DEV Community

Cover image for Building My First Generative AI Journey with Kiro
David Kljajo
David Kljajo

Posted on

Building My First Generative AI Journey with Kiro

Originally published on Builder AWS by David Kljajo

I explored Generative AI by building real projects instead of just reading tutorials. Using Kiro, I experimented, iterated, and learned how to turn ideas into interactive outputs. This story shares my process, lessons learned, and my personal journey with screenshots along the way.

πŸš€ My Builder Journey into Generative AI

I didn’t start with a clear plan β€” I just knew I wanted to understand how Generative AI actually works beyond the hype.

At first, things were confusing. There were too many tools, too many tutorials, and a lot of theory that didn’t translate into real skills. Instead of trying to learn everything, I focused on building something small and practical. That’s when I started using Kiro.

πŸ› οΈ What I Built

Using Kiro, I explored how to:

  • Ask better prompts
  • Structure ideas into usable outputs
  • Turn concepts into something interactive

I experimented with different approaches, tested what worked, and improved step by step. It wasn’t perfect, but it was real progress.

πŸ“Έ My Process (Screenshots)

🧠 Questions I Asked Kiro

Kiro Answer 1 (Career-Focused)

Question: What is the most practical GenAI certification path in 2026 if I want to build real-world projects and not just pass exams?

Answer from Kiro:

  • Foundations (free): DeepLearning.AI, LangChain Academy
  • Pick 1 Cloud Cert: AWS AI Practitioner, Google GenAI Engineer, or Azure AI-102
  • 3 Real Projects:
    • RAG chatbot
    • AI agent with tools
    • Full-stack AI product
  • Showcase: GitHub + live demos β€” projects > certs

Kiro Answer 2 (Learning + Strategy)

Question: Design a step-by-step roadmap to become certified in Generative AI, including free resources, hands-on projects, and how to stand out to employers.

Answer from Kiro:

  1. Weeks 1-2: Learn AI basics & GenAI landscape
  2. Weeks 3-6: Core stack: Python, LangChain, OpenAI API
  3. Weeks 5-8: Build RAG chatbot
  4. Weeks 8-14: Pass cloud cert
  5. Weeks 12-20: Build AI agent + full-stack AI product
  6. Ongoing: Post projects, contribute to open source, polish GitHub & LinkedIn

🧩 The Core Philosophy

Certifications alone won't get you hired or make you effective. The winning combo is: free/cheap foundational certs + cloud cert for credibility + a portfolio of 3 deployed projects.


Phase 1 β€” Foundation (1-2 months, mostly free)

  • DeepLearning.AI short courses β€” prompt engineering, LangChain, RAG, agents. Free, practical, 1-2 hours each
  • LangChain Academy β€” free, hands-on agent building
  • Fast.ai Practical Deep Learning β€” model-level understanding
  • Tools to get comfortable with: Python, LangChain/LangGraph, OpenAI/Anthropic APIs, vector DBs (Chroma, Pinecone, Weaviate), HuggingFace

Phase 2 β€” One Cloud Cert (pick based on your target job)

Target Cert
AWS shops AWS AI Practitioner β†’ AWS ML Specialty
Google/GCP Google Cloud GenAI Engineer
Microsoft/enterprise Azure AI Engineer Associate (AI-102)
Vendor-neutral IBM AI Engineering Professional (Coursera)

Phase 3 β€” The 3 Portfolio Projects That Actually Matter

  1. RAG chatbot β€” ingest PDFs/docs, answer questions, deploy using LangChain + Chroma + frontend (Streamlit/FastAPI)
  2. AI agent with tools β€” searches web, runs code, calls APIs (LangGraph/CrewAI)
  3. Full-stack AI product β€” real use case, auth, deployed URL (AI assistant, code reviewer, domain Q&A)

Each project should have a GitHub repo, live demo, and write-up.


What to Skip

  • Generic "AI for everyone" certs with no coding
  • Paying for bootcamps before trying free resources
  • Chasing every framework β€” pick one (LangChain or LlamaIndex) and go deep

Realistic Timeline

Months Focus
1-2 DeepLearning.AI courses + first RAG project
3-4 Cloud cert prep + agent project
5-6 Full-stack project + polish portfolio + apply

Stage-by-Stage Guide

Stage 1 β€” Get Your Bearings (Weeks 1-2, free)

  • 3Blue1Brown Neural Networks series
  • DeepLearning.AI: Generative AI for Everyone
  • Read: β€œAttention Is All You Need” abstract + plain-English explainer

Stage 2 β€” Learn the Core Stack (Weeks 3-6, free)

  • DeepLearning.AI short courses
  • LangChain Academy β€” Introduction to LangGraph
  • HuggingFace free courses β€” NLP + Agents
  • Tools: Python, LangChain, OpenAI/Anthropic SDK, Chroma/FAISS, Streamlit, FastAPI, Docker basics

Stage 3 β€” First Real Project (Weeks 5-8)

  • Build a RAG chatbot with minimal stack: LangChain + Chroma + OpenAI API + Streamlit + deployed (Railway/Render free tier). Push to GitHub with README.

Stage 4 β€” Pick One Cloud Cert (Weeks 8-14)

  • AWS-heavy companies β†’ AWS Certified AI Practitioner β†’ ML Specialty
  • Google/GCP roles β†’ Google Cloud GenAI Engineer
  • Enterprise/Microsoft β†’ Azure AI Engineer Associate (AI-102)
  • Vendor-neutral β†’ IBM AI Engineering Professional (Coursera)

Stage 5 β€” Build Remaining Portfolio Projects (Weeks 12-20)

  • Project 2 β€” AI Agent with Tools (multi-step tasks, research agent, uses LangGraph/CrewAI)
  • Project 3 β€” Full-stack AI Product (real use case, auth, live URL, FastAPI + React/Next.js + Supabase + Vercel/Railway)

Stage 6 β€” Stand Out to Employers (Ongoing)

  • LinkedIn posts, dev.to/Hashnode articles for projects
  • GitHub: pinned repos, clean READMEs, live demos
  • Open source contributions
  • Resume: projects > certifications, quantify impact

Certs get you past ATS filters; your portfolio gets the interview; your ability to explain projects gets the offer.


Originally published on Builder AWS

Top comments (0)