Skip to main content

Testiva

Starts 28 July Every Tuesday at 8 PM PKT

AI Systems Testing Training

Six hands-on sessions covering LLM fundamentals, chatbot and RAG testing, agent observability, voice AI, note-taking apps, and AI security taught by practitioners who do this every day.

6

Sessions

1.5 hr

Per Session

100%

Hands-On

Cert

On Completion

Schedule

Starting 28 July Every Tuesday

One session per week, every Tuesday for 6 weeks. Sessions run at the same time each week.

Pakistan Standard Time

8:00 PM PKT

Pacific Time (US)

8:00 AM PT

Greenwich Mean Time

3:00 PM GMT

28th July
Tuesday

Session 1

Foundations of LLM testing

AI testing fundamentals, LLM concepts, evaluation basics

4th August
Tuesday

Session 2

Chatbot and RAG testing

Conversational testing, retrieval evaluation, hallucination detection

11th August
Tuesday

Session 3

Agent testing and observability

Agentic workflows, tool calling, tracing with LangSmith

18th August
Tuesday

Session 4

Voice agent testing

STT, VAD, TTS pipeline, dialogue flow, voice quality metrics

25th August
Tuesday

Session 5

AI note-taking application testing

Medical scribe testing, synthetic conversations, transcript quality

1st September
Tuesday

Session 6

AI security and red teaming

Prompt injection, jailbreak testing, adversarial evaluation

Who's teaching you

AI and LLM Testing Specialists
Not Theorists

Testiva is a specialist QA company with deep, hands-on expertise in AI and LLM testing. Our team has designed and executed testing strategies for production AI systems across industries from healthcare and fintech to SaaS and enterprise platforms. Every instructor has tested real AI applications in the wild, not just studied them.

15+

AI Apps Tested

LLM

Native Expertise

Red

Team Certified

UK / US

Client Delivery

Who should attend

Built for the people closest to AI quality

Designed for QA professionals and engineers who need to test AI systems with structure and confidence.

QA engineers and leads

Expand your skills into LLMs, agents, and AI pipelines.

AI engineers testing their own code

Learn structured evaluation so you're not the only reviewer.

Automation engineers

Add AI evaluation to your existing test pipelines.

Security and red team testers

Master adversarial testing and prompt injection methods.

QA managers

Understand what AI testing needs so you can plan and resource it.

Healthcare QA specialists

Validate clinical AI the highest-stakes AI environment.

Career outcomes

What this training unlocks for you

AI testing is one of the fastest-growing specialisms in the QA industry. Completing this workshop gives you skills, credentials, and positioning that are in high demand right now.

Higher earning potential

AI testing skills command significantly higher rates than traditional QA in employment and freelance markets

Verifiable credential

A Testiva certificate you can display on LinkedIn to stand out to hiring managers and clients

New job opportunities

Access AI QA Engineer, LLM Tester, and AI Red Team roles that did not exist 2 years ago

Freelance & consulting

Offer AI testing audits and evaluations as a premium service to startups and product teams

Curriculum

6 sessions
From Fundamentals To AI Security

Each session is one focused hour with learning objectives, structured topics, and a hands-on exercise.

Session 1 · Tue 28 Jul · 8 PM PKT

Foundations of LLM testing
PromptfooDeepEval
Learning objectives
  • Understand how AI systems differ from traditional software.
  • Learn why conventional testing approaches are insufficient for LLMs
  • Understand evaluation fundamentals
Topics
  • AI Testing Fundamentals
  • AI/ML and LLM Concepts
  • Traditional QA vs AI QA
  • LLM Application Architecture
  • Evaluation Fundamentals
  • Evaluation Metrics
  • Common LLM Failure Modes
  • AI Testing Lifecycle and Evaluation Workflow
  • Promptfoo and DeepEval Overview

Create first LLM test suite and run basic evaluations using Promptfoo and DeepEval

Session 2 · Tue 4 Aug · 8 PM PKT

Chatbot and RAG testing
PromptfooDeepEval
Learning objectives
  • Learn systematic testing methodologies for chatbot and RAG applications
  • Understand retrieval and response evaluation
  • Build automated evaluation pipelines
Topics
  • Chatbot and RAG architecture
  • Functional and conversational testing
  • Context and memory validation
  • Retrieval evaluation
  • Generation evaluation
  • Hallucination detection
  • Common RAG failure modes
  • Test dataset creation
  • Regression testing strategies

