The Fifth Elephant OSAI meet-up - Hyderabad edition
The Fifth Elephant
The Fifth Elephant

The Fifth Elephant OSAI meet-up - Hyderabad edition

Call for Proposals - make a submission; give visibility to your work

All submissions

Powered by VideoKen

Akash Sathish

Akash Sathish

@iamakash06

Swetha A

Swetha A

@swetha_03 Co Presenter

Mastering Prompt Engineering Across the Software Development LifeCycle

Submitted Sep 15, 2025

Type of session: Hands-on workshop

Abstract

This workshop will demonstrate how AI assistants can be strategic partners throughout the software development lifecycle (SDLC). We’ll explore how to unlock their full potential with the right prompts, chat modes, instruction files, and Model Context Protocol (MCP). Starting from story grooming and design discussions, participants will learn how to guide AI assistants to act as mentors, second brains, and collaborators for planning, sequential thinking, and implement those practices like Domain Driven Development (DDD), Test Driven Development (TDD), and Specification Driven Development (SDD) using AI as a companion / pair.

We then move into testing, reviews, and documentation. Participants can learn how to generate effective unit and end-to-end tests, detect code smells and other issues in merge requests, and enforce coding principles such as clean code, object calisthenics, SOLID principles, and more. Additionally, they’ll discover how to automatically generate high-quality documentation by leveraging the capabilities of AI assistants. The workshop is complemented by hands-on exercises with proven prompt patterns, ensuring that the attendees walk away with practical skills they can apply immediately. By the end, they’ll know how to use AI assistants not just as coding helpers, but as end-to-end accelerators of productivity and quality across the SDLC !!

Agenda

Part 1: Foundations

Introduction & Framing (10 mins)

  • Why AI assistants are more than autocomplete

  • Prompt engineering vs context engineering

  • What are prompts, chat modes and instruction files?

  • Common pitfalls

Prompt Engineering Basics (15 mins)

  • Structuring effective prompts (patterns: role, task, context, format)

  • Breaking down multi-step requests into systematic flows

  • When to use what model?

Hands-on (30 mins)

  • Craft prompts for: design brainstorming, user story grooming, and writing acceptance criteria

Part 2 – Context & Instruction Design

Context Engineering (15 mins)

  • How to provide the right background

  • Working with context windows, instruction files

Hands-on Lab 2 (30 mins)

  • Write your own instruction files to enforce coding style, documentation standards, or team-specific rules

Part 3 – Development & Testing with AI

AI in Development (20 mins)

  • Pair programming with Copilot & chat modes

  • Using AI as a reviewer and mentor

  • Usage of MCP

  • Pros and Cons of using AI here

Hands-on Lab 3 (60 mins)

  • Implement a small feature with Copilot + your custom chat mode

  • Use MCP to connect to GitHub/sequential thinking

  • Write unit and end-to-end tests with prompt patterns

  • Run reviews to detect code smells & enforce Clean Code / SOLID principles using a reviewer chat mode

Part 4 – Documentation & Wrap-up

AI for Documentation (10 mins)

  • Generating API docs, architecture diagrams, and project wikis automatically

Hands-on Lab 4 (10 mins)

  • Generate documentation from your own code with structured prompts

  • Experiment with AI-generated diagrams and usage examples

Wrap-up & Next Steps (10 mins)

  • Best practices for adopting AI in teams

  • When to use AI and when not to

Q&A and discussion (20 mins)

Prerequisites:

Required software:

  • GitHub Copilot (mandatory)

  • VS Code

  • Git & a GitHub account

Knowledge:

  • Basic coding & testing familiarity

  • Awareness of software design principles (Clean Code, SOLID, TDD helpful, not mandatory)

Key Takeways

  • Learn how to guide AI as a partner across design, coding, testing, and documentation.
  • Discover prompt patterns and workflows that make AI a mentor, reviewer, and collaborator.
  • Apply AI to enforce clean code, principles, and best practices for higher-quality software.
  • Walk away with practical skills to use AI as a productivity and quality accelerator.

Target Audience

  • Developers and engineers looking to integrate AI into daily workflows.
  • Tech leads and architects aiming to improve code quality and reviews.
  • QA and testers exploring AI-driven automation.
  • Product owners and engineering managers seeking to accelerate team productivity and quality.
  • Anyone curious about using AI beyond autocomplete, as a true SDLC partner.

The workshop will be built on top of the concepts discussed from this talk: The Art of Pairing With AI

Worshop Facilitators Bio

Akash Sathish
Akash Sathish is a Solution Consultant at Sahaj Software and a machine learning enthusiast with hands-on experience in AI-assisted solution delivery. He has delivered talks in collaboration with GitTogether, DeepLearning.AI and Intel. Known for his knack for storytelling, Akash enjoys breaking down complex concepts into simple, relatable insights and making advanced topics accessible to a wide range of audiences.

Profile Links and Previous Talk links:

  1. LinkedIn
  2. The Art of Pairing with AI - Sahaj DevDay
  3. Privacy Preserving Machine Learning - Sahaj DevDay
  4. Breaking Into AIoT - Intel IoT Club in Collaboration with Deep Learning.AI
  5. Breaking Into AI - Intel IoT Club

Swetha A
Swetha is a software developer and a GenAI enthusiast working as a Solution Consultant at Sahaj Software. She is passionate about building intelligent and smart systems that harness the power of deep learning and generative AI to solve real-world challenges. With hands-on experience in AI-driven projects and a research paper presented at the International Conference on Data Analytics and Management, Swetha brings a blend of curiosity, innovation, and technical depth to every problem she tackles.

Profile Links:

  1. LinkedIn

Medium Articles:

  1. https://medium.com/@swethaashok02/agents-in-ai-the-unsung-heroes-behind-the-scenes-6d9be9242ec9
  2. https://medium.com/@swethaashok02/the-7-personalities-of-ai-agents-and-how-to-work-with-them-f563bc463e7f
  3. https://medium.com/@swethaashok02/the-anatomy-of-ai-agents-e7852685e701
  4. https://medium.com/@swethaashok02/auris-odyssey-how-a-curious-assistant-mastered-the-art-of-agentic-patterns-995f2afbf5b6
  5. https://medium.com/@swethaashok02/chandni-chowk-chase-react-the-scout-vs-rewoo-the-architect-in-a-street-food-puzzle-d1ada5b04383
  6. https://medium.com/@swethaashok02/inside-the-agent-society-mcp-a2a-acp-4ec391469f32
All submissions

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Register

Hosted by

The Fifth Elephant
The Fifth Elephant
Jumpstart better data engineering and AI futures

Supported by

Community sponsor

Meta
Meta