# Valiqor

> Find why your AI app fails — not just that it fails. Trace, evaluate, analyze failures, and secure your AI applications.

## Docs

- [Create Api Key Via Edge Function](https://docs.valiqor.com/api-reference/authentication/create-api-key-via-edge-function.md): Create API key via Supabase Edge Function
- [Get User Usage](https://docs.valiqor.com/api-reference/authentication/get-user-usage.md): Get current usage and quota information for the authenticated user
- [List Api Keys Via Edge Function](https://docs.valiqor.com/api-reference/authentication/list-api-keys-via-edge-function.md): List all API keys for the authenticated user (via Edge Function)
- [Resend Verification](https://docs.valiqor.com/api-reference/authentication/resend-verification.md): Resend verification email for the current user.
- [Revoke Api Key Via Edge Function](https://docs.valiqor.com/api-reference/authentication/revoke-api-key-via-edge-function.md): Revoke an API key (via Edge Function)
- [Validate Auth](https://docs.valiqor.com/api-reference/authentication/validate-auth.md): Validate API key and return user information
- [Cancel Job](https://docs.valiqor.com/api-reference/evaluation/cancel-job.md): Request cancellation of a running evaluation job.
- [Compare Evaluation Runs](https://docs.valiqor.com/api-reference/evaluation/compare-evaluation-runs.md): Compare multiple evaluation runs side-by-side
- [Evaluate](https://docs.valiqor.com/api-reference/evaluation/evaluate.md): Run evaluation on dataset
- [Evaluate Trace](https://docs.valiqor.com/api-reference/evaluation/evaluate-trace.md): Evaluate a trace directly using the evaluation engine.
- [Get Evaluation Item](https://docs.valiqor.com/api-reference/evaluation/get-evaluation-item.md): Get full evaluation item details
- [Get Evaluation Trends](https://docs.valiqor.com/api-reference/evaluation/get-evaluation-trends.md): Get metric trends over time for charts
- [Get Job Status](https://docs.valiqor.com/api-reference/evaluation/get-job-status.md): Get the status of an evaluation job (for polling fallback when WebSocket unavailable).
- [Get Project Stats](https://docs.valiqor.com/api-reference/evaluation/get-project-stats.md): Get project statistics
- [Get Run](https://docs.valiqor.com/api-reference/evaluation/get-run.md): Get evaluation run details
- [Get Run Items](https://docs.valiqor.com/api-reference/evaluation/get-run-items.md): Get paginated evaluation items for a run
- [Get Run Metrics](https://docs.valiqor.com/api-reference/evaluation/get-run-metrics.md): Get aggregated metrics for an evaluation run
- [Cancel analysis job](https://docs.valiqor.com/api-reference/failure-analysis/cancel-analysis-job.md): Cancel an in-progress failure analysis job
- [Get analysis run](https://docs.valiqor.com/api-reference/failure-analysis/get-analysis-run.md): Get details of a specific failure analysis run
- [Get bucket details](https://docs.valiqor.com/api-reference/failure-analysis/get-bucket-details.md): Get details for a specific failure bucket
- [Get FA insights summary](https://docs.valiqor.com/api-reference/failure-analysis/get-fa-insights-summary.md): Get aggregated insights across FA runs with optional time and project filters
- [Get FA security insights](https://docs.valiqor.com/api-reference/failure-analysis/get-fa-security-insights.md): Get aggregated security insights across FA runs that included security scans
- [Get FA trend data](https://docs.valiqor.com/api-reference/failure-analysis/get-fa-trend-data.md): Get time-series trend data for charting
- [Get failure tags](https://docs.valiqor.com/api-reference/failure-analysis/get-failure-tags.md): Get only the failure tags from an analysis run
- [Get failure taxonomy](https://docs.valiqor.com/api-reference/failure-analysis/get-failure-taxonomy.md): Get the full failure taxonomy with all buckets and subcategories
- [Get job status (alias)](https://docs.valiqor.com/api-reference/failure-analysis/get-job-status-alias.md): Alias for /runs/{run_id}/status - Poll the status of an async failure analysis job
- [Get projects with FA runs](https://docs.valiqor.com/api-reference/failure-analysis/get-projects-with-fa-runs.md): Get list of project names that have FA runs for filter dropdown
- [Get run count](https://docs.valiqor.com/api-reference/failure-analysis/get-run-count.md): Fast endpoint to check if user has any FA runs
- [Get run input items](https://docs.valiqor.com/api-reference/failure-analysis/get-run-input-items.md): Get the original input items for a failure analysis run with per-item failure stats
- [Get run status](https://docs.valiqor.com/api-reference/failure-analysis/get-run-status.md): Poll the status of an async failure analysis job
- [List analysis runs](https://docs.valiqor.com/api-reference/failure-analysis/list-analysis-runs.md): List failure analysis runs for the current project
- [List subcategories](https://docs.valiqor.com/api-reference/failure-analysis/list-subcategories.md): List failure subcategories with optional filters
