AI in Software Testing
Explore AI-assisted test design, LLM evaluation, and practical approaches to testing AI-powered systems.
Who this is planned for
QA and SDET professionals exploring responsible AI-assisted testing and AI product evaluation.
Suggested starting point
Test design fundamentals and basic API testing knowledge.
Proposed curriculum
Planned topics
This outline is provisional and may change before launch.
- 01
AI-assisted test design
Generate candidate cases and review them for missing risks and incorrect assumptions.
- 02
Prompting and data safety
Context, structured outputs, sensitive data and human review.
- 03
Evaluation datasets
Representative cases, reference answers and reproducible evaluation criteria.
- 04
LLM quality checks
Hallucinations, groundedness, relevance and nondeterministic responses.
- 05
Security and robustness
Prompt injection, harmful outputs and adversarial input scenarios.
- 06
Operational evaluation
Latency, cost, regression baselines and monitoring model changes.
Skills to build
Planned learning outcomes
- Review AI-generated tests rather than treating them as authoritative.
- Define evaluation criteria and representative datasets.
- Test AI features for quality, safety and adversarial behavior.
- Explain evaluation limitations and track regressions over time.