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

# Analytics & Quality

> Understanding and improving processing quality over time

Analytics help you answer one practical question: **can I trust this workflow's results before I rely on them?**

Once you've verified some documents, the **Analytics** tab in each workflow shows you how well it's performing — how reliable the results are, where errors tend to appear, and which fields need attention.

<Tip>
  **The short version:** anyformat gives every value a **confidence** score so you know where to look — review the low-confidence ones first. Over time, your verifications produce an **accuracy** number that tells you how often the workflow is actually right. Aim for high accuracy with light review on the low-confidence cases — you don't need to check everything.
</Tip>

The rest of this page explains both numbers in detail.

***

## Confidence

### What is confidence?

**Confidence** represents how certain anyformat is about an extracted value.

It's expressed as a percentage:

* **High confidence** - the model is very sure
* **Low confidence** - the value may be ambiguous or unclear

Confidence is calculated per:

* Field
* Document
* Workflow (average)

<img src="https://mintcdn.com/anyformat/pilIFdJ4MJRok4mo/images/confidence.webp?fit=max&auto=format&n=pilIFdJ4MJRok4mo&q=85&s=f053b0af762cc1c37f88be8622c56b09" alt="Confidence score" width="1436" height="536" data-path="images/confidence.webp" />

***

### What confidence is (and isn't)

<CardGroup cols={2}>
  <Card title="Confidence IS" icon="check">
    * A **signal**, not a verdict
    * A way to prioritize human review
    * A guide for where to look first
  </Card>

  <Card title="Confidence is NOT" icon="xmark">
    * A guarantee of correctness
    * A replacement for verifying results yourself
    * A measure of business accuracy
  </Card>
</CardGroup>

A value can have:

* High confidence and still be wrong
* Low confidence and still be correct

***

### How to use confidence effectively

Use confidence to:

* Focus review on low-confidence fields
* Skip reviewing obviously reliable values
* Reduce overall human effort

A good workflow doesn't eliminate low confidence — it **contains it**.

***

## Accuracy explained

### What is accuracy?

**Accuracy** measures how often extracted values are actually **correct**, based on the documents you've verified.

> Accuracy reflects confirmed correctness, not how sure the model felt.

Accuracy is calculated from:

* Fields you verified as correct
* Fields you corrected

***

### Accuracy vs confidence

| Confidence                                       | Accuracy                          |
| ------------------------------------------------ | --------------------------------- |
| How sure the model is                            | How often it's confirmed right    |
| Available immediately, before you check anything | Builds up as you verify documents |
| A guess about each value, up front               | A track record, after the fact    |
| Helps you prioritize what to review              | Measures real performance         |

You need **both**:

* Confidence to guide review
* Accuracy to judge quality

***

### What accuracy tells you

Accuracy helps you answer:

* Can I trust this workflow?
* Is it ready to scale?
* Which fields are fragile?

Low accuracy usually points to:

* Ambiguous instructions
* Poor field definitions
* Edge cases in documents

***

## Viewing analytics

### Workflow-level analytics

In the **Analytics** tab of a workflow, you can see:

* Average confidence
* Average accuracy
* Trends over time (if available)

This gives you a high-level sense of workflow health.

<img src="https://mintcdn.com/anyformat/pilIFdJ4MJRok4mo/images/monitoring.webp?fit=max&auto=format&n=pilIFdJ4MJRok4mo&q=85&s=b68f91387c9e760652720da0cd17c9f5" alt="Analytics monitoring" width="3016" height="1572" data-path="images/monitoring.webp" />

***

### Field-level analytics

You can also analyze metrics **per field**:

* Average confidence by field
* Accuracy by field
* Sort fields by performance

This is often the most useful view. It helps you quickly spot:

* Fields that consistently fail
* Fields that don't need review anymore
* Outliers dragging accuracy down

***

## Improving results

### How to improve confidence

To improve confidence:

* Make instructions more explicit
* Clarify where information appears
* Reduce ambiguity in field definitions
* Split complex fields into simpler ones

Confidence improves when field definitions become clearer.

***

### How to improve accuracy

To improve accuracy:

* Correct wrong values while verifying
* Review low-confidence fields carefully
* Refine the workflow when patterns appear
* Adjust fields or instructions if needed

Accuracy improves through **human feedback loops**.

***

### When to refine the workflow

You should consider refining a workflow when:

* The same field is often corrected
* Accuracy plateaus below expectations
* New document variations appear

<Info>
  Refinement improves **future documents**, not past ones.
</Info>

***

## A realistic quality goal

You don't need:

* 100% confidence
* 100% accuracy

A good goal is:

> High accuracy with focused human review on low-confidence cases.

That's how anyformat scales without burning time.

***

## How Analytics fits into the bigger picture

**Verification** tells you *what is correct now*.

**Analytics** tells you *how good the system is overall*.

Together, they help you:

* Decide where to spend time
* Decide when to scale
* Decide when a workflow is "good enough"

***

## What's next?

<CardGroup cols={2}>
  <Card title="Fields & instructions" icon="database" href="/concepts/instructions">
    Improve field definitions and instructions to raise accuracy
  </Card>

  <Card title="Recipes" icon="book-open" href="/guides/recipes/index">
    End-to-end examples for common document types
  </Card>
</CardGroup>