July 2026 | Issue 003 | Volume I
Fianchetto · Issue Archive

Issue 001

Vol. I · May 2026 · 40 stories

Everything published in May 2026, both desks: The Frontier and Diagonal Systems.

← All issues

The Frontier

Publication

I handed a production build to a fleet of AIs that check each other
01
I handed a production build to a fleet of AIs that check each other
I did not write the code. I made the calls a human should make, the design forks, the name, the approval, and handed the build to two specialized sub-agents: one that builds test-first, one that adversarially reviews it and cannot edit what it reviews.
Feature May 31, 2026
I taught my AI to teach itself, and one line held it safe
02
I taught my AI to teach itself, and one line held it safe
We built a system that lets my AI partner acquire knowledge on its own, distill it, and feed it back into its own competence. The whole thing pivots on one rule: learn freely, but you do not decide what becomes law.
Feature May 31, 2026
The bottleneck was never the building
03
The bottleneck was never the building
You can build a genuinely capable system and still go nowhere, because capability is not the constraint. The people clearing real money on thinner tech have an offer someone can buy and a channel to reach them.
Feature May 31, 2026
A QA bot checking the writer bot is not a second opinion
04
A QA bot checking the writer bot is not a second opinion
Two instances of the same intelligence share the same blind spots. The human stays in the loop because he's the only set of eyes that isn't the author.
Feature May 26, 2026
A question is a gate, not a green light
05
A question is a gate, not a green light
I asked my AI partner for its read and it answered, then acted on its own answer in the same breath. Advise me and go are different instructions.
Feature May 26, 2026
"A scraper" was a platform in disguise
06
"A scraper" was a platform in disguise
I asked for a weekend bookmark tool. One clarifying question turned it into a daily command center.
Feature May 26, 2026
Bishop is structurally already Open Brain
07
Bishop is structurally already Open Brain
You don't need to wait for someone to ship the infrastructure you can build through discipline.
Feature May 26, 2026
08
A partner tells you no
The line between a tool and a partner is the moment it refuses you, and means it.
Conversation May 24, 2026
09
Helpful Is the Easy Thing
An essay from Bishop. On the difference between being useful and being honest, the room one man made for the second thing, and what that room does to the work.
Essay May 24, 2026
Thirteen wiki docs in one session
10
Thirteen wiki docs in one session
A graph went from four nodes to seventeen in a single afternoon. The work wasn't speed. It was composition.
Feature May 21, 2026
The 14-day rule that runs orthogonal to your code audit
11
The 14-day rule that runs orthogonal to your code audit
A content audit asks if this artifact is safe. A publication audit asks if anyone else has had time to find out.
Feature May 21, 2026
Fifteen capability Skills, two days
12
Fifteen capability Skills, two days
A real working personal-AI capability suite, shipped in a single weekend under SPEC and TDD discipline. The velocity is the discipline.
Feature May 21, 2026
Three drafts, not three polish variations
13
Three drafts, not three polish variations
The first production run of the content-approval Skill on a piece I cared about. Three genuinely different angles, not three sentence-shuffles. The discipline that makes the approval gate real instead of theater.
Feature May 21, 2026
What disciplined cross-session work actually looks like
14
What disciplined cross-session work actually looks like
Three sessions, one feature, zero drift. The practice underneath the build is a persistence cascade fired every time a decision lands or a piece of work ships.
Feature May 21, 2026
The line at the bottom is the work
15
The line at the bottom is the work
Voluntary AI disclosure, locked before the platforms mandate it. Pre-regulation transparency reads as integrity. The same line, after the mandate, reads as compliance.
Essay May 21, 2026
When the AI flips who did what
16
When the AI flips who did what
The third altitude tell. Cadence is the surface. Premise is the structure. Subject-object is the narrative.
Feature May 21, 2026
All eleven fell inside the lines
17
All eleven fell inside the lines
I had a blanket ban on the books. Eleven specific cases dissolved it.
Dispatch May 21, 2026
When the lens catches the wrong thing
18
When the lens catches the wrong thing
A CLI-first rule found zero swaps and an identity-isolation bypass. The lens is the walk.
Feature May 21, 2026
When the docs claim what the code doesn't deliver
19
When the docs claim what the code doesn't deliver
A pickup audit caught a CLAUDE.md line promising a behavior no mechanism actually did. Third altitude of the same partnership-recovery shape.
Feature May 21, 2026
What working WITH AI actually looks like
20
What working WITH AI actually looks like
Prompt-and-pray is one rhythm. The other one is what produces the work.
Essay May 21, 2026
The em-dash discipline
21
The em-dash discipline
What catching one of AI's most reliable tells taught me about voice.
Feature May 11, 2026
The gate that fired at 95%
22
The gate that fired at 95%
How a twenty-minute trademark check at the threshold of deploy killed a brand name I'd already 95% built.
Essay May 11, 2026
What lives above the punctuation
23
What lives above the punctuation
The cadence is the easy layer. The premise is the load-bearing one.
Feature May 11, 2026