Test an internal knowledge base customer support assistant

Session 3 · Tue 11 Aug · 8 PM PKT

Agent testing and observability
LangSmithPromptfoo
Learning objectives
  • Understand agentic systems and how they behave
  • Learn observability and debugging techniques
Topics
  • Agent fundamentals
  • Tool calling validation
  • Workflow and task completion testing
  • Agent failure analysis
  • Observability and tracing

Test an AI travel planning agent with full tracing

Session 4 · Tue 18 Aug · 8 PM PKT

Voice agent testing
STT / TTSVoice AI
Learning objectives
  • Understand the complete voice AI pipeline
  • Learn voice-specific testing methodologies
Topics
  • Voice agent architecture STT, VAD, LLM, TTS
  • Speech recognition testing
  • Dialogue and conversation testing
  • Voice quality and latency
  • Voice agent evaluation metrics

Test a clinic appointment booking voice agent

Session 5 · Tue 25 Aug · 8 PM PKT

AI note-taking application testing
Medical AIPipelines
Learning objectives
  • Learn how to test AI note-taking applications such as AI medical scribes
  • Build scalable automated evaluation pipelines for real-world conversations
  • Understand scenario-based testing for speech-to-document AI systems
Topics
  • AI note-taking architecture
  • Synthetic conversation generation pipeline
  • Automated evaluation pipeline
  • Speaker attribution testing
  • Noise and multi-speaker scenario testing
  • Transcript vs note quality evaluation
  • Scenario-based regression testing

Test an AI medical scribe across realistic consultation scenarios

Session 6 · Tue 1 Sep · 8 PM PKT

AI security and red teaming
PromptfooSecurity
Learning objectives
  • Identify vulnerabilities in AI applications
  • Build systematic adversarial testing approaches
  • Red Teaming Configuration (Providers, Targets, Plugins,Strategies)
Topics
  • AI security fundamentals
  • Prompt injection testing
  • Jailbreak testing
  • Adversarial evaluation
  • Risk assessment and governance
  • Domain Specified Plugins
  • Promptfoo red teaming report

Red team an AI assistant for vulnerabilities

Pricing & registration

Secure your seat

Select your location to see your fee, fill in your details, and the Testiva team will contact you within 24 hours with payment instructions. Your seat is confirmed once payment is received.

Course fee

Full 6-session course — all included

Full course pricing

🌍
International
All countries except Pakistan
$100
full course
🇵🇰
Pakistan
Local pricing for Pakistan participants
PKR 25,000
full course
  • All 6 live sessions (1.5 hr each)
  • Hands-on exercise every session
  • Session recordings included
  • Tool setup guidance
  • Certificate of completion

How to secure your seat

Fill the registration form

Testiva contacts you in 24 hrs

Complete your payment

Seat confirmed + link sent

Registration Form

    Team or Corporate Bookings

    Group pricing and private cohorts available for teams of 5 or more. Get in touch info@testiva.io to discuss a dedicated run for your organisation.

    FAQs

    Common questions

    All the sessions will be Online only.
    - Instructor will share his practical knowledge about the topic.
    - Questions/Answers at the end.
    - Learning Material
    - Assignment.
    No prior AI experience needed. Session 1 covers all foundational AI and LLM concepts from scratch. A background in software testing or QA is helpful but not required AI engineers testing their own code are equally welcome.
    All 6 sessions are delivered live with a Testiva instructor every Tuesday at 8 PM PKT. Recordings are shared after each session so you can revisit the content at your own pace.
    A laptop with internet access and Node.js installed. All tools Promptfoo, DeepEval, LangSmith are free or have free tiers. Full setup instructions are shared after your seat is confirmed.
    Yes, participants who attend all 6 sessions receive a Testiva AI Testing certificate, shareable on LinkedIn to showcase your skills to employers and clients.
    Yes, group bookings and private cohorts are available for teams of 5 or more. Get in touch info@testiva.io to discuss options and team pricing.