> ## Documentation Index
> Fetch the complete documentation index at: https://docs.valiqor.com/llms.txt
> Use this file to discover all available pages before exploring further.

# What Valiqor Does

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

## Valiqor finds *why* your AI app fails

Most evaluation tools tell you something is wrong. Valiqor tells you **what went wrong, why it happened, and how to fix it** — with severity scoring, root-cause analysis, and actionable remediation.

<Info>
  **You can get started in 5 minutes** — no tracing or instrumentation needed. Just pass your existing AI inputs and outputs to Failure Analysis and see results immediately.
</Info>

***

## Five modules, one SDK

Valiqor's Python SDK exposes five modules through a single client:

```python theme={"system"}
from valiqor import ValiqorClient

client = ValiqorClient(api_key="vq_...")

client.failure_analysis   # Root-cause failure detection
client.eval               # Metric-based evaluation
client.security           # Red-team audits & vulnerability scanning
client.trace              # Auto-instrumentation for OpenAI, Anthropic, LangChain
client.scanner            # Repository & prompt scanning
```

| Module               | What it does                                                                                 | When to use it                                      |
| -------------------- | -------------------------------------------------------------------------------------------- | --------------------------------------------------- |
| **Failure Analysis** | Classifies failures into buckets & subcategories, scores severity (0–5), explains root cause | First thing to run — works on any input/output data |
| **Evaluation**       | Runs metric-based checks (hallucination, relevance, coherence, etc.)                         | When you need granular metric scores                |
| **Security**         | Runs red-team attacks, checks for prompt injection, data leakage, jailbreaks                 | Before deploying to production                      |
| **Tracing**          | Auto-captures LLM calls, tool use, retrieval steps as structured traces                      | When you want continuous monitoring in production   |
| **Scanner**          | Scans repositories and prompts for best-practice violations                                  | During code review or CI                            |

***

## Two ways to get started

<CardGroup cols={2}>
  <Card title="Quick start — Run on existing data" icon="bolt" href="/start-here/see-a-failure">
    Pass your AI inputs/outputs directly. No tracing, no instrumentation. See failure results in under 5 minutes.
  </Card>

  <Card title="Full observability — Add tracing" icon="radar" href="/workflows/tracing">
    Instrument your LLM calls with auto-tracing. Run Failure Analysis on traces for continuous production monitoring.
  </Card>
</CardGroup>

***

## Who is Valiqor for?

Valiqor is built for **AI engineers and teams** who build applications on top of:

* **LLM providers** — OpenAI, Anthropic, Google, Mistral, Cohere, and any OpenAI-compatible API
* **Orchestration frameworks** — LangChain, CrewAI, LlamaIndex, Haystack
* **Custom pipelines** — RAG systems, agent loops, multi-step chains

Whether you're prototyping or running in production, Valiqor helps you catch and fix failures before your users do.

***

## What you get

<Steps>
  <Step title="Failure taxonomy">
    Every failure is classified into **buckets** (e.g., Hallucination, Context Ignorance) and **subcategories** (e.g., Entity Fabrication, Contradicts Source).
  </Step>

  <Step title="Root-cause analysis">
    Each failure includes a `judge_rationale` explaining exactly what went wrong, plus a `scoring_breakdown` with evidence.
  </Step>

  <Step title="Severity & confidence scoring">
    Severity from 0 (no issue) to 5 (critical). Confidence from 0.0 to 1.0. Filter and prioritize failures automatically.
  </Step>

  <Step title="Actionable remediation">
    Fix your prompts, retrieval pipeline, or guardrails based on concrete failure evidence — not guesswork.
  </Step>
</Steps>

***

<Card title="Ready? See your first failure →" icon="arrow-right" href="/start-here/see-a-failure">
  Run Failure Analysis on your existing data in under 5 minutes.
</Card>