Thiago-code-lab/aws-certified-ai-practitioner-brasil

Conteúdo em PT-BR para a AWS AI Practitioner (AIF-C01), com foco em fundamentos de IA/ML na AWS, serviços gerenciados (Bedrock, Sagemaker, etc.), boas práticas de governança e aplicações de negócio.

What it solves

Passing the AWS AI Practitioner (AIF-C01) certification can feel overwhelming because the exam covers many topics, from machine learning basics to generative AI on AWS. This project organises the official scope into 18 clear modules in Brazilian Portuguese, so beginners can study progressively, revise quickly, and practice with short exams and commented questions.

How it works

The repository is a structured study roadmap. You start with modules 01–05 covering AI/ML fundamentals, generative AI, foundational models, and Amazon Bedrock. Then modules 06–10 dive into SageMaker, governance, data for AI, and prompt engineering. Modules 11–15 focus on security, use cases, and integration. Finally, modules 16–18 consolidate everything with practice tests, a glossary, and extra resources. Each module has its own README file, and the project also includes cheatsheets, flashcards, and guided labs.

Who it’s for

Anyone preparing for the AWS AI Practitioner (AIF-C01) exam who prefers a free, open-source, Portuguese-language path. It is especially useful for beginners who want a linear progression from core concepts to exam-style questions, and for AWS learners looking for supplementary material to pair with paid courses or practical AWS experience.

Highlights

  • 18 structured modules that mirror the AIF-C01 exam scope
  • Covers generative AI, Amazon Bedrock, SageMaker, and responsible AI
  • Includes practice tests, commented questions, glossary, and review materials
  • Completely open source under the MIT license and written in Brazilian Portuguese
  • Provides cheatsheets, flashcards, and guided labs for hands-on revision

Related

  • Project
    SynaLinks/synalinks

    Synalinks is an open‑source Python framework that provides a Keras‑like, declarative API for building, training (via in‑context reinforcement learning), and deploying neuro‑symbolic language‑model applications such as RAGs, autonomous agents, and recursive agents. It includes an embedded sandbox for safe code execution, built‑in graph/SQL knowledge bases, multi‑model support via LiteLLM, FastAPI/FastMCP deployment, MLflow observability, and integration with coding agents through `synalinks-skills`. Licensed under Apache‑2.0.

  • Project
    llnl/OGhidra

    OGhidra is a genuine open‑source project that adds large‑language‑model assistance to the Ghidra reverse‑engineering platform. It lets users ask natural‑language questions, runs AI‑driven analysis (function renaming, malware pattern detection, report generation), and supports both local Ollama models and cloud APIs while keeping binaries private.

  • Project
    farshed/sage

    Sage is an open‑source app that lets you speak to a large language model. It combines Whisper (speech‑to‑text), any LLM you host via Ollama or a cloud provider (OpenAI, Anthropic, Deepseek, Together.ai), and a text‑to‑speech voice catalog. The whole pipeline runs locally (Docker or native) on consumer hardware, and you switch LLMs simply by editing a .env file.

  • Project
    openaccountants/openaccountants

    OpenAccountants is an open‑source, AI‑ready tax knowledge library. It stores accountant‑reviewed or source‑cited tax guides for 231 jurisdictions, generates nightly bundles, and serves them via a Python MCP server. LLMs can query the MCP endpoint to get cited, up‑to‑date tax answers, with reviewer attribution, helping reduce hallucinations in tax‑related queries.