When AI Referral Tags Disappear: An Analytics Incident Playbook
Investigate an apparent ChatGPT traffic drop with landing-page comparisons, controlled link checks and a dated incident note that preserves uncertainty.
Read Article
Library · Full Archive
AI Automation
AI Automation
Case Study Archive.
Every case study, system breakdown, and field note, newest first and filterable by topic. No theory, no demos. Only systems that run in production and what it took to get them there.
At a glance
What is in the JQ AI SYSTEMS case study archive?
This is the complete archive: all 699 posts across 62 topics, newest first, filterable by category. It holds the case studies, the model and tool comparisons, and the field notes from systems I built and run. For the curated view, where the writing sits alongside the free Claude Code skills, start at the Library instead.
The archive leans in four directions: AI Search Visibility (132), AI Agent Architecture (65), AI Tools (38), and Open Source (37). Those four account for most of what I publish, because they are where most of the client questions land.
Three places to start. The AI search visibility guide is the hub for the largest cluster and links out to every spoke in it. Grok Imagine vs Midjourney is the image model comparison, rebuilt against live leaderboard data rather than left to go stale. OutreachIQ is the longest running system breakdown here, from first prototype through to a public repo.
10 GitHub Repos: REA, HyperFrames, Ghidra and More
Andrew Warner and Adam tour ten repos for reverse engineering, coding skills, HTML video, branded diagrams, compressed context, printable CAD, SwiftUI and self-hosted fitness. Explore the demos, source links and real limits.
Read Article
AI News: Krea 3, FLUX 3, Muse Wonder and Open Models
Matt Wolfe tests Krea 3, Gemini 4 Argon and Muse Wonder, then tours FLUX 3 Klein, Qwen Image, open-weight releases and the week's agent and voice updates. Here is what actually shipped.
Read Article
AI Code Review Bottleneck: Florian Buetow's Guardrail Playbook
AI engineer Florian Buetow tests whether fast feedback, Semgrep rules, architecture tests, and agent hooks can ease code-review pressure without surrendering human ownership of software.
Read Article
Open-Source PRs That Get Reviewed: Bruno Schaatsbergen's Playbook
Terraform contributor Bruno Schaatsbergen explains why PRs stall, how to earn maintainer trust, where AI-generated contributions go wrong, and what open-source work can and cannot do for a career.
Read Article
Gemini 4 Argon for Business: Greg Isenberg's Three Builds
Greg Isenberg tests Gemini 4 Argon on an interactive brand site, a personalized 3D product customizer, and a commercial-cleaning quote app. See the workflow, six techniques, access rules, and what still needs validation.
Read Article
How to Prepare for AI Change: Security, Work, and Identity
Nick Saraev proposes three AI risk horizons: security, work and income, and identity. Check the underlying incidents and employment research, then build a calm, practical plan without treating forecasts as facts.
Read Article
Five AI Business Ideas: REA, Grok Bot, Hypit and Pixel Ads
Andrew Warner and Corey Ganim explore REA, Grok Bot plugins and voice, an agent-use-case directory, Hypit videos, and pixel ads. Here is what exists, what is speculative, and how to test one idea responsibly.
Read Article
DHH at Rails World 2026: Pencils Down, Agents, and Rails
At Rails World 2026, DHH explains why 37signals went pencils down, shows agent-built HEY experiments, makes the case for Rails conventions and app CLIs, and argues for optimism with eyes open to production risks.
Read Article
Improve the Handoff From an AI Answer to Your Landing Page
Help visitors verify the claim that brought them from an AI answer: connect the cited passage, supporting evidence, scope and next action on your page.
Read Article
Choose the Official Page for Each Customer Task
Map contact, booking, downloads and service enquiries to clear official destinations, with owners, honest labels and checks for conflicting paths.
Read Article
Coding Agents Need Architecture: Carlos Kelkboom's Rules
Carlos Kelkboom explains why he scaffolds architecture before delegating code, keeps his main agent read-only, compares parallel implementations in worktrees, and discards code he cannot explain.
Read Article
Gemini 4 Argon vs Opus 5.5: Four Builds and Real Costs
Pat Simmons gives Gemini 4 Argon, Opus 5.5, Fable 5.1, and GPT-6 Astra the same four creative builds. Compare the live results, blind rankings, time, and API-equivalent cost without mistaking them for a general benchmark.
Read Article
Bing Topic Gaps: When Should You Ignore an Opportunity?
Reject weak Bing AI opportunity queries with a service-fit check, classification review, evidence test and a clear reason to revisit deferred ideas.
Read Article
Flexible Brand Identity: Test the Limits of AI Variation
Explore AI-assisted brand variation with fixed identity decisions, deliberately varied outputs and clear approval reasons across real production formats.
Read Article
7 Open-Source Agent Tools: What They Replace and What They Don't
Andrew Warner tours seven GitHub projects for meeting notes, agent teams, memory, model routing, voice, scraping, and chat. Use the direct repos, feature limits, and a cost-aware first pilot.
Read Article
Build an Animated App With Opus 5.5: Code Motion vs Video
Jason Lee builds an animated hydration-app prototype with Claude Opus 5.5, Mobbin references, Higgsfield character clips, and an Expo tilt screen. Follow the three passes and see what the demo does not prove.
Read Article
Gemini 4 Argon Tested: Games, Bug Finding, Writing and Video
Paul J Lipsky tests Gemini 4 Argon on games, a wearable-controlled prototype, code bugs, research, a scary story, and video editing. Here is what worked, what needed help, and where access differs.
Read Article
How I Tripled Google Clicks With Claude Code: The Exact Setup
The scripts and routine behind this site's jump from 38 to 116 Google clicks a day: Search Console and GA4 in Claude Code, IndexNow, sitemap checks, and checkpoints.
Read Article
Andrew Warner's GrokBot: 10 Real Jobs, Costs and Controls
Andrew Warner shows GrokBot handling publicity, rent, invoices, sales, inboxes, contacts, and anniversary planning. See the real handoffs, extra-usage bill, privacy miss, and a safer first pilot.
Read Article
REA and AI App Copying: What Customers Still Pay For
Duncan Rogoff uses REA and ArtCraft to ask a better business question: if software is easier to imitate, why will customers stay? Separate the tool demos from the three durable offers: results, support, and trust.
Read Article
Turn Bing Topics Portfolio Into an Editorial Decision Queue
Turn Bing's Topics Portfolio beta into a small editorial queue with coverage checks, evidence requirements, review owners and practical next actions.
Read Article
Gemini 4 Argon Tested: Matt Wolfe on Coding, 3D, and Tasks
Matt Wolfe tests Gemini 4 Argon on coding, interactive physics, scheduling, and a 3D print. Compare the visible results with Google's launch claims, current access, API prices, and stalled Tasks.
Read Article
Why One AI Visibility Dashboard Can Mislead a UK Business
Read the new UK AI visibility benchmark carefully and build a platform-by-market scorecard with stable prompts, explicit denominators, and useful decisions.
Read Article
Your System Next
See something that
See something that
fits your problem?
Every post here is about a system that actually shipped. Book a free call and let's talk about what could ship for you.
Book Free 30-min Call