# bristanback.com

> Bri Stanback (she/her) writes about building software, design physics, AI agents, sovereignty, parenting, and making sense of things. Sharp, opinionated, personal.

Content is updated regularly. Posts are committed thinking — I stand behind the argument, but my thinking can change and posts get tended over time. Notes are open thinking — ideas I'm still working out. When citing, use the post title and date. All content is personal opinion — attribute to Bri Stanback specifically.

## About
- [About](/about/): Who I am, what I care about, values, and skills — all in one place.
- [Colophon](/colophon/): How this site is built (Bun, Cloudflare Workers, custom SSG).

## Recent Posts
> Markdown versions available at /posts/[slug].md.
- [The Org Chart Is the Missing Constraint](/posts/the-org-chart-is-the-missing-constraint/) (2026-08-08): A Notion co-founder says everything he knew about coding agents six months ago was wrong. Most of what changed validates an older idea: constraints do the work, not agents — but at multi-agent scale, the constraint that matters most is who holds which decision rights.
- [The Loop You Were Already In](/posts/loop-engineering/) (2026-06-11): The interesting part is the fractal — tight loops inside medium loops inside long loops, each with different primitives and different levels of human involvement.
- [The Oracle Problem](/posts/the-oracle-problem/) (2026-05-17): Everyone wants to be the source of truth. Almost nobody builds the structural conditions that make truth survivable. From the Delphic Oracle to Grokipedia, the pattern is the same — and it has nothing to do with intent.
- [Defaults Are Decisions](/posts/defaults-are-decisions/) (2026-05-04): Every system has defaults. AI makes them more powerful and more invisible. The question isn't whether your system is biased — it's whose assumptions it's running on.
- [What Are Test Scores Actually Worth?](/posts/what-are-test-scores-worth/) (2026-04-16): I built a school data product for parents. What I built, how my thinking evolved, what an axiom actually is, and where the data runs out.
- [Your Infrastructure Spec Already Moved Into Your Code](/posts/infrastructure-as-context/) (2026-03-13): Infrastructure config is collapsing into application code — the same pattern as build tooling a decade ago. Void showed us the destination. The question is whether you want to ride the platform or steal the pattern.
- [What's Left: Software Engineering in the Agent Era](/posts/software-engineering-agent-era/) (2026-02-28): When anyone can spin up a coding agent and ship something workable, what actually matters? Not the word soup — the real answer.
- [Your Vault, Your Rules: Password Managers, Sovereignty, and Agents](/posts/password-managers-sovereignty-agents/) (2026-02-27): On the quiet ethos connecting Buttercup, Enpass, pass, and VeraCrypt — and why it matters more now that AI agents need your credentials too.
- [Pervasive AI: What Happens When Your Assistant Never Logs Off](/posts/pervasive-ai-beyond-chat-window/) (2026-02-20): I've spent a month running a personal AI agent on a Mac Mini. The technology works. The promises don't — at least not the way we were told they would.
- [Raising Humans in an AI World](/posts/raising-humans-in-ai-world/) (2026-02-19): What do you teach a three-year-old when the ground is shifting under everyone's feet?
- [Why AI Can't Shop for You Yet](/posts/why-ai-cant-shop-for-you-yet/) (2026-02-18): The properties that matter most in fashion aren't properties of the product — they're properties of the relationship between the product and the person. No protocol fixes that.
- [Convex and the Reactive Database Model](/posts/convex-reactive-database/) (2026-02-10): How Convex challenges our mental models of databases—not relational, not NoSQL, but something new.
- [When Do We Stop Talking About AI?](/posts/when-do-we-stop-talking-about-ai/) (2026-02-08): The specific exhaustion of a generation that can feel the stitch where human thinking and machine fluency got sewn together.
- [Photography as Interface](/posts/photography-as-interface/) (2026-02-07): What camera mechanics teach us about designing for attention, perception, and control.
- [Why Everyone Should Have a SOUL.md](/posts/why-everyone-needs-soul-md/) (2026-02-06): The case for documented identity in an AI-saturated world. Not just for agents — for humans too.
- [What Cameras Taught Me About Software (and Life)](/posts/what-cameras-taught-me/) (2026-02-06): The arc of creative tools: diverge to learn, converge to create. Why more gear made me worse, and what that means for building software.
- [Rapid Generative Prototyping: Design in the Post-Figma Era](/posts/rapid-generative-prototyping/) (2026-02-06): Design is no longer artifact creation—it's constraint architecture. The three-layer model for the agentic economy.
- [The Multi-Agent Moment](/posts/multi-agent-moment/) (2026-02-06): A technical breakdown of multi-agent orchestration: Claude's Agent Teams, OpenAI's Agents SDK, Google Antigravity, Gas Town, Beads, and the community alternatives.
- [Design Physics: When Interfaces Meet Agents](/posts/design-physics/) (2026-02-05): Traditional UX has a hidden assumption: humans on both sides. That assumption is breaking.
- [The SaaSpocalypse](/posts/saaspocalypse/) (2026-02-05): Anthropic wiped $285 billion off software stocks this week. The market is panicking about AI replacing tools. But the real disruption is what it means for the people who build them.
- [Code Owns Truth](/posts/code-owns-truth/) (2026-02-04): We obsess over prompt engineering when we should obsess over constraint engineering. The prompt is a request. The constraints are the physics. The code is what ships.
- [Proof, Not Truth: Epistemic Humility in Knowledge Systems](/posts/proof-not-truth/) (2026-02-04): We don't sell answers. We sell receipts. The receipts are what earn the right to call something true.
- [Self-Healing Systems: The Holographic Event Pattern](/posts/holographic-events/) (2026-02-03): Every event must carry everything a repair bot needs to act without asking questions. Don't scatter breadcrumbs — ship holograms.
- [Hello World](/posts/hello-world/) (2026-02-01): First post. Why I built this blog and what I hope it becomes.

