Skip to main content

10 articles tagged with "AI Agents"

View All Tags

· 12 min read
IntelliNode Team

Take a small software company whose product has three AI features. The website has a support chatbot, the sales team has a tool that summarizes their calls, and a job runs every night to write product descriptions. The features were built at different times, so each one calls a model provider directly, with its own API key inside its own code.

This works well until the day one provider has an outage, or starts rejecting requests because of a rate limit. The chatbot stops answering in front of customers, and the only fix is to change its code and deploy it again. Some simple questions are also hard to answer in this setup. Nobody can say how much each feature costs per month, or whether the call summaries, which are full of customer details, should be going to a cloud model at all.

An AI gateway handles all of this in one place. In this guide we build a small one in Node.js with IntelliNode. The three features send their requests to one OpenAI-compatible endpoint. The gateway picks the provider, moves to the next one when a provider fails, keeps private requests on a local model, and writes one log line per call so you can see which feature used what.

Thin lines from small dots on the left meet in one rounded gate in the middle, and three lines leave it toward round targets on the right, like apps reaching several AI models through one gateway

· 14 min read
IntelliNode Team

Think of a small e-commerce business that sells shirts, hoodies and mugs on its own website. Every Monday the owner opens the stock system, exports a spreadsheet and works out by hand what is about to sell out and how many to order from each supplier. During the week, the person answering customers keeps asking the same thing in the team chat: do we still have the grey hoodie in medium?

All of those answers already sit in the store's inventory system, behind an API. The AI assistant the team uses every day cannot see any of it.

MCP fixes that. The Model Context Protocol is an open standard that lets AI apps such as Claude, Cursor and VS Code call your systems as tools. In this guide we build an MCP server in Node.js with IntelliNode, put it in front of the inventory API, connect it to Claude Code, and then use the same server from a small Node script that drafts the Monday purchase orders.

Small round dots on the left and a grid of squares on the right, joined by thin lines through one hexagon in the middle, like AI apps reaching an inventory API through one Node.js MCP server

· 15 min read
IntelliNode Team

Picture a small dental clinic around lunchtime. The receptionist is at lunch, the dentist is with a patient, and the phone keeps ringing. One caller wants to know if the clinic takes their insurance. Another has a broken tooth and wants to come in today. A third wants to move a cleaning to Saturday. Nobody picks up, so two of them call the clinic down the road.

Most small businesses have an hour like this every day, which is a big part of why "AI receptionist" grew into one of the fastest rising searches of the year. The idea is simple. A voice agent picks up every time, deals with the easy questions on its own, books the visit, and hands anything it is unsure about to a person.

In this guide we build that agent in Python with Intelli, the Python library in IntelliNode. It answers from the clinic's own notes rather than from memory, it checks the calendar before it promises a time, and it recognizes a caller who phoned last month. You can run it on your laptop with nothing more than an OpenAI key. The real phone number comes at the end.

Soft rings spreading out from a small point, like a voice on a phone line

· 10 min read
IntelliNode Team

Your support team answers the same question all day: where is my order? The answer sits in your order system, behind an API your developers built years ago. The AI assistant your team uses can't see it, so someone copies the order number into one window and pastes the status back into another.

MCP removes that copy and paste. The Model Context Protocol is an open standard that lets AI apps such as Claude, Cursor and your own agents call your systems as tools. You put a small MCP server in front of the API you already have, and every app that speaks MCP can use it.

This guide builds one in Python with Intelli, the Python library in IntelliNode. You'll connect it to Claude Code, then reuse the same server in a flow that writes a morning brief and apology emails with nobody typing a thing.

Small dots on the left joined by thin curved lines to one hub in the middle, which links to a cluster on the right, like AI apps reaching an API through one MCP server

· 19 min read
IntelliNode Team

You run the support queue or the Friday customer update, and you know what an AI helper should do there. You don't write code. Claude Code or Codex will write it for you from one plain request.

The trouble starts when the work comes back. If you build AI agents with Claude Code or Codex, you get a few hundred lines you can't read, and you're asked to trust them.

