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

# Log Anything

> AI-powered universal input that routes your entries to the right Helper automatically

## What is Log Anything?

Log Anything is the AI-powered universal input on your Peanuts home screen. Using the [Unified Input](/features/unified-input) bar, just describe what you want to log — via text, voice, image, or link — and Peanuts automatically routes it to the right Helper.

<Info>
  Log Anything uses a **4-tier matching system**. Simple entries often log for **0 credits** using Affinity or Local matching. Only ambiguous inputs require AI (1 credit).
</Info>

## The 4-Tier Matching Pipeline

When you type in the Unified Input, Peanuts processes your entry through four matching tiers:

| Tier | Name         | Credits | How It Works                                          |
| ---- | ------------ | ------- | ----------------------------------------------------- |
| 1    | **Affinity** | 0 ⚡     | Matches based on your learned patterns and history    |
| 2    | **Local**    | 0 ⚡     | Pattern matching against Helper field definitions     |
| 3    | **AI**       | 1       | OpenAI analysis for complex/ambiguous inputs          |
| 4    | **Fallback** | 0       | Goes to [Shoebox](/core-concepts/shoebox) if no match |

<Tip>
  The more you use Peanuts, the smarter Affinity matching becomes. Most routine entries will log instantly for free.
</Tip>

## Instant Logs ⚡

For simple, unambiguous inputs, Peanuts can log instantly without using AI credits.

<CardGroup cols={2}>
  <Card title="Instant ⚡ (0 credits)" icon="bolt">
    * "coffee \$5"
    * "ran 3km"
    * "slept 7 hours"
  </Card>

  <Card title="Requires AI (1 credit)" icon="brain">
    * "about \$5" (ambiguous)
    * "yesterday's lunch" (time context)
    * "total for the week" (calculation)
  </Card>
</CardGroup>

When an entry is processed instantly, you'll see a confirmation with a ⚡ lightning icon. Learn more about [Instant Logs](/features/instant-logs).

## How to Use

Type directly in the **Unified Input Bar** at the bottom of your home screen. As you type, the **Context Cloud** appears showing:

* Which Helper matches your input
* Which fields will be populated
* Confidence level of the match

<CardGroup cols={2}>
  <Card title="Text" icon="keyboard">
    Type naturally: "Spent \$45 at Whole Foods on groceries"
  </Card>

  <Card title="Voice" icon="microphone">
    Tap the mic and speak your entry
  </Card>

  <Card title="Camera" icon="camera">
    Take a photo of a receipt, meal, document, or anything
  </Card>

  <Card title="Link" icon="link">
    Paste a URL to save articles, recipes, products, or web content
  </Card>
</CardGroup>

## How It Works

<Steps>
  <Step title="You start typing">
    The Context Cloud activates, showing real-time matching
  </Step>

  <Step title="Affinity check">
    Peanuts checks your learned patterns (0 credits)
  </Step>

  <Step title="Local matching">
    If no affinity match, pattern matching against Helper definitions (0 credits)
  </Step>

  <Step title="AI understanding (if needed)">
    For complex inputs, AI analyzes the content (1 credit)
  </Step>

  <Step title="Fallback to Shoebox">
    If no confident match, entry goes to [Shoebox](/core-concepts/shoebox) (0 credits)
  </Step>

  <Step title="Entry created">
    Your entry is added to the appropriate Helper with all fields filled in
  </Step>
</Steps>

## Clarification Pills

When your input could match multiple Helpers, Peanuts shows **Clarification Pills** — tappable options to disambiguate:

```
"$45 groceries" → Could be: [Expenses] [Grocery List] [Budget]
```

Tap the correct pill to route your entry. Your choice improves future Affinity matching.

## Input Types

### Text Input

Just type naturally:

* "Coffee at Starbucks \$5.50"
* "Ran 5k in 28 minutes"
* "Feeling tired today, slept badly"
* "Book recommendation: Atomic Habits"

Peanuts extracts the relevant data and routes to the matching Helper.

