AI Citations, Impressions, Clicks, and Mentions Are Not the Same Metric
Use a platform-neutral vocabulary for AI visibility reports so different denominators do not create false conclusions.
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.
GPT-6 Sol First Impressions: Faster Builds, Smarter Defaults
Peter compares GPT-6 Sol with GPT-5.6 Sol on the same max-reasoning creative builds. See the reported time, token, quality, and reasoning-effort lessons.
Read Article
Claude Opus 5.5 Review: Anthropic's New AI Workhorse
Matthew Berman reviews Claude Opus 5.5 with an Anthropic engineer. Learn why cost per task matters, which effort level to use, and when Fable 5.1 still fits.
Read Article
Claude Opus 5.5 Tested: Four Builds Against Fable 5.1 and GPT-6 Astra
Pat Simmons blind-tests Claude Opus 5.5, Fable 5.1, and GPT-6 Astra across four real builds. Compare visual quality, 3D work, gameplay, reported cost, and runtime.
Read Article
Jev Explained: The 100x Decision Model and 11 AI Updates
Jev makes typed decisions instead of writing prose. See what its 100x claim means, how four practical demos work, and the 11 other AI releases worth tracking.
Read Article
Claude Opus 5.5 vs GPT-6 Sol: Capability, Cost, and the Right Workload
Claude Opus 5.5 raises the capability ceiling while GPT-6 Sol and Luna cut the cost of routine agent work. Compare pricing, benchmarks, access, and the workloads each model fits.
Read Article
Needle Local AI: Build Private Automation Directly on Device
Needle turns natural-language requests into constrained local tool calls. Learn how it differs from Jev, what runs offline, and how to pilot it safely.
Read Article
Does Your Website Hide Important Service Copy in CSS?
Audit CSS-generated copy before a visual treatment conceals the service facts that people and search systems need.
Read Article
Video Creator Identity: The Missing Layer in AI-Search Video Strategy
Connect video authorship, visible credits, source pages, and accurate VideoObject markup without promising a rich-result outcome.
Read Article
Grok 4.7 Review: Near-Frontier Coding at a Lower Token Price
Grok 4.7 closes much of the gap on coding and agentic knowledge work. Here is what xAI claims, what independent tests show, and where the value case holds.
Read Article
Instinct AI Assistant: Start With One Job, Not Your Whole Inbox
Instinct brings a proactive AI assistant into messaging. This practical guide covers useful first jobs, connected-account risks, privacy controls, and a least-access pilot.
Read Article
The Right Way to Write With AI: Build a Personal Language Model
Nicolas Cole explains commodity, personality, and original content, then shows how approved language becomes a personal language model that AI can repeat without replacing human thinking.
Read Article
Build an AI Voice Sales Agent That Qualifies and Books Leads
Andrew Warner and Achint Singh build an outbound AI voice workflow with GrokBot, ElevenLabs, Twilio, Netlify, and Attio. Here is the architecture, setup sequence, CRM handoff, testing plan, and compliance layer.
Read Article
From Brand Archive to AI Art Direction: Make Every Visual Choice Traceable
Use approved brand history to guide AI art direction with an evidence map, explicit interpretations, constrained exploration, and human selection.
Read Article
Should a Small Expert Site Spend Time on AI Content-Payment Pilots?
Assess AI content-payment pilots through access, eligible material, observable payment events, maintenance effort, and the value of keeping content discoverable.
Read Article
Is Google Choosing Another Domain as Your Canonical? Build an Early-Warning Check
Investigate an unexpected Google-selected canonical with URL evidence, redirect and template checks, and monitoring for important business pages.
Read Article
Give Your Demo Video a Useful Evidence Page
Turn an AI demo into a useful buyer resource with setup details, limits, examples, failure cases, and a companion page that adds more than a transcript.
Read Article
7 GitHub Repos You Can Turn Into Client Services
Corey Ganim maps Firecrawl, Chatwoot, Twenty, Activepieces, HyperFrames, Formbricks, and Documenso to practical client services built around measurable outcomes.
Read Article
How to Build and Deploy a Jev-Powered App
David Ondrej builds a Jev-powered qualification form, connects the TypeSafe API, packages the app with Docker, and deploys it through Coolify on a VPS.
Read Article
Build an Animated App with Claude Fable 5.1, Seedance 2.5, and Expo
Jason Lee builds a Finch-inspired animated self-care app with Claude Fable 5.1, Higgsfield, Seedance 2.5, LottieFiles, React Native, and Expo. Follow the workflow and separate the polished prototype from production work.
Read Article
Astra for Law Beyond Chat: Building a Connected AI Workforce
Bill Hauser and Eli Gill explain why Astra for Law matters beyond chat. This guide maps legal research, firm integrations, scheduled skills, multi-model review, and human controls into a practical operating model.
Read Article
Local Directory or Direct Provider? Build the Right Google Data Workflow
Separate Google aggregator and supplier requirements, then plan accurate local-business records, feed ownership, validation, and correction workflows.
Read Article
Write an AI-Use Policy That Answers a Buyer’s Actual Questions
Build a practical AI-use policy around buyer questions, verified data handling, named reviewers, and the operational evidence behind each promise.
Read Article
Fake Jev Demos: What the Decision Model Actually Does
Steve Sewell audits viral Jev demos, explains the decision model's real boundary, and shows stronger uses in email classification, browser routing, and Agent-Native tool selection.
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