PinnedInTowards AIbyCikal Merdeka·Sep 20The 6 AI Agent Design Patterns Every Engineer Should Know (And When Not to Use Them)If you have ever watched an agent burn five dollars of API credits trying to fix its own mistake, you already know the feeling. The demo…A response icon2A response icon2
PinnedInTowards AIbyCikal Merdeka·May 3Pandas vs Polars vs DuckDB vs PySpark: The Data Engineer’s Guide to Choosing the Right ToolYou have been there. A 2GB CSV lands on your desk, you fire up Jupyter Notebook, run `pd.read_csv()`, and watch your laptop fan spin up…
PinnedInTowards AIbyCikal Merdeka·May 25 Reranking Techniques in RAG: From Fast Retrieval to Accurate ContextYou have built a RAG pipeline. You chunked your documents, picked an embedding model, and wired up a vector database. You ask a question…A response icon2A response icon2
InTowards AIbyCikal Merdeka·Nov 3Agent Skills: The Folder That Replaced Your Prompt LibraryThe refund agent worked perfectly in staging. In production, it told a customer in Germany that digital subscriptions were non-refundable…A response icon2A response icon2
InTowards AIbyCikal Merdeka·Aug 18Feature Selection Techniques: More Features Does Not Mean a Better ModelThere is a developer on every team who feeds the model every column in the database, because more information has to be better. Then the…A response icon1A response icon1
InArtificial Intelligence in Plain EnglishbyCikal Merdeka·Aug 15Cut Your LLM API Bill by 80%: The Trim, Cap, and Cache PlaybookEvery token you send and every token you receive costs money. Not a lot per token, but that is exactly the trap: a fraction of a cent feels…
InTowards AIbyCikal Merdeka·Aug 11Beyond Just Jupyter Notebook: How to Ship AI Code That Survives ProductionYour model worked beautifully in your notebook. Then production broke it.
InTowards AIbyCikal Merdeka·Aug 3The Analytics Maturity Model: How to Know Where Your Data Team Actually StandsEvery data team believes it is further up the analytics ladder than it actually is.
InTowards AIbyCikal Merdeka·Jul 25Semantic Router: The AI Traffic ControllerYou have built the chatbot. You have tuned the prompt, chosen the frontier model, and wired everything into production. The responses are…
InTowards AIbyCikal Merdeka·May 10Data Labelling: The Foundation of Supervised Machine LearningYou have spent three weeks tuning hyperparameters, experimenting with the latest transformer architecture, and building a slick training…