IntelliNode changes what comes back. The agent builds the tool as a flow, a small graph of steps. It draws a picture of the graph before anything runs, then runs it and reports back in plain words. This guide starts with one example on an OpenAI or Claude key, then moves the same tool to an offline model and shows what our tests found.

Clusters of dots joined by thin curved lines, like a coding agent linking project rules, docs and agent apps

· 21 min read
IntelliNode Team

A small SaaS team bumps a dependency on Monday morning and 14 tests go red. Nothing is seriously broken. A helper now rounds a little differently, and someone gives up the morning to fixes that are dull, careful and easy to get slightly wrong.

That morning is a good job for an AI coding agent that fixes failing tests. It takes the first pass while the team does something else, but only if "done" means the tests really pass and a person still approves the merge. An agent that says it's finished, or quietly edits the tests until they agree, costs more time than it saves.

By the end of this guide you'll have a short Node.js script that fixes a failing test, refuses to stop early, can't rewrite your tests, and opens a pull request for someone to review. It runs on a cloud model or on your own machine.

Loose shapes settling into an ordered grid, like a coding agent turning failing tests into passing ones

· 23 min read
IntelliNode Team

Picture an online store with a small support team. Much of the inbox is some version of "where is my order", and every answer means opening the order system and copying a status into a reply. You've used ChatGPT, maybe called an AI API once, and now the team wants an agent to take that first pass.

This guide shows you how to build AI agents in Node.js by building that one, a piece at a time. By the end it looks orders up by itself, asks a person before it gives money back, and keeps answering when an AI service goes down. You start on your laptop with no API key and move to a hosted model when you're ready.

We ran every example on a deliberately tiny model and show you where it got things wrong. Those mistakes are much cheaper to meet here than in front of a customer.

Blue hub with thin spokes to round and square endpoints, like one Node.js AI agent wired to many tools

· 21 min read
IntelliNode Team

Most teams build their first agentic workflow in Python almost by accident. A script sends support tickets to a model, the demo sorts twenty of them nicely, and then the real queue shows up. Soon one prompt has become five jobs: read the ticket, pull out the facts, spot customers who might leave, draft a reply, and have someone check it before it goes out.

Now the hard part is the wiring, not the prompt: what runs first, what can run side by side, what happens when a step breaks, and what it all costs each month. It's tempting to grab the biggest framework you've heard of. Often you don't need it.

This guide builds the few shapes that nearly every multi-step AI process takes, from ticket triage to content work to research briefs, in short readable code. Then it helps you decide whether a lighter tool can carry your process or a heavier framework is worth the weight.

Blue and lavender ribbons crossing and merging from left to right, like steps in an agentic workflow

· 19 min read
IntelliNode Team

Picture the support inbox at an online retailer on a Monday morning. Ticket after ticket asks the same thing: where is my order? Each one means a rep checks the order, then the carrier, then types a reply.

A plain chatbot can't help. It doesn't know your orders, so it guesses. An AI agent can look things up on its own and hand anything risky to a person. This guide shows how to build an AI agent in Python for that job, without a big framework.

You'll start with the idea, write the agent in one file, run it on a hosted model and on a free one on your laptop, then add the checks you'd want before customers see it. Along the way, a tiny local model shows where things quietly go wrong.

Blue core circled by orbit rings and small bodies, showing a Python AI agent loop that calls tools and returns

· 4 min read
IntelliNode Team

Updated in October 2026. An earlier version of this article walked through the IntelliCloud app, which has since been retired. Everything it did now runs in the open source libraries, Intelli for Python and IntelliNode for Node.js.

Most teams don't start by looking for an AI framework. They start with a job that eats hours every week: answering the same customer questions, reading invoices, writing product copy, or arguing about which of three models is the best.

This article goes through six of those jobs. For each one you'll see what IntelliNode does and where to find working code, so you can pick the one closest to your own problem and start there.

A bento grid of rounded tiles in different sizes, each holding one small mark, like many jobs on one framework