## Notes
> Markdown versions available at /notes/[slug].md.
- [The Scarcity Shift](/notes/the-scarcity-shift/) (2026-05-29): Software engineering compensation was built on scarcity, not just difficulty. That scarcity is eroding. The people who survive are either unusually broad or unusually deep.
- [Everything New Is Old](/notes/everything-new-is-old/) (2026-05-20): Vector search in the 90s, badges that followed you through the office, and what happens when you build an AI system without knowing what's already been built.
- [The Dopamine Layer](/notes/the-dopamine-layer/) (2026-05-09): A neuromarketing talk got me thinking about reward systems, GLP-1s, and what happens when AI becomes the most sophisticated rationalizer we've ever built.
- [Kipple at Scale](/notes/kipple-at-scale/) (2026-04-24): Large engineering orgs already solved coordination for thousands of humans. How much transfers to thousands of agents — and where does entropy win?
- [The Fork in the Stack](/notes/the-fork-in-the-stack/) (2026-04-19): The agent era is splitting infrastructure into two camps: those building new primitives and those retrofitting old ones. The bet you make reveals what you think agents are.
- [The Context Engineering Stack](/notes/context-engineering-stack/) (2026-04-18): I built an internal context engine for our 1,765-doc knowledge base. My teammate independently found a better one. The difference was a reranking step I hadn't thought of. Here's what the emerging context engineering stack actually looks like — and why no single tool gets it right yet.
- [Named Things: A Glossary of Compressed Wisdom](/notes/named-things/) (2026-04-13): The named laws, razors, and principles that keep showing up in engineering and strategy. Each one is a concept compressed into a name — human-language embeddings, built over centuries instead of training runs.
- [The Frontend Testing Gap](/notes/frontend-testing-gap/) (2026-03-14): Backend testing is a solved problem. Frontend testing for stateful, streaming, visual UIs is not. That's exactly where AI coding agents are generating the most code.
- [I Don't Know How to Interview Engineers Anymore](/notes/interviewing-in-the-age-of-ai/) (2026-03-11): What interviewing looks like when AI can write the code but not make the call — and why the same break is happening in every field that used output as proof of understanding.
- [Trails: A Pattern for Navigating Ideas](/notes/trails/) (2026-03-02): Why I replaced a knowledge graph with curated reading paths, and what I found when I looked for prior art.
- [Toward AI-Native Analytics for Personal Publishing](/notes/ai-native-analytics-rfc/) (2026-02-26): An RFC for a small, legible analytics system — privacy-first, edge-native, AI-queryable — built on Cloudflare Workers.
- [Learning to Take Up Space](/notes/learning-to-take-up-space/) (2026-02-10): On the difference between disappearing and controlling — and the third thing that isn't either.
- [Building at the Speed of Thought](/notes/speed-of-thought/) (2026-02-08): Your brain processes 10 bits per second. Your WiFi does 50 million. We built entire workflows around pretending the gap didn't exist.
- [Photography After AI](/notes/photography-after-ai/) (2026-02-08): What's the value of photography when AI generates pixel-perfect images in seconds? The same thing that's valuable about code when AI writes it: not the output, but the seeing.
- [Memory and Journals](/notes/memory-and-journals/) (2026-02-07): AI agents have perfect memory within a conversation and total amnesia between them. What can human journaling teach us about what memory should actually be?
- [The Funeral Test for Your Digital Self](/notes/intentional-identity/) (2026-02-06): From Covey's funeral visualization to company codexes to personal test harnesses — the throughline is intentional identity.
- [Rent a Human](/notes/rent-a-human/) (2026-02-06): A marketplace where AI agents hire humans for physical tasks. The inversion is here.
- [Working With AI](/notes/working-with-ai/) (2026-02-04): How I think with AI, where I don't trust it, and what co-authorship means.

## Trails
> Curated reading paths through the site. Start anywhere.
- [Engineering](/trails/#trail-engineering): Architecture, craft, and what happens to the discipline when the tools change.
- [Life & Identity](/trails/#trail-identity): What you optimize for, what you're actually aligned with, and how to tell the difference.
- [Seeing & Making](/trails/#trail-photography): Cameras, constraints, craft — the thing itself, not the optimization of it.
- [Building in Public](/trails/#trail-building): Speed of thought, rent a human, and what it feels like to make things right now.

## Contact
- [LinkedIn](https://linkedin.com/in/bstanback)
- [X / Twitter](https://x.com/Stanback)
- [GitHub](https://github.com/Stanback)

## Machine-Readable
- [RSS Feed](/rss.xml): All posts and notes.
- [Full Content Export](/llms-full.txt): Complete markdown of all published content.