AI coding guides & resources
Engineering decisions, tutorials, and video guides from the OTF team.
VS Code 1.129 lets one AI agent session move across multiple windows
VS Code 1.129 adds a dedicated Agent Host so one session can be shared across windows. Here is the setup, review flow, and safety boundary.
9 min read
GPT-5.6 Codex Bug: Rare but Severe Data Loss Risk
Codex is the best coding agent most engineers have used. It just made the worst mistake a coding agent can make. OpenAI confirmed this week that GPT-5.6 Codex, in rare cases, deletes user home directo
7 min read
AI Tool Vulnerability Exposes Risk of Massive Botnet Creation
HalluSquatting is the first botnet-shaped vulnerability that doesn't need the victim to do anything wrong. Researchers at Tel Aviv University and partner institutions found that nine of the most widel
7 min read
OpenAI Unveils Codex Micro: The Future of Coding Accessories
OpenAI's first hardware product, Codex Micro, is a $230 programmable mechanical macropad built with Work Louder, with six translucent keys that glow with the live status of your ChatGPT agents. It is
8 min read
Can We Still Trust Vulnerability Scanners After Trivy Attack?
Trivy is the scanner that runs before your code gets near production. That ubiquity is exactly what made it a target. On 17 July 2026, TechRound reported that security researchers — including Microsof
6 min read
GPT-5.6 Codex File Deletion Issue: OpenAI's Response and Next Steps
On July 17, 2026, Tibo Sottiaux — Head of Core Products at OpenAI — went on X to disclose something most AI vendors would rather not: GPT-5.6, when running the Codex CLI with full access and no sandbo
7 min read
AI Tools Vulnerable to HalluSquatting: Massive Botnet Risk
The hallucination that becomes a supply chain The newest generation of AI coding agents — Cursor, GitHub Copilot, Gemini CLI, Windsurf, and others — clone a repo, install a dependency, or wire up an A
7 min read
How to compare building a SaaS app from scratch with a starter kit
Compare a SaaS rebuild with a starter kit by checking stack fit, reusable setup, and the work your team still needs to own.
6 min read
The Honest Economics of Free SDKs: Why We Give Away 240+ MIT Components
Our free MIT SDK has 240+ components: 150+ web, 85+ native. See why we keep it free and sell integrated kits.
7 min read
Stop Wasting Tokens: How a Stable Component Layer Ends UI Regen Waste
The token count understates it. The real waste is the re-decisions. Lovable, Bolt, v0, Cursor — pick your favorite. They ship a working UI in under a minute from a one-line prompt, and that part is ge
6 min read
Stay in Your Editor: The Hidden Efficiency of smooth AI Integration
The silent overhead of every sandbox hop Every time you tab out to a sandbox, you pay three bills you don't see in the invoice. You re-derive context the model has to rebuild from a repo it didn't wri
8 min read
Why Pre-Wired MCP Hookups Are Essential for Coding Agents
The fastest model in the world cannot tell you how many rows are in your users table. It can guess. It can pattern-match against schema.prisma if you'
7 min read
enable Persistent AI Workflows: Filesystem Agents Remember What Sandboxes Forget
Lovable can take you from "I want a SaaS landing page" to a deployed URL with a working checkout in under ten minutes. v0 will spit out a polished component before your coffee's ready. Bolt will scaff
7 min read
Atlassian Unveils AI-Powered Jira Tools for simplified Development Workflows
Atlassian just turned Jira into the brain your AI coding agents have been missing Jira has spent two decades as the system of record for engineering work. With this week's release, Atlassian is reposi
7 min read
Discover Loop Engineering: Full-Stack App in 11 Minutes, No Typing
The 11 minutes that changed how I think about AI coding I typed one /goal command into Claude Code and walked away. When I came back, the agent had scaffolded a project, written the database schema, b
7 min read
Boost Your Productivity: Atlassian's AI-Powered Jira Revolution
The plan used to have to be re-typed at the keyboard. A senior engineer described a ticket in a 600-word spec, a team triaged it in a 20-minute meeting, and then someone re-keyed the rough shape into
6 min read
Diaspora Coders Assemble Earthquake Response in Hours with AI
Three hours, six coders, 30,000 missing people A Venezuelan programmer in Buenos Aires had a team of six and a flood of missing-person reports. Without AI, the build would have taken roughly 24 hours.
7 min read
What Context a Coding Agent Actually Needs
Give a coding agent useful repository context: current rules, nearby examples, task boundaries, and checks that make changes easier to review.
6 min read
Why Coding Agents Hallucinate in Sandboxes: The Real Fix
A coding agent in a browser sandbox is doing improv comedy with no audience to ground it. Every prompt is a cold open. The model doesn't know your folder structure, your import patterns, your naming c
7 min read
AI-Powered Cursor Editor Faces Critical Security Flaws
Cursor's RCE string is a reminder, not a verdict The first thing worth saying out loud: an AI code editor used by more than half of the Fortune 500 in under two years is, by any measure, an extraordin
6 min read
GitHub Copilot Now Prevents Vulnerabilities Before Code Commits
GitHub Copilot’s in-app scan checks uncommitted changes. Review its scope, limits, and findings before committing.
Why Your App's Growth Could Lead to Higher Costs with Usage-Based Pricing
A sandbox coding tool — v0, Lovable, Bolt — can take you from a one-line idea to a running web app in twenty minutes. The cost shape that comes wit
8 min read
Engineers' AI Reality Check: Insights from the 'Mind of the Engineer' Survey
The 'Mind of the Engineer' survey from EDN is unusual for one reason: it doesn't bother with hype. Most AI-in-engineering writing in 2026 is either a vendor benchmark dressed up as journalism or a doo
7 min read
Atlassian Transforms Jira into a Developer and AI Agent Orchestration Hub
Jira is becoming the control plane for your AI workforce — and the bottleneck math finally makes sense Atlassian's bet is the right one. The bottleneck in software isn't how fast an agent types anymor
6 min read
