# Automotive Log Analyzer Workflow Agent

**Use Case: Urban Pedestrian Crossing Validation**

## 1. Overview

The **AEB Functional Logs Analyzer Agent** is an AI-powered ADAS validation workflow built in Soika to automatically analyze CAN logs for Urban Pedestrian Crossing scenarios.

This agent validates whether the Automatic Emergency Braking (AEB) system behaves correctly when a pedestrian crosses in front of the vehicle.

It performs:

* CAN log parsing
* Pedestrian event identification
* Time-to-Collision (TTC) calculation
* AEB trigger validation
* Outcome classification (PASS / False Negative / False Positive)

## 2. Business Objective

 Primary Objective

Automate AEB validation for pedestrian crossing scenarios to reduce manual log analysis effort and improve safety validation accuracy.

### 2.1 Engineering Goals

* Identify pedestrian detection events
* Validate AEB braking trigger timing
* Detect safety-critical failures (False Negatives)
* Detect unnecessary braking (False Positives)
* Generate explainable engineering reports

### 2.2 Business Impact

| Area               | Value Delivered                          |
| ------------------ | ---------------------------------------- |
| Validation Time    | Reduced manual effort by 40–60%          |
| Safety             | Early detection of missed braking events |
| Compliance         | Traceable requirement validation         |
| Release Confidence | Scenario-level validation evidence       |
| Automation         | Continuous validation in CI/CD           |

### 3.Step-by-Step Validation Process

### **A. AI Agent Creation**

**Step 1**

Login with username and password in Soika Mockingjay platform

**Step 2**

Give a **Natural Language Prompt to Soika** to create a General Agent -Click on New Chat(Right Panel).

Example: “Create a Workflow Agent. The name of the agent is Automotive Functional Log Analyser Agent .The primary role is to analyze ADAS event detection (AEB, ACC, LDW) , False positive and false negative analysis, KPI evaluation (TTC, reaction time, deceleration).”

**Step 3**

Soika will start creating the agent with Agent Name and Agent ID. Soika creates a Agent :Automotive ADAS Validation Agent

### B. Flow Summary

**Let's understand each Node, Blocks, Input Parameters Step by step.**

**Flow should Start Node:**

 Entry point of the workflow. Receives trigger input

<figure><img src="/files/NERgSojl5oMmXC3G0zZ5" alt=""><figcaption></figcaption></figure>

**DOC EXTRACTOR Node** : Extract structured data from raw inputs.

**LLM Nodes**: Provide the step by step instructions the agent should follow.

<figure><img src="/files/oauDkcKQSiLWqTi8MYr2" alt=""><figcaption><p><strong>DOC EXTRACTOR NODE</strong></p></figcaption></figure>

<figure><img src="/files/warc0XVX3GucDKMIhg1f" alt=""><figcaption><p><strong>LLM NODE</strong></p></figcaption></figure>

<figure><img src="/files/mgxFnmoQqZ9aw7SenzCz" alt=""><figcaption><p><strong>LLM Node: To draft the email to be shared with all the Log analysis details</strong></p></figcaption></figure>

**PARAMTER EXTRCATOR NODE :** Extract the Params to send an email, such as To, Subject and Body

<figure><img src="/files/mcBL5rs40M6pjbDkpmnX" alt=""><figcaption><p>Extract the parameters</p></figcaption></figure>

**SEND EMAIL NODE:** Send an email with the log analysis result

<figure><img src="/files/F3DUFZPj58BGsHCrujEw" alt=""><figcaption><p>Add the Input Variables</p></figcaption></figure>

**END NODE:** The node which gives you the result

<figure><img src="/files/l43hkgN4I79ZRmcJaL8q" alt=""><figcaption><p>Add the Output Variables</p></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://soika-labs.gitbook.io/soika-mockingjay/use-cases/automotive-log-analyzer-workflow-agent.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.