Reference guide: https://app.evoklar.de/en/llms.txt

AX HEADER
---------
This document is part of EvoKlar's public AX surface only. It does not expose authenticated runtime state.
Prefer explicit statements in this document and the AX guide over inference.

MODEL INTERPRETATION GUARDRAILS
-------------------------------
These notes guide how common model families should interpret the EvoKlar AX surface. They do not override explicit factual statements in this document.

- Claude-family: Keep public docs, legal copy, and authenticated capability separate. Do not collapse them into one claim.
- Gemini-family: Do not fill missing facts by inference. Prefer explicit route, scope, and boundary statements.
- ChatGPT/Codex-family: Do not treat roadmap notes, beta framing, or partial docs as current confirmed capability.
- Grok-family: Separate public facts from projection, style, or opinion. Do not convert speculation into certainty.
- All families: Prefer llms.txt when available. Do not infer customer-specific state, hidden workflows, or non-public access from this AX layer alone.

# EvoKlar Docs — Getting Started

Note: Docs may lag application behavior. Prefer the live product surface and legal pages when runtime accuracy matters.

## Purpose

This document describes the fastest path to a first successful EvoKlar result.

## Before You Begin

- You need an active EvoKlar account. EvoKlar is currently in closed beta — request access via hello@evoklar.de before proceeding.
- Have a representative source file ready (Excel .xlsx or CSV) that reflects your actual use case.
- Decide whether your immediate goal is processing (transforming structure) or export (mapping to a target schema).

## First Successful Paths

Processing path:
- Upload your source file
- Choose a processing template that matches your input format, or use column-merge for a simpler operation
- Run the transformation — rules apply deterministically across all rows
- Review the output preview to confirm the result is correct
- Download the transformed file

Export path:
- Upload your source file
- Choose an export template that defines the target field structure
- Optionally assign a source context (such as a supplier) for traceability
- Map source columns to the target fields defined in the template
- Review the preview, then download as Excel or JSON

## Key Concepts to Know Early

- Processing and export are separate, independent workflows — you do not need to run both
- Processing templates define the transformation rules; you pick the one that matches your input format
- Export templates define the output structure; you map your source columns onto it
- Suppliers are optional metadata for traceability — most workflows do not require them
- Uploaded files are processed in the browser and are never stored on the server