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
Rent the Agent, Own the Proof
Anthropic's Claude Tag is the best agentic Slack teammate you can rent. The question it doesn't answer: who owns the memory, and who can verify the audit log? What customer-owned, verifiable agent governance looks like in code — CCSC and AGP.
in-progressAgent-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.
Recent posts
A Green Recovery Drill Can Still Be Lying
A recovery drill that passes green can still be lying. Learn four false-pass traps in disaster recovery and backup restore verification.
ReadLet the Model Judge. Make the Code Decide.
A production writing pipeline rebuilt around one rule: the language model owns judgment, deterministic code owns the gates and the audit trail.
ReadCopying Files Is Not Installing
A marketplace install copies a plugin's files into place but never runs its installer. Here is how that bricked local mode and the dependency-free bootstrap that fixed it.
ReadProducer Fallback: When Claude Hits the Weekly Limit, the Pipeline Still Ships
A weekly LLM limit is a producer outage, not a reason to miss the daily post. Grok fallback + land path kept startaitools shipping.
ReadExit 0 Is Not Success: Automation Assurance That Verifies Outcomes
A green exit code can hide a dead job. Intent-OS automation assurance treats outcome verification as the success criterion, not exit 0.
ReadEmpty Is Not Clean: Five Fail-Open Bugs in an AI Agent
One fail-open bug, five disguises: empty args, an empty log, a missing property, a sheared chain, an unset scope. When there's nothing to check, fail closed.
ReadThe Kernel Must Not Import Its Agents
We extracted a stateful watcher agent from a governance kernel and enforced a one-way agent-to-kernel dependency edge — the kernel must not import its agents.
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
June 2026: The First Full Month Under the Repaired Rubric — Tier 1 Went From 5% to 50%, and the Last Mile Got Louder
June 2026 retrospective: the first full month running under May's repaired tier rubric. The distribution corrected from 5% to 50% Tier 1, exactly as predicted — but the structural sweep still flags every disagreement as inflation, and no human has adjudicated one. 27 posts, 1,166 commits.
May 2026May 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.