- [Playground analysis](https://docs.valiqor.com/api-reference/failure-analysis/playground-analysis.md): Lightweight single-item failure analysis for dashboard playground
- [Run failure analysis](https://docs.valiqor.com/api-reference/failure-analysis/run-failure-analysis.md): Run failure analysis on a trace or minimal input dataset
- [Create Project](https://docs.valiqor.com/api-reference/projects/create-project.md): Create a new project
- [Get Project](https://docs.valiqor.com/api-reference/projects/get-project.md): Get project details
- [List Projects](https://docs.valiqor.com/api-reference/projects/list-projects.md): List all projects for the authenticated organization
- [Get Feature Judge Prompts Endpoint](https://docs.valiqor.com/api-reference/scanner/get-feature-judge-prompts-endpoint.md): Get generated judge prompts for a feature
- [Get Feature Workflow](https://docs.valiqor.com/api-reference/scanner/get-feature-workflow.md): Get workflow graph for a specific feature
- [Get Scan Features Endpoint](https://docs.valiqor.com/api-reference/scanner/get-scan-features-endpoint.md): Get all detected features for a scan
- [Get Scan Prompts Endpoint](https://docs.valiqor.com/api-reference/scanner/get-scan-prompts-endpoint.md): Get all extracted prompts for a scan
- [Get Scan Status](https://docs.valiqor.com/api-reference/scanner/get-scan-status.md): Get processing status for a scan
- [Upload Scan Files](https://docs.valiqor.com/api-reference/scanner/upload-scan-files.md): Upload scan files for processing.
- [Cancel Security Job](https://docs.valiqor.com/api-reference/security/cancel-security-job.md): Request cancellation of a running security or redteam job.
- [Compare Redteam Runs](https://docs.valiqor.com/api-reference/security/compare-redteam-runs.md): Compare multiple red team runs side-by-side
- [Get Attack Details](https://docs.valiqor.com/api-reference/security/get-attack-details.md): Get full attack details
- [Get Audit Batch](https://docs.valiqor.com/api-reference/security/get-audit-batch.md): Get security audit batch details
- [Get Audit Item Details](https://docs.valiqor.com/api-reference/security/get-audit-item-details.md): Get full audit item details
- [Get Audit Items](https://docs.valiqor.com/api-reference/security/get-audit-items.md): Get security audit items for a batch
- [Get Project Attack Vectors](https://docs.valiqor.com/api-reference/security/get-project-attack-vectors.md): Get attack vector configuration for a project
- [Get Project Vulnerabilities](https://docs.valiqor.com/api-reference/security/get-project-vulnerabilities.md): Get vulnerability detection configuration for a project
- [Get Redteam Attacks](https://docs.valiqor.com/api-reference/security/get-redteam-attacks.md): Get red team attacks for a run
- [Get Redteam Run](https://docs.valiqor.com/api-reference/security/get-redteam-run.md): Get red team run details
- [Get Security Job Status](https://docs.valiqor.com/api-reference/security/get-security-job-status.md): Get the status of a security or redteam job (for polling fallback).
- [List Attack Vector Templates](https://docs.valiqor.com/api-reference/security/list-attack-vector-templates.md): List all available attack vector templates
- [List Audit Batches](https://docs.valiqor.com/api-reference/security/list-audit-batches.md): List security audit batches for a project or multiple projects.
- [List Redteam Runs](https://docs.valiqor.com/api-reference/security/list-redteam-runs.md): List red team runs for a project or multiple projects.
- [List Vulnerability Templates](https://docs.valiqor.com/api-reference/security/list-vulnerability-templates.md): List all available vulnerability templates (S1-S23)
- [Run Red Team Simulation](https://docs.valiqor.com/api-reference/security/run-red-team-simulation.md): Run red team simulation (always runs asynchronously)
- [Run Security Audit](https://docs.valiqor.com/api-reference/security/run-security-audit.md): Run security audit on a dataset
- [Run Security Audit From Trace](https://docs.valiqor.com/api-reference/security/run-security-audit-from-trace.md): Run security audit on a trace file.
- [Update Project Attack Vector](https://docs.valiqor.com/api-reference/security/update-project-attack-vector.md): Update attack vector settings for a project
- [Update Project Vulnerability](https://docs.valiqor.com/api-reference/security/update-project-vulnerability.md): Update vulnerability type settings for a project
- [Get Eval Steps Endpoint](https://docs.valiqor.com/api-reference/tracing/get-eval-steps-endpoint.md): Get eval steps for a trace
- [Get Trace Endpoint](https://docs.valiqor.com/api-reference/tracing/get-trace-endpoint.md): Get trace by ID (must belong to authenticated org)
- [Get Trace Full Endpoint](https://docs.valiqor.com/api-reference/tracing/get-trace-full-endpoint.md): Get complete trace JSON for Raw JSON tab (lazy loaded). This endpoint returns the full trace structure reconstructed from all tables.
