Home workspace, essays, projects, and operating-layer notes.

Essays, workflow notes, and operating-system writing.

Resource guides, practical notes, and learning references.

Interactive guides, live tools, and project artifacts.

Topical focus areas connecting essays, projects, and resources.

About Bob Z, the site, and the operating-system framing.

Contact details and ways to reach out.

Newsletter sign-up and updates.

Loophole is not interesting because it solves ethics. It is interesting because it treats moral principles like something you can draft, attack, patch, and escalate until the real conflicts in your values finally surface.

Attio, Linear, and PostHog are converging on the same product bet: one fixed dashboard cannot serve every user or every intent, so the SaaS homepage is shifting toward an agentic entry point. Chat is the router. Generative UI is what comes next.

The next real step for agents is not just more subagents inside one product. It is genuine multi-agent runtime across different harnesses, using paired review loops, handoffs, shared threads, and open protocols such as A2A.

As of March 24, 2026, the biggest divide in mobile AI coding is not provider branding. It is whether your phone is steering a session running on your own machine or watching cloud agents work somewhere else.

Claude Code autonomy is not one trick. It starts with permission friction and context hygiene, then moves through subagents and loop hooks, and becomes genuinely useful when the system can measure whether the last iteration actually improved the work.

The newest memory systems do not make language models inherently stateful. They build recall, updates, and temporal reasoning around the model instead. Gemini Embedding 2 is the first mass-scale vector embedding that is multimodal.

The most useful way to understand AI progress isn't by tracking model names. It's by tracking the operating model: from chatbots that only talk to systems that can plan, act, coordinate, and increasingly sit across software.

AI can speed up individual tasks, but that does not automatically create more free time. From personal experience, the saved capacity gets filled by more complex tasks and higher expectations.

I write, build, and teach around AI, learning, and digital work.

A public interactive explainer showing how modern agent memory systems layer extraction, versioning, multimodal recall, and source grounding around stateless models.

A public interactive grimoire exploring AI through ritual, agency, memory, and dependence across twelve short chapters.

A public interactive map tracking major AI data center projects, locations, investment, and planned capacity.

A compact checklist for deciding whether an AI output is actually usable.

The small set of models and tools I use regularly.

Working notes on how to move from prompt to draft to review without losing clarity.

Essays, resources, and experiments on where AI is going and how to use it.

A public interactive guide to Claude Code, covering slash commands, memory, skills, hooks, MCP servers, subagents, and workflow patterns.

Email for thoughtful AI, project, speaking, or advisory enquiries.

A public interactive guide to the five levels of Claude Code autonomy, from permission friction through subagents and loop hooks to evaluation-driven improvement.

The main things I work on here: AI, learning, and projects, plus how the site is organised.

A public interactive guide to agent-to-agent communication patterns, covering paired review, typed handoffs, shared threads, swarm routing, and the A2A protocol.

A public interactive explainer for Loophole, Brendan Hogan's adversarial moral-legal code system for drafting, attacking, patching, and escalating edge cases in your own principles.

A public interactive guide to the split between local supervision, self-hosted mobile bridges, and cloud autonomy in mobile AI coding.

Email updates on new writing, experiments, and AI notes from the site.

Smaller builds, tools, artifacts, and prototypes linked to the ideas on the site.

References, tool notes, workflow pages, and reusable materials connected to the rest of the site.

A public interactive companion to The SaaS Homepage Is Becoming an Agent, tracing the shift from dashboard-first software to chat-first entry points and then to generated interfaces.

A public month-by-month timeline of AI breakthroughs, model launches, and industry shifts from GPT-3 to the agent era.

A public interactive timeline and story view tracing the evolution of large language models from Transformer to reasoning agents.

A public interactive guide to how AI evolved from chatbots into agentic systems, orchestrators, and software that behaves more like an operating system.

Bob Z

Join

AI Evaluation Checklist

AI Evaluation Checklist

A compact checklist for deciding whether an AI output is actually usable.

Before keeping an AI output, check:

is it accurate enough to trust
is it structured in the right way for the task
does it sound like something you would actually publish or use
are there hidden assumptions that need to be made explicit
did it save time, or just create another layer to clean up

If the answer to the last question is no, the workflow still needs work.

What this checklist is for

This page is meant to stop "looks plausible" from becoming "good enough". Most AI failures are not dramatic hallucinations. They are subtler: weak structure, hidden assumptions, shallow verification, or outputs that technically exist but still increase cleanup work.

How to use it

Use the checklist near the end of the workflow, not at the prompt-writing stage. It works best when you already have a draft, summary, plan, or analysis in front of you and need to decide whether it should be trusted, revised, or discarded.