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 Gates on Standard-User BitLocker State Observation
Standard-user BitLocker state observation has three gates. A Codex audit caught the third one on three failure modes; two were the kind it was