BuildingJeremy Longshore · Intent Solutions
I make teams
AI-native.
I build AI systems around real work, test what they do, and help teams operate and improve them. Intent Solutions connects that engineering to evidence, teaching, open source, and products.
Claude Code credential
Anthropic-issued badge for scoping, deploying, configuring, and operating Claude Code. Earned through eight courses and a scenario-based capstone.
Verify on CredlyProof of work
19,162 contributions in the last year
Shipped and running
Projects
Tons of Skills
LiveOpen-source skills marketplace · about 56K Skills.sh installs (Oct 2026)
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
Upstream, not just downstream
Open-source contributions
45 merged PRs across 17 external repos
Authored by Jeremy and accepted by outside maintainers. Contribution does not imply employment, partnership, or client status.
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 OmaSafe · agent-brain · xireactor-brilliant · wasteland · claude-skills-collection · awesome-agent-skills · cx-core
Work diary
Writing
Build logs and field notes from startaitools.com
When a Third-Party CI Credential Expires, the Deploy Fallback Has to Already Live on the VPS
GitHub Actions deploys that depend on a third-party OIDC identity silently 402 deep in the run when that identity’s plan ends, and the run summary still turns green while pro...
When git describe Traps Your CI Semver Bump, Look Up the Highest Existing Tag Instead
A CI-driven semver bump that reports tag already exists on every push looks like a duplicate-tag bug. It usually is not. The trap is git describe and a single bot commit that the p...
When Your Documentation Evaluation Is Driving the Cleanup, Report Gap Answers by Rank Instead of Adding Them to the Scored Set
If you are running a search or retrieval evaluation against a documentation corpus, and the same eval is what surfaces the holes you then fill, you have a quiet training problem. T...
Coordinating a Product Launch Across Multiple Repos
Multi-repo launches drift by default. A demo site keeps showing the old name while the canonical route (the one URL the product should be reachable at) finally exists, the homepage...
Verify Audit Evidence with a Signed Payload, Not by Format
When many audit-evidence publishers (the systems that produce signed rows of evidence) each emit a different shape and the consumer checks signatures case by case, a tampered row i...
SMTP 250 is not delivery: three receipts that fix transactional mail
SMTP returns “accepted” for a message the relay may still lose ten minutes later, and APPEND is not delivery. After this, an engineer auditing a transactional mail syst...
Stuff I run
Tools
The stack behind everything on this page — no affiliate links, just what survives daily use.