Search
Field notes from building AI in production.
Daily case studies, deep-dives, and operator-grade write-ups on AI engineering, DevOps, and the messy reality of shipping software that touches LLMs. Written from the cab, the office, and the trenches — by Jeremy Longshore at Intent Solutions.
Curated long reads
Agent-Native Mobile Testing
A three-chapter series on plugin authoring, first-mover dynamics, and AI triage for agent-orchestrated mobile cloud testing — worked through kobiton/automate as the running case study.
in-progressBuilding MCP Servers in Production
A three-chapter case study on shipping production-grade Model Context Protocol servers — synthesized from the daily case-study posts that documented the work.
Recent posts
Vite Dev Server in Production: The 871-Byte Tell
scorecardecho.com shipped the Vite dev server to every visitor. Three signals catch it in a minute; a multi-stage Dockerfile fixes it for any SPA container.
ReadCI gap: shellcheck + ruff caught 4 findings
Plugin scripts had zero lint coverage. Added shellcheck + ruff to CI; caught four issues on first run. Behavior tests missed them.
ReadCodeQL Caught the Race I Dismissed
Static analyzer caught a real TOCTOU race in audit-trail code I'd dismissed. How FD-based patterns beat suppression and lock-free approaches.
ReadThe Unicode Layer Your Validator Can't See
Schema validation can't see invisible Unicode. A stdlib-only CI gate that catches tag-char injection, Trojan Source bidi overrides, and homoglyph attacks.
ReadSelf-Expiring Report-Only CI Gates: From Advisory to Enforced
How a meta-gate enforces deadline-driven CI hardening without freezing contributors — one logical concern per PR, permanent blocking by design.
ReadSafety Model First: 16-Tool Ops MCP, One Day
Design a 7-point safety model before writing tools. How server-ops-mcp shipped 16 tools, 40 tests, and v0.1.0 in a single day.
ReadFTS5 Fallback: How Zero Search Results Became Five (ICO Dogfood Day One)
First real dog-food run of Intentional Cognition OS scored 0/5 question engagement against a corpus that contained every answer. Root cause: AND-only FTS5 query construction plus a possessive normalization order-of-operations bug. Fix: strict-then-broad fallback. Result: 5/5, 28 citations, ~$0.20.
ReadSeries & ecosystems
MCP for Beginners
End-to-end Model Context Protocol curriculum — solutions in Python, TypeScript, Java, Rust, C#, .NET — translated across six languages.
Agentic Design Patterns
Patterns and anti-patterns for production agent systems. Decision frameworks, prompt scaffolds, evaluation harnesses.
Tiny Recursive Models
Building small recursive systems where simple loops compose into emergent behavior. Series in progress.
IRSB Ecosystem
Intent Solutions release tooling — the open-source family of plugins, skills, and packages.
Wild Ecosystem
The shared-GCP, multi-MCP family of standalone integrations powered by a common platform spine.
Research & Curriculum
Long-form research articles, learning paths, and reading lists for the AI builder community.
Retrospectives
April 2026: Tier 3 Finds Its Footing — Eight Case Studies, the Audit Harness Ships, and the Schema Postmortem
April 2026 retrospective — 30 posts, 162 commits, eight Tier 3 case studies (the first real month of Tier 3 publishing), audit-harness v0.1.0 shipped, the rubric-on-spec postmortem set the architectural rule, and the daily classification pipeline ran clean for half the month.
March 2026March 2026: 35 Posts, the Eval Framework That Shipped 10 Epics in a Day, and a Meta-Milestone
March 2026 retrospective — 35 posts published, 340 commits, j-rig binary eval framework shipped 10 epics in one day, and the tier classification system itself was designed and built.