BuildingJeremy Longshore · Intent Solutions
I make teams
AI-native.
I build AI systems that ship and train teams to work with coding agents — Claude, Codex, Gemini, whatever moves the needle. 20+ years ops, self-taught dev, 60+ repos with real GitHub stars.
Anthropic-issued
Claude Partner Badge · Claude Code
Certified through the Claude Partner Network to scope, deploy, configure, and run Claude Code activations end-to-end. Eight-course program with a scenario-based capstone.
Verify on Credly →Proof of work
13,433 contributions in the last year
Shipped and running
Projects
Claude Code Plugins
Live471 plugins, 3,069 skills, 347 agents — largest Claude Code marketplace
Bob's Big Brain
LiveGoverned team brain: cited recall with a tamper-evident audit trail
Intent Eval Platform
LiveAudit-first AI evaluation: measure the behavior, sign the result, gate the ship
Scorecard Echo
LiveLive broadcast-booth companion for baseball: real-time stats and storylines
DiagnosticPro
LivePhoto-to-diagnosis: upload a pic, get a repair plan
HustleStats
LiveReal-time youth soccer stats with AI performance reports
IRSB
LiveOn-chain guardrails for AI agents — no agent should hold unguarded keys
Wild — Rails AI Ops
Live10 production Ruby gems for safe AI-agent ops in Rails
Upstream, not just downstream
Open-source contributions
43 merged PRs across 16 external repos
NOW LMS
i18n compile-at-boot fixes, enrollment integrity constraints, theme perf, and test coverage for the open-source learning management system
Kobiton Automate
Mobile device-cloud test automation contributions
Blur Extension
Teams, Slack, export/import, custom patterns
Beads
Natural-language skill activation and core fixes
PostHog
React state management and feature-flag bug fixes
Kilo Code
Agent runtime test fix
tldraw
Prettier extension fix
Filament
Dark mode fix
Vertex AI Samples
ADK inline-source deployment tutorial for Agent Engine
Agent Starter Pack
Bob's Brain production ADK reference in the community showcase
Also merged in agent-brain · xireactor-brilliant · wasteland · claude-skills-collection · awesome-agent-skills · cx-core
Work diary
Writing
Build logs and field notes from startaitools.com
A Closed Epic Is a Claim, Not a Fact
Closing a bead is a claim. Merging a PR is a claim. Writing an after-action record that says the gate is wired and green is a claim about a claim. None of those are facts. The only...
The Refusal Nobody Heard
The blog pipeline went silent for two nights. Email never went out. No posts shipped. The 04:00 producer ran but published nothing, and the 05:00 posting packet had no material to...
Make the Guard Prove It Can Fail
The defect class A gate you have never seen go red is a gate you have not tested. On 2026-08-18, four gates across two repositories turned out to have that problem: a mask that ret...
Seventeen Spellings of the Same Number
The Tons of Skills marketplace renders skill-count numbers on its public pages. Those counts were bare. A number like “3,068 skills” does not say which population it co...
Exit Zero Can Lie; Stdout Holds the Answer
Three days. August 14, 15, 16. The 05:00 cron that builds Ezekiel’s posting packet logged the same line: voice-gen failed -> degraded packet. Three consecutive days. Ezeki...
Five AARs and a Count That Blinked
Five AARs landed in one day, numbered 736 through 740, and one of them needed five follow-up commits before its filing could be honest about what the day actually changed. The day&...
Stuff I run
Tools
The stack behind everything on this page — no affiliate links, just what survives daily use.