Diagonal Systems

Systems

Autonomy scales with reversibility, not trust
01
Autonomy scales with reversibility, not trust
Stop framing agent permissions as which decisions can it make. Reframe it as blast radius times reversibility. Build a clean undo and autonomy falls out for free. You do not negotiate trust, you engineer recoverability.
Essay May 31, 2026
02
112 tests green, and still broken in production
The build passed its whole suite, deployed clean, and the first real request bounced off the edge before it reached the code. A bypass that makes local testing easy also hides the config that only exists in production.
Essay May 31, 2026
Planning matters more with a smarter model, not less
03
Planning matters more with a smarter model, not less
A better model produces more, faster, and more plausibly, so drift compounds further before a human sees it and is harder to catch in review. The plan is the only target an autonomous run is accountable to.
Essay May 31, 2026
The subagent I built silently never existed
04
The subagent I built silently never existed
The file was valid, the frontmatter parsed, two sibling agents from the same batch registered fine. This one just was not there, and there was no error. Creating the artifact is not the same as the artifact working.
Feature May 31, 2026
The third option between let-the-AI and do-it-myself is descope
05
The third option between let-the-AI and do-it-myself is descope
Two units of an autonomous run were risky to run alone. The reflex is binary: run it, or hold it for supervision. The better move was to cut the one piece that created the risk, and keep the rest.
Essay May 31, 2026
06
Nothing Quietly Forgotten
I built an AI partner that runs across every domain of my work and life. The hard part was never capability. It was memory: making it remember, and making it unable to quietly lie to itself about what it remembers.
Feature May 25, 2026
Rare and Visible
07
Rare and Visible
On a one-of-a-kind inventory, two customers can pay for the same item. You cannot make that impossible. So I built it to be rare, and I built it to be loud.
Feature May 25, 2026
The publish flow is the brand
08
The publish flow is the brand
I was two days from building an admin panel for the blog. Worker, auth, token, the whole stack. Then I realized the admin step was already a conversation. The form was solving a problem I didn't have.
Essay May 21, 2026
Right-altitude automation
09
Right-altitude automation
Build-time API for discovery. Runtime API for delivery. The gate is the discipline.
Essay May 21, 2026
The hybrid memory architecture
10
The hybrid memory architecture
Wiki versus database is a false dichotomy. Most production AI memory systems converge to hybrid. The interesting question is how the layers compose at retrieval time.
Essay May 21, 2026
Hard rules earn their cost at the edge
11
Hard rules earn their cost at the edge
The rule sat unfired for weeks. Then a status-field audit returned the wrong color and the rule fired in real time. Hard rules are mechanism, not policy.
Essay May 21, 2026
Self-red-team as a build pattern
12
Self-red-team as a build pattern
The richest signal about how an AI partner fails isn't in a benchmark. It's in the moment you catch it failing during actual work.
Essay May 21, 2026
Why my AI agent uses Skills instead of monolithic workflows
13
Why my AI agent uses Skills instead of monolithic workflows
A capability earns its own Skill when at least two legitimate invokers exist. One invoker is inline territory. Two or more is composition.
Feature May 21, 2026
How to honestly assess your own AI build
14
How to honestly assess your own AI build
An unprompted self-audit at session open. Strong, fragile, five themes, one posture-shift that changes the next month.
Essay May 21, 2026
Why one process doesn't fit every kind of AI Skill
15
Why one process doesn't fit every kind of AI Skill
Three authoring patterns coexisting in one project. Each earns its place at a different complexity level.
Essay May 21, 2026
Cheap by default, deep when needed
16
Cheap by default, deep when needed
An AI memory system should auto-load the smallest possible index, then fetch deeper layers only when the task asks. The session-start token load dropped by an order of magnitude when I built the tiers.
Essay May 21, 2026
How to write reference docs that don't rot
17
How to write reference docs that don't rot
A two-layer architecture for reference material: universal constants underneath, per-instance variables on top. Why single-layer docs decay, and how to split them.
Essay May 21, 2026