Systems | Development | Analytics | API | Testing

How to Use ChatGPT Codex in Terminal to Build Your First Tool #aicoding #iosdev #aidevelopment

You don’t need a big app idea to try Codex. A messy Downloads folder is enough. In this beginner walkthrough, you’ll ask ChatGPT to write a prompt in plain language, then paste it into Codex in Terminal to build a simple file organizer. You’ll see how to: The file names and folder contents shown are fictional examples. Your first version doesn’t have to be perfect; you can improve it with follow-up prompts.

AI Literacy Starts at the Top

AI literacy across 60,000 people starts with the C-suite. In this clip from podcast, Bethany Miles, Chief AI Officer at Advantage Solutions, shares how she built enterprise-wide AI fluency, starting with 10+ hours of hands-on executive training and a CEO coding workshop. What you'll learn in the full episode:→ Why AI literacy has to start at the top before it can scale anywhere else→ How Advantage Solutions redesigned broken processes before automating them→ What to measure beyond adoption (service excellence and time-to-complete)

Can AI Agents Safely Debug Production Node.js?

AI agents are getting remarkably good at fixing code. Give an agent a well-defined performance problem, enough runtime data, and access to the relevant codebase, and it can often trace the evidence back to a function, suggest an optimization, validate the change, and produce a useful patch. That workflow is no longer particularly difficult to imagine. In some cases, it is already practical. Production debugging, however, has never been only about fixing the code directly in front of you.

Control how much autonomy your AI testing agents have | SmartBear BearQ

Can you trust AI agents to run your tests without losing control of your release process? In this video, you’ll learn how, with SmartBear BearQ’s agentic QA system, the answer is yes, because you decide exactly how much autonomy the agents get. This enables you to adapt QA to fast-moving AI codebases, all with human oversight.

AI Is Changing How We Code - But What About the Data Behind It? | Innovation Blueprint

How is AI changing software development — and what happens when AI-generated code meets real-world data? In this clip from The Innovation Blueprint Podcast, Roman Havrylyuk from ORIL and Bob Frady, Co-Founder of PropertyLens, disscuss how AI is changing the way teams write code, work with data, and make business decisions — and why better AI capabilities don’t eliminate the need for strong engineering and data foundations.

Self-Driving Regression Testing with AI Agents | Somu Suryanarayanan

This session looks at how agentic automation can take over web and mobile regression. We start with the regression tax: the slow 3-day cycle, the manual triage, and the flaky reruns nobody trusts. We then cover why scripted suites hit a wall and make the case for handing regression to agents instead. The core of the talk is how it actually works, with Appium MCP driving mobile and Playwright MCP driving web, interpreting intent rather than hard-coded steps and adapting when the UI shifts.

Add an App With Your Coding Agent

You can now ask your coding agent to set up AppSignal in your application. Give it a prompt, let it follow the installation instructions, and watch a checklist fill in as data starts arriving. Installing AppSignal was already straightforward, but it still meant checking your environment, adding the right integration, creating an app, handling credentials, and confirming that telemetry arrived. These are useful checks, but they don't all need your attention.

4 Signs Your AI has a Context Problem, Not a Model Problem

Most AI agents can write SQL. The problem is they write it against the wrong definition of revenue, for the wrong team, using the wrong business rules, and you won't catch that in a demo. Before you evaluate a single semantic layer vendor, there are four things worth getting right first. The semantic layer market has never been more crowded. Every major analytics vendor, data platform, and BI tool now claims to have one.