Codersarts Blog.

Notes from my conversation with Ishwar, Engineering Lead at JPMorgan Chase, on reliability, cost, security and the future of AI-assisted engineering. Getting an AI feature to work in a demo takes an afternoon. Getting customers, engineers and stakeholders to trust it in production is a different engineering problem. Most teams find this out the hard way. The prototype impresses everyone, then the real problems show up: token bills that grow every month, answers nobody can ver

Sooner or later, an AI system says something false to a real customer. It sounds confident, it looks official, and it was never in any of your documents. The first reaction is usually to blame the model. That is rarely the whole story. Hallucinations that reach customers almost always pass through several weak points: a missing document, a search that returned the wrong passage, a prompt that rewards guessing, and no check before the answer went out. This blog explains how to

The Model Context Protocol makes it easy to connect AI assistants to company systems, and that ease is exactly why security needs attention early. An MCP server can expose databases, files, tickets, and actions to a model that reads untrusted text and sometimes follows it. If the server is open, over-permissioned, or silent, one clever message can turn a helpful assistant into a data leak. This blog explains how to secure MCP servers around three controls: authentication, per

Choosing between a small language model and a frontier model is one of the most expensive decisions in a production AI project, and it is often made on reputation rather than evidence. Frontier models are more capable on hard problems. Small models are cheaper, faster, and easier to run privately. The right choice depends on the task, and most businesses have several different tasks. This blog compares the two on five common business tasks, explains where each tends to do wel

Most enterprise AI assistants answer questions by finding the passages that look most similar to the question and handing them to a language model. That works well for lookups, but it struggles when the answer depends on how things are connected, such as which systems fail when one service goes down, or what the main themes are across thousands of documents. GraphRAG addresses this by adding a knowledge graph to retrieval, so the system can follow relationships and reason acr

An AI system that reads loan documents, summarizes customer emails, or drafts responses to account queries can save a bank thousands of hours, but only if it can be trusted with sensitive data and cannot be manipulated into doing something it should not. A secure AI banking operations workflow is the set of controls, checkpoints, and monitoring that makes that trust possible, and for banking leaders it is less about the model itself and more about everything built around it.

Picture two lawyers using AI for the same research task. The first receives a confident, well-formatted answer with five case citations and files it without checking. Two of the cases do not exist, and the lawyer ends up explaining the mistake to a judge. The second uses an assistant that finds the relevant cases in minutes, shows the exact passage behind every claim, and flags the one point it could not support. A task that once took hours takes a fraction of the time, and e

Introduction Every developer who uses an AI coding assistant hits the same wall: the assistant is brilliant for one session, then forgets everything by the next. You re-explain the stack, re-state the conventions, re-warn it about the same trap, and watch it make the same mistake it made last Tuesday. Repeating yourself to a tool that is supposed to save you time is a strange way to work. Claude Code solves this with a single file called CLAUDE.md: a markdown document that lo

Introduction Asking an LLM a question about your data usually means one of two bad options: paste the rows into the chat and hope the model does the arithmetic correctly, or write the analysis code yourself and lose the convenience of just asking. LLMs are unreliable calculators, and hand-written analysis defeats the point of a conversational assistant. In this tutorial we build a CSV data analyst using Microsoft’s AutoGen framework and OpenAI. You upload a CSV and ask a ques

Introduction Most chatbots forget everything the moment a session ends. Ask one for a book recommendation today and tomorrow it has no memory of what you already read, rated, or disliked, so it falls back to generic suggestions that ignore your actual taste. In this tutorial we build a personal book tracker using Mem0’s open-source local memory layer and the OpenAI Agents SDK. You tell it what you have read and how you felt about it, and it remembers that across every future

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 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,