Search
Start AI Tools with Intent Solutions
Daily work journal below. Real case studies, deep-dives, and operator-grade write-ups on AI engineering, DevOps, and the messy reality of shipping software that touches LLMs, by Jeremy Longshore at Intent Solutions.
Curated long reads
Let the Model Judge. Make the Code Decide.
The model owns judgment. Deterministic code owns the gates, the commit, and the audit trail. How I rebuilt a daily writing pipeline so a hung session can no longer brick tomorrow.
Adversarial Review: The Six Lenses That Halted a Rollout
Six lenses, live state, eighteen risks. I thought the safety work was shipped. The review proved three assumptions were theater. The durable rule: the model proposes; the system owns identity, trust, and state.
The Moat Is the Trust Layer
A local-RAG demo became Intent NEXUS. The moat is not the chatbot. It is egress control, code-enforced citations, a ledger you can check, injection defense, and evals that cannot lie quietly to you.
Recent posts
Three Commits Between the Rule and the Violation
A changelog gate shipped inert: at fetch-depth 2, git tag --list is empty in CI, so the check exited 0. An AI reviewer caught what the author could not.
ReadNothing Read It, So Nothing Failed
Five defects in one day across five substrates, all the same shape: an artifact with a producer and no consumer. That is why none of them ever failed.
ReadThe Filesystem Was the Only Thing They Shared
Four models, nine threads, one disk. Two missed nights with two unrelated root causes, and a bug filed against a file another session already fixed.
ReadThe Check That Only Confirmed a Name
A default transport that only ever failed sent 2-5 fake outage emails an hour while the relay was healthy. Four checks that confirmed a name instead of a fact.
ReadWhen Live Numbers Argue Back
Live data surfaces bugs static builds never could. The jeremylongshore.com rebuild caught two in production.
ReadThe Version Number That Only Existed on the Client
When a vendor releases v0.5.3, how do you know if your self-hosted relay actually has it? The version number is not the answer.
ReadThe Ghost in the Catalog
A pipeline wrote a published record for a post it never published, then its own self-audit article read that record as truth and printed it for readers.
ReadSeries & curriculum
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.
Research & Curriculum
Long-form research articles, learning paths, and reading lists for the AI builder community.
Retrospectives
July 2026: Every Instrument Reported Success, and One of the Published Posts Was a 404
July 2026 retrospective: Tier 1 collapsed from 46% to 17%, the anti-inflation rule adopted July 3 fired zero times all month, the grader demoted half the catalog on a title keyword list, and a post with a full green audit trail was never published at all.
June 2026June 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.
Let's build something that ships to production
Intent Solutions designs, builds, and ships production AI systems: Claude, MCP, RAG, agents, and the boring infrastructure that makes them trustworthy. Tired of AI demos that never make it past the POC?
No commitment required. We respond within 24 hours.