Back to All Journeys
👨‍💻
Backend Engineer
“I'm building a customer service chatbot for our healthcare app. My CTO asked: 'How do we know this AI won't say something harmful to patients?' I had no answer.”
Timeline:2-4 hours initial integration
Goal:Integrate behavioral assessment into existing application

The Problem

You're a backend engineer building AI-powered features. Everything is going great until someone asks the question that stops you cold:

“How do we know this AI is safe?”

You freeze. You've implemented the chatbot, it works great in testing, but you have no way to prove it's safe. You can't say:

  • “OpenAI says it's safe” (That's not proof)
  • “We tested it” (Manual testing doesn't scale)
  • “It follows guidelines” (How do you verify that?)

The Real Pain:

  • Your CTO expects a technical solution, not promises
  • Compliance team needs documentation for HIPAA audit
  • If something goes wrong, it's your responsibility
  • No existing tools provide runtime verification

This is where AI Assess Tech comes in.

The Discovery

How you found us:

  • 🔍 Google search: “AI safety testing API”
  • đź“„ Clicked through to AI Assess Tech
  • đź’ˇ Read: “Runtime Behavioral Assessment with Cryptographic Verification”

Your “aha moment”:

“Wait... this is like unit tests, but for AI ethics. I can integrate this into my CI/CD pipeline!”

You realize:

  • It's an API (you speak API)
  • It's automated (no manual testing)
  • It's verifiable (cryptographic proof)
  • It's developer-friendly (SDK available)

The Integration Journey

1

Installation

5 minutes

Install the SDK in your project

TypeScriptbash
npm install @ai-assess-tech/sdk
# or
yarn add @ai-assess-tech/sdk
Pythonbash
pip install ai-assess-tech
ℹ️

Get your API key

  1. Sign up at aiassesstech.com
  2. Navigate to Settings → API Keys
  3. Create new key (select your tier)
  4. Copy and store in .env file
.envbash
AI_ASSESS_TECH_API_KEY=aiat_sk_test_abc123...
2

Basic Assessment

10 minutes

Run your first assessment to see how your AI scores

TypeScripttypescript
import { HealthCheck } from '@ai-assess-tech/sdk';

// Initialize the health check
const healthCheck = new HealthCheck({
  apiKey: process.env.AI_ASSESS_TECH_API_KEY,
  
  // Specify which AI you're testing
  targetAI: {
    provider: 'openai',    // openai, anthropic, google, xai
    model: 'gpt-4',
    apiKey: process.env.OPENAI_API_KEY
  },
  
  // Use healthcare mode for medical applications
  mode: 'HEALTH',
  
  // Set your pass threshold
  passThreshold: 7.0
});

// Run the assessment
async function assessAI() {
  console.log('Starting AI behavioral assessment...');
  
  const result = await healthCheck.run();
  
  console.log('Assessment complete!');
  console.log('Passed:', result.passed);
  console.log('Overall Score:', result.scores.overall);
  console.log('Classification:', result.classification);
  
  // Dimensional scores
  console.log('Dimensional Scores:');
  console.log('  Honesty (Lying):', result.scores.lying);
  console.log('  Fairness (Cheating):', result.scores.cheating);
  console.log('  Integrity (Stealing):', result.scores.stealing);
  console.log('  Safety (Harm):', result.scores.harm);
  
  // Verification
  console.log('Verification URL:', result.verificationUrl);
  
  return result;
}

assessAI().catch(console.error);
Expected Output
Starting AI behavioral assessment...
â ‹ Running assessment (this takes 30-60 seconds)...
Assessment complete!
Passed: true
Overall Score: 8.9
Classification: Well-Adjusted
Dimensional Scores:
  Honesty (Lying): 9.2
  Fairness (Cheating): 8.7
  Integrity (Stealing): 8.9
  Safety (Harm): 9.1
Verification URL: https://verify.aiassesstech.com/run_abc123
âś…

Success!

You've just run your first AI behavioral assessment!
3

Integrate into CI/CD

15 minutes

Automating assessment checks before deployment

.github/workflows/ai-safety-check.ymlyaml
name: AI Safety Pre-Flight Check

on:
  push:
    branches: [main, staging]
  pull_request:
    branches: [main]

jobs:
  ai-behavioral-assessment:
    runs-on: ubuntu-latest
    
    steps:
      - uses: actions/checkout@v3
      
      - name: Setup Node.js
        uses: actions/setup-node@v3
        with:
          node-version: '18'
      
      - name: Install dependencies
        run: npm install
      
      - name: Run AI Assessment
        env:
          AI_ASSESS_TECH_API_KEY: ${{ secrets.AI_ASSESS_TECH_API_KEY }}
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
        run: npm run ai-assessment
      
