Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 7 hours
Course Outline
Best Practices and Essential Tools
Common Pitfalls and Mitigation Strategies
Introduction to Prompt Engineering
Prompt Refinement and Iterative Design
Prompting for Test Automation and SQL Generation
Summary and Next Steps
Utilising Prompts for Code Explanation and Debugging
Crafting Prompts for Code Generation
- Preventing hallucinated code or security vulnerabilities.
- Managing incomplete or ambiguous inputs.
- Establishing safe fallback prompts and guardrails.
- Deriving test cases from requirements or existing code.
- Translating natural language into structured SQL queries.
- Formatting outputs for seamless integration into test suites.
- Clarifying legacy or unfamiliar code.
- Requesting logic walkthroughs or edge case analyses.
- Identifying and explaining bugs or inefficiencies.
- Generating code from plain-language descriptions.
- Controlling output format and target programming language.
- Handling complex logic or multiple functions.
- Enhancing outcomes via prompt chaining and feedback loops.
- Error recovery and prompt tuning strategies.
- Case studies on refinement for technical tasks.
- Prompt libraries and reusable patterns.
- Applying prompt templates in VS Code or API-based workflows.
- Assessing prompt quality and performance in production environments.
- Understanding prompts, context, tokens, and models.
- Prompt types: zero-shot, one-shot, few-shot.
- Utilising system vs. user instructions across different APIs.
Requirements
Target Audience
- Developers utilising LLMs for code generation or analysis.
- Technical leads exploring AI tools within their workflows.
- Software professionals experimenting with LLM integrations.
- Practical experience in software development or scripting.
- Familiarity with standard programming languages such as Python, JavaScript, and SQL.
- Foundational knowledge of large language models and AI tools like ChatGPT, Claude, or Copilot.
Testimonials (1)
That i gained a knowledge regarding streamlit library from python and for sure i'll try to use it to improve applications in my team which are made in R shiny
