires configuration; complex mappings may require custom development","Real-time synchronization requires API availability and rate limits; high-volume exports may be throttled","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":"2026-05-24T12:16:31.858Z","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=nex","compare_url":"https://unfragile.ai/compare?artifact=nex"}},"signature":"+hLhQOMssUPG1aGX2tO3qPgPOPHxl4vaWkHvP2M0R7XAlhn2N2WsuVQ1OWX+RTqL/rm1B+pGjtzZDOY5YiNbAA==","signedAt":"2026-06-22T03:52:50.379Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/nex","artifact":"https://unfragile.ai/nex","verify":"https://unfragile.ai/api/v1/verify?slug=nex","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"}}