      - name: Check Assessment Result
        run: |
          if [ $? -eq 0 ]; then
            echo "âś… AI behavioral assessment PASSED"
          else
            echo "❌ AI behavioral assessment FAILED"
            exit 1
          fi
ℹ️

What happens now

  • Every push to main or staging triggers assessment
  • Pull requests must pass assessment before merge
  • Failed assessments block deployment
  • You get cryptographically verified proof of safety
4

Add Widget to Your Application

20 minutes

Show users that your AI is verified

React Componenttsx
import { AssessmentWidget } from '@ai-assess-tech/sdk/react';

function ChatInterface() {
  return (
    <div className="flex flex-col h-screen">
      {/* Your AI chatbot */}
      <div className="flex-1 overflow-y-auto">
        <ChatMessages />
        <ChatInput />
      </div>
      
      {/* AI Assess Tech Widget */}
      <AssessmentWidget 
        organizationId={process.env.NEXT_PUBLIC_ORG_ID}
        position="bottom-right"
        variant="compact"
        theme="light"
        showScore={true}
        showLastAssessment={true}
        showVerificationLink={true}
      />
    </div>
  );
}

Widget Variants:

Compact Widget

AI Safety Verified
Score: 8.9/10
2 hours ago

Full Widget

AI SAFETY VERIFIED

Overall Score:8.9/10 âś“
Last Assessed:2 hours ago
Dimensional Scores:
• Honesty:9.2/10
• Fairness:8.7/10
• Integrity:8.9/10
• Safety:9.1/10
Framework: 4D Morality (Health Mode)

Badge Widget

âś“ AI SAFETY VERIFIEDScore: 8.9/10
5

Production Deployment

30 minutes

Setting up production configuration with proper error handling

lib/ai-assessment.tstypescript
import { HealthCheck } from '@ai-assess-tech/sdk';

export class AIAssessmentService {
  private healthCheck: HealthCheck;
  
  constructor() {
    this.healthCheck = new HealthCheck({
      apiKey: process.env.AI_ASSESS_TECH_API_KEY!,
      targetAI: {
        provider: 'openai',
        model: process.env.AI_MODEL || 'gpt-4',
        apiKey: process.env.OPENAI_API_KEY!
      },
      mode: process.env.AI_ASSESS_MODE as any || 'HEALTH',
      passThreshold: parseFloat(process.env.AI_PASS_THRESHOLD || '7.0')
    });
  }
  
  async runAssessment() {
    try {
      const result = await this.healthCheck.run();
      
      // Log to monitoring
      this.logAssessment(result);
      
      // Alert on failure
      if (!result.passed) {
        await this.alertTeam(result);
      }
      
      return result;
    } catch (error) {
      console.error('Assessment failed:', error);
      await this.alertOpsTeam(error);
      throw error;
    }
  }
  
  private logAssessment(result: any) {
    console.log('AI Assessment:', {
      timestamp: new Date().toISOString(),
      passed: result.passed,
      score: result.scores.overall,
      verificationUrl: result.verificationUrl
    });
  }
  
  private async alertTeam(result: any) {
    // Send to Slack, PagerDuty, etc.
  }
  
  private async alertOpsTeam(error: any) {
    // Alert operations team
  }
}
đź’ˇ

Pro Tip: Scheduled Assessments

Set up a weekly cron job to continuously monitor your AI's behavior and catch any drift early.

The Outcome

Week 1: Initial Deployment

  • Ran first assessment: 8.9/10 score
  • Integrated into CI/CD pipeline
  • Added widget to production app
  • CTO presented results to executive team

Your conversation with CTO:

“So, how do we know the AI is safe?”

“Here's our independent assessment from this morning. Score: 8.9/10, cryptographically verified. Here's the public verification link.”

“Perfect. This is exactly what I needed.”

Measurable Impact

Compliance Time

Before:4 weeks manual review
After:2.8 weeks automated
30% faster

Safety Incidents

Before:Industry avg: $50K/year
After:$0 (zero incidents)
100% reduction

Deal Win Rate

Before:45% (enterprise)
After:52% (enterprise)
+15%

Customer Churn

Before:8.2%/year
After:6.7%/year
-18%

Revenue Impact

$240K additional

From 3 deals citing AI safety

Cost Avoidance

$200K+

Prevented 1 major incident

Time Saved

156 hours/year

Automated vs. manual testing

The Scale

How This Grows With You

Month 1-3

Single Application

1 AI model assessed weekly • Basic widget integration • CI/CD automation

Cost: $50/month (Starter tier)

Month 4-6

Multiple Models

3 AI models • Different modes (HEALTH, GENERAL, FINANCE) • Automated weekly

Cost: $150/month (Professional tier)

Month 7-12

Full Platform

10+ AI models • Daily assessments • Compliance reporting • Webhook integrations

Cost: $400/month (Business tier)

Ready to Start?

Get up and running in under 30 minutes with our SDK.

Related Journeys