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, agent reliability on real-device clouds, 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
Making Agents Reliable on Real-Device Clouds
Reliability on a real-device cloud isn't in the API calls — it's in the partial-failure seams between MCP tool calls. Three task-specific agents, four advisory hooks, and a documented-limitations list make those seams legible so an agent routes instead of guessing.
ReadStop Crying Wolf: A 3-Strike Gate for Uptime Monitors
Fix uptime monitor alert fatigue with a 3-strike debounce gate and real per-probe diagnostics. Stops false positives, keeps real outages visible.
ReadHuman-in-the-Loop Is a Delivery Guarantee, Not a UI Feature
Human-in-the-loop agent delivery is exactly-once, fail-closed. Two repos shipped the same four-move discipline the same day — convergence, not coincidence.
ReadNine Days Silent: When the Blog's Own Pipeline Stopped Publishing Itself
A 9-day publishing blackout went unnoticed because monitoring reported success while producing nothing. Git worktrees + orphan branches + timeout logs = silent failure at scale.
ReadThe Wrong Product, Built Perfectly
A new site was scaffolded, deployed, and live with valid TLS in under an hour — then declared the wrong product. The decoupling made the reversal cheap.
ReadFrom one adopter to two: the discovery-affordance spec just got named
A 39.7k-star skills repo adopted my discovery-manifest pattern by name. What changed, why it matters, and the install_source_url work that comes next.
ReadVite 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.
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
May 2026: The Month the Classifier Caught Itself — A Mid-Month Calibration Reckoning, 27 Posts, and 964 Commits
May 2026 retrospective: the tier classifier caught itself inflating. Calibration found the rubric structurally broken mid-month. 27 posts, 964 commits.
April 2026April 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.