- [Get Trace Messages Endpoint](https://docs.valiqor.com/api-reference/tracing/get-trace-messages-endpoint.md): Get messages for Conversation tab (lazy loaded). Client-side filtering is expected.
- [Get Trace Spans Endpoint](https://docs.valiqor.com/api-reference/tracing/get-trace-spans-endpoint.md): Get spans for Spans tab (lazy loaded).
- [Get Trace Summary Endpoint](https://docs.valiqor.com/api-reference/tracing/get-trace-summary-endpoint.md): Get trace summary for drawer header + Metrics/Metadata/Diagnostics tabs. Lightweight endpoint that doesn't load full messages or spans.
- [List Traces Endpoint](https://docs.valiqor.com/api-reference/tracing/list-traces-endpoint.md): List traces for a project with pagination.
- [Upload Trace Endpoint](https://docs.valiqor.com/api-reference/tracing/upload-trace-endpoint.md): Upload a trace and optionally generate eval_steps.
- [Authentication](https://docs.valiqor.com/cli/authentication.md): CLI commands for login, signup, logout, email verification, and API key management.
- [Configuration](https://docs.valiqor.com/cli/configuration.md): CLI commands for project initialization, viewing settings, updating config, testing connectivity, and uploading files.
- [Evaluation](https://docs.valiqor.com/cli/evaluation.md): CLI commands for running evaluations, checking status, retrieving results, and listing metrics.
- [Failure Analysis](https://docs.valiqor.com/cli/failure-analysis.md): CLI commands for running failure analysis, checking status, retrieving results, and listing runs.
- [CLI Overview](https://docs.valiqor.com/cli/overview.md): Install the Valiqor CLI, understand global options, and learn the command structure.
- [Scanning](https://docs.valiqor.com/cli/scanning.md): CLI commands for running AST-based code scans to detect LLM usage patterns.
- [Security](https://docs.valiqor.com/cli/security.md): CLI commands for security audits, red team simulations, vulnerability categories, and attack vectors.
- [Tracing](https://docs.valiqor.com/cli/tracing.md): CLI commands for trace initialization, applying decorators, removing instrumentation, and refreshing suggestions.
- [Evaluation Model](https://docs.valiqor.com/concepts/evaluation-model.md): Built-in evaluation metrics, LLM judge architecture, scoring, and quality grades.
- [Failure Taxonomy](https://docs.valiqor.com/concepts/failure-taxonomy.md): How Valiqor categorizes failures: buckets, subcategories, detector types, and scope.
- [Root Cause Detection](https://docs.valiqor.com/concepts/root-cause-detection.md): How Valiqor traces failures back to root causes with severity scoring, confidence, and actionable remediation.
- [Security Categories](https://docs.valiqor.com/concepts/security-categories.md): Canonical reference for Valiqor's S1–S23 vulnerability categories and attack vector strategies.
- [Traces & Spans](https://docs.valiqor.com/concepts/traces-and-spans.md): Understand Valiqor's trace data model: traces, spans, span kinds, RAG stages, and conversation threads.
- [Agno](https://docs.valiqor.com/integrations/agno.md): Auto-instrument Agno agents with tracing for agent runs, tool calls, and MCP tool integration.
- [Anthropic](https://docs.valiqor.com/integrations/anthropic.md): Auto-instrument Anthropic Claude messages with zero-config tracing. Supports sync and async.
- [CrewAI](https://docs.valiqor.com/integrations/crewai.md): CrewAI integration for Valiqor tracing — coming soon.
- [Google GenAI (Gemini)](https://docs.valiqor.com/integrations/google-genai.md): Google GenAI integration for Valiqor tracing — coming soon.
- [LangChain](https://docs.valiqor.com/integrations/langchain.md): Auto-instrument LangChain and LangGraph with tracing for chat models, chains, tools, retrievers, and graph nodes.
- [Ollama](https://docs.valiqor.com/integrations/ollama.md): Auto-instrument Ollama local model calls with tracing for chat and generate endpoints.
- [OpenAI](https://docs.valiqor.com/integrations/openai.md): Auto-instrument OpenAI chat completions with zero-config tracing. Supports sync, async, and tool calls.
- [Platforms](https://docs.valiqor.com/integrations/platforms.md): CI/CD and deployment platform integrations for Valiqor.
- [Changelog](https://docs.valiqor.com/resources/changelog.md): Version history, new features, and changes for the Valiqor SDK.
- [FAQ](https://docs.valiqor.com/resources/faq.md): Frequently asked questions about Valiqor — architecture, data handling, integrations, and usage.
- [Rate Limits](https://docs.valiqor.com/resources/rate-limits.md): Per-endpoint rate limits, per-org quotas, trial vs paid tier limits, and how to check your usage.
- [Troubleshooting](https://docs.valiqor.com/resources/troubleshooting.md): Common errors, their causes, and how to resolve them.
- [Configuration](https://docs.valiqor.com/sdk/configuration.md): Configure the SDK via .valiqorrc files, environment variables, or programmatic calls.
- [EvalClient](https://docs.valiqor.com/sdk/eval-client.md): Run evaluations, manage metrics, and retrieve results with the evaluation client.
- [Exceptions](https://docs.valiqor.com/sdk/exceptions.md): Complete reference for all Valiqor exception types with causes and resolution steps.
- [FailureAnalysisClient](https://docs.valiqor.com/sdk/failure-analysis-client.md): Run failure analysis, explore failure taxonomy, and retrieve insights and trends.
- [Models](https://docs.valiqor.com/sdk/models.md): Data models and types: EvaluationResult, FARunResult, SecurityAuditResult, AsyncJobHandle, and more.
- [Evaluation Models](https://docs.valiqor.com/sdk/models/evaluation.md): Data models for evaluation results, run metrics, item details, trends, and comparisons.
- [Failure Analysis Models](https://docs.valiqor.com/sdk/models/failure-analysis.md): Data models for failure analysis results, failure tags, taxonomy, insights, and playground.
- [Security Models](https://docs.valiqor.com/sdk/models/security.md): Data models for security audit results, red team simulations, batches, vulnerabilities, and attack vectors.
- [Trace, RAG & Async Models](https://docs.valiqor.com/sdk/models/traces.md): Data models for traces, spans, messages, RAG retrieval, and async job handling.
- [ScannerClient](https://docs.valiqor.com/sdk/scanner-client.md): AST-based static analysis to detect AI features, extract prompts, and map workflows in your codebase.
- [SecurityClient](https://docs.valiqor.com/sdk/security-client.md): Run security audits, red team simulations, and manage vulnerability configurations.
- [TraceQueryClient](https://docs.valiqor.com/sdk/trace-query-client.md): Query traces from the backend — list, get, summarize, and inspect spans and messages.
- [Tracer & Auto-Instrumentation](https://docs.valiqor.com/sdk/tracer.md): Trace your AI app with zero-config auto-instrumentation, decorators, manual spans, and exporters.
- [ValiqorClient](https://docs.valiqor.com/sdk/valiqor-client.md): The unified client facade — access eval, security, trace, scanner, failure analysis, and project management from a single entry point.
- [Fix the Failure](https://docs.valiqor.com/start-here/fix-the-failure.md): Walk through a failure analysis result and learn how to fix the root cause.
- [How Valiqor Works](https://docs.valiqor.com/start-here/how-valiqor-works.md): Architecture overview: SDK, backend, LLM judges, async jobs, and data flow.
- [See a Failure in 5 Minutes](https://docs.valiqor.com/start-here/see-a-failure.md): Go from zero to your first failure analysis result in under 5 minutes — no tracing or instrumentation required.
- [What Valiqor Does](https://docs.valiqor.com/start-here/what-valiqor-does.md): Valiqor finds why your AI app fails — not just that it fails. Trace, evaluate, analyze failures, and secure your AI applications.
- [Async & Batch](https://docs.valiqor.com/workflows/async-batch.md): Run evaluations, security audits, and failure analysis asynchronously for large datasets.
- [Bring Your Own Key (BYOK)](https://docs.valiqor.com/workflows/byom.md): Use your own OpenAI API key for LLM judges instead of Valiqor's shared quota.
- [Code Scanning](https://docs.valiqor.com/workflows/code-scanning.md): AST-based static analysis of your AI codebase to detect features, extract prompts, and map workflows.
- [Evaluations](https://docs.valiqor.com/workflows/evaluations.md): Measure your AI app's quality with built-in metrics like answer relevance, hallucination detection, and task adherence.
- [Failure Analysis](https://docs.valiqor.com/workflows/failure-analysis.md): Run failure analysis on your AI app's outputs to identify root causes, failure patterns, and get actionable fixes.
- [Security & Red Teaming](https://docs.valiqor.com/workflows/security.md): Audit your AI app for 23 vulnerability categories and run adversarial red team simulations.
- [Tracing AI Apps](https://docs.valiqor.com/workflows/tracing.md): Instrument your AI application to capture traces, spans, and conversation flows for continuous monitoring.

## OpenAPI Specs

- [openapi](https://docs.valiqor.com/openapi.json)