### Voice Input

Tap the microphone and speak:

* Works in any language Peanuts supports
* Transcription is done instantly
* Same routing as text input
* Costs **9 credits** (8 for transcription + 1 for routing)

### Image Input

Take a photo or upload from gallery:

* **Receipts** → Extracted and added to expense tracker
* **Food** → Analyzed and added to meal log
* **Documents** → Text extracted and stored
* **Products** → Identified and cataloged
* **Anything else** → AI figures out the best destination

<Tip>
  For complex documents with tables and structured data, use [Smart Scan](/features/smart-scan) instead (5 credits) for better extraction.
</Tip>

### Link Input

Paste any URL:

* **Articles** → Title, summary, and content saved
* **Recipes** → Ingredients and instructions extracted
* **Products** → Name, price, and details captured
* **Videos** → Title and description saved
* **Any webpage** → Relevant content extracted

## Shoebox Fallback

If Peanuts can't confidently match your input to any Helper:

1. Entry goes to the **[Shoebox](/core-concepts/shoebox)** (0 credits)
2. You can organize it later
3. If similar items accumulate, Peanuts suggests creating a new Helper

This ensures nothing is lost — every input is captured somewhere.

## Examples

<AccordionGroup>
  <Accordion title="Expense Tracking">
    **Input:** "Uber to airport \$35"

    **Result:** Entry added to Expense Tracker with:

    * Amount: \$35
    * Category: Transportation
    * Description: Uber to airport
    * Date: Today
  </Accordion>

  <Accordion title="Meal Logging">
    **Input:** 📷 Photo of a salad

    **Result:** Entry added to Meal Log with:

    * Meal: Lunch
    * Description: Garden salad
    * Estimated calories: \~250
    * Photo attached
  </Accordion>

  <Accordion title="Recipe Saving">
    **Input:** [https://cooking.nytimes.com/recipes/chocolate-cake](https://cooking.nytimes.com/recipes/chocolate-cake)

    **Result:** Entry added to Recipes with:

    * Title: Chocolate Cake
    * Source: NY Times Cooking
    * Ingredients: Extracted list
    * Instructions: Step-by-step
  </Accordion>

  <Accordion title="Workout Logging">
    **Input:** 🎤 "Did 30 minutes on the treadmill, felt good"

    **Result:** Entry added to Workouts with:

    * Type: Cardio - Treadmill
    * Duration: 30 minutes
    * Notes: Felt good
  </Accordion>
</AccordionGroup>

## Offline Support

Log Anything works offline with some limitations:

* **Instant Logs** ⚡ work fully offline
* **Complex entries** are queued and sync when online
* **Images and voice** require connectivity for processing

See [Offline Mode](/features/offline-mode) for details.

## Tips for Best Results

1. **Be specific** — "Coffee $4" is good, "$4" alone is ambiguous
2. **Include context** — "Lunch with clients" helps with categorization
3. **Use consistent language** — Similar inputs route the same way
4. **Take clear photos** — Good lighting helps receipt scanning
5. **Paste full URLs** — Shortened links may not scrape well
6. **Use scoped input** — Tap a Helper chip first for guaranteed 0-credit logging

## Credit Usage

| Input Type | Affinity/Local Match | AI-Powered    | Fallback |
| ---------- | -------------------- | ------------- | -------- |
| Text       | 0 ⚡                  | 1             | 0        |
| Voice      | —                    | 9 (8 STT + 1) | 0        |
| Image      | —                    | 5             | 0        |
| Link       | —                    | 1-3           | 0        |

All inputs try Affinity/Local matching first. Only when those fail does AI take over.

## Related

<CardGroup cols={2}>
  <Card title="Unified Input" icon="message-lines" href="/features/unified-input">
    The home screen input experience
  </Card>

  <Card title="Instant Logs" icon="bolt" href="/features/instant-logs">
    Zero-credit logging for simple inputs
  </Card>

  <Card title="Shoebox" icon="inbox" href="/core-concepts/shoebox">
    Where unmatched content goes
  </Card>

  <Card title="Smart Scan" icon="scan" href="/features/smart-scan">
    Advanced document extraction
  </Card>
</CardGroup>