Codersarts Blog.

Introduction Writing product page copy is a task most developers outsource to a human copywriter or a single prompt. Neither approach demonstrates what a multi-agent system can do differently: break the task into focused, independent specialists, run them in parallel, and recombine their output into something no single prompt would produce as reliably. In this tutorial we build a product page copy generator using Google’s open-source Agent Development Kit (ADK). You provide a

Introduction Most browser-automation agent tutorials demo a narrow, single-purpose task and stop there, the agent finds one type of result on one type of site, and the tutorial never has to confront what happens when the page it’s scraping changes shape, or when the search engine itself starts treating the request as a bot. In this tutorial we build a real-time news research agent using GLM-5-Turbo, a tool-calling model from Z.AI, paired with a real Playwright-driven Chromium

Introduction Most “AI memory” tutorials show a single isolated call: add one fact, search for it, print the result. They rarely show a real conversational agent deciding for itself, turn by turn, whether something the user just said should be written to memory, recalled from memory, or neither. In this tutorial we build a reading companion using Supermemory, a hosted memory API, paired with the OpenAI Agents SDK. You chat with it the way you’d chat with a tutor: tell it what

Introduction Most “run this model locally” tutorials stop the moment the model produces any output at all. They download a file, start a server, send one test prompt, and call it done. They rarely cover what happens when that output is technically present but practically useless, because the model spent its entire response budget thinking instead of answering. In this tutorial we build a local writing assistant on top of Bonsai, PrismML’s 1-bit quantized language model, serve

Introduction Most “build an AI agent” tutorials show the happy path: write a skill, register it, call it, done. What they skip is the part where the agent confidently does the wrong thing anyway, in a different way every single time you try again, and you have to figure out why. This tutorial is the version that doesn’t skip that part. We build a customer feedback analyzer using OpenClaw, an orchestration layer that dispatches commands to registered skills, paired with OpenAI

Introduction Most LLM evaluation tutorials check whether a generated answer “sounds right” by asking another LLM to grade it. That works for tone and style, but it falls apart for tasks with an objectively correct answer. SQL generation is exactly that kind of task: a query either returns the right rows or it does not, and no amount of LLM-rubric grading can substitute for actually running the query. In this tutorial we build a promptfoo evaluation for a natural language to S

Business teams sit on huge tables of orders, sales, and profit, yet answering a simple question like “which market is most profitable?” usually means waiting on an analyst or building another pivot table. The gap between having the data and understanding it is where decisions slow down. Chat With Your Data closes that gap. It is a conversational analytics dashboard that pairs interactive charts with an AI assistant, so anyone can explore the numbers by clicking or simply by a

Introduction Content moderation at scale is one of the most operationally demanding problems in AI applications. Rule-based filters miss context and produce too many false positives. Fully manual review does not scale. A large language model can read text the way a human moderator would, understanding tone, context, and intent, and produce structured output that downstream systems can act on automatically. In this tutorial we build a FastAPI content moderation API that passes

Introduction Retrieval-Augmented Generation (RAG) pipelines are widely used to build question-answering systems grounded in private or domain-specific documents. But evaluating whether a RAG pipeline is actually working well is harder than building it. Traditional metrics like BLEU and ROUGE measure surface-level word overlap and miss the semantic quality of answers. Human review is accurate but expensive and slow at any meaningful scale. LLM-as-a-Judge sits between these two

Introduction NVIDIA Nemotron-3 is a family of open models built for reasoning, coding, chat, and agentic workflows. The Nano variant packs strong language understanding into a 4-billion-parameter model that can be fine-tuned on a single 24GB GPU, making it practical for teams who want to adapt a capable base model to their own domain without renting a large training cluster. In this tutorial, we fine-tune Nemotron-3-Nano-4B on a customer support dataset. After training, the m

Introduction Most AI tutorials show you a text box. You type, the model replies, and the whole exchange stays on screen. That covers the mechanics of calling an LLM, but it leaves out what makes voice AI feel genuinely different: the question comes from a microphone, the answer comes back as speech, and the whole thing happens without touching a keyboard. This tutorial builds a working voice AI agent from scratch in Python. Press Enter to start recording, speak your question,

Every AI team building a product in 2026 eventually hits the same wall. The model works. The demo is good. Investors are happy. And then someone asks the question that changes everything: "How do we know it's actually getting better?" Or worse — six months later: "Why did it get worse after the last fine-tune?" This is the moment a team discovers that building an LLM product and doing LLM research engineering are two different disciplines, staffed by two different kinds of pe

Introduction Before you build agents that use tools, remember conversations, or talk to other agents, it helps to start with the simplest possible thing an LLM app can do: take some text in, send it to a model with clear instructions, and return a useful result. In this tutorial, we build a Text Summarizer and Explainer, a terminal application that takes any block of text and processes it in one of three ways: a short summary, a plain language explanation, or a bulleted list

Introduction Most AI chatbot demos are stateless: every message you send is treated as the first. The model has no idea what you said three turns ago, cannot refer back to details you shared earlier, and cannot build a coherent conversation over time. This is the biggest gap between a demo and a real chatbot. In this tutorial, we fix that. We build an AI Chatbot with Memory that maintains the full conversation history across every turn, passes it to the model on each request,

You shipped the demo. It looked great. The retrieval worked. The model responded fluently. The investors nodded. The Slack channel celebrated. Then you deployed to production. Within 30 days, your support queue filled with complaints. The model was confidently wrong. It hallucinated facts that were nowhere in your documents. It ignored your output format half the time. It worked fine on the test queries and broke on real user inputs. Your inference bill was 3x the estimate. A

If you are building an LLM-powered product in 2026, writing code or integrating an API is the easy part. The hard part is everything that comes after: How do you know your model actually works on your domain? How do you prove it improved after fine-tuning? How do you stop it from hallucinating in production? How do you align its behavior to what your users expect? These are not product questions. They are LLM training research questions — and most engineering teams do not hav

Introduction Understanding how people feel about a product, a service, or an idea is one of the most valuable things a business can do, and it is also one of the tasks where AI consistently outperforms rule-based approaches. A single review can carry joy, frustration, and sarcasm all at once. A rules-based keyword matcher misses this nuance. An LLM does not. In this tutorial, we build a Sentiment Analysis Agent. It is a terminal application that takes any text input, sends it

Introduction Most AI assistants are good at answering questions but poor at remembering what you asked them to do yesterday. They have no persistent state across conversations — every session starts fresh. The Model Context Protocol (MCP) solves this by letting you build external tools that Claude (or any MCP-compatible host) can call during a conversation, with results persisted wherever you choose. In this tutorial, we build an MCP To-Do List Manager — a local server that g

Introduction Most AI email tools work as a single prompt: paste your draft, get a rewrite. The problem is that rewriting well requires two very different cognitive tasks — understanding what is wrong with the email, and then knowing how to fix it. Combining both into one prompt produces mediocre results for the same reason that asking a single person to be both a critic and a writer at the same time produces weak output. In this tutorial, we build an A2A Multi-Agent Email Dra

Introduction Not every piece of text needs the most powerful language model to check it. A short sentence with a grammar error can be caught by a fast, cheap model in under a second. Only long, complex writing with structural and coherence problems genuinely benefits from the most capable model available. Tiered model routing applies this logic systematically. Short to medium text (up to 100 words) goes to GPT-4o-mini for grammar and clarity. If it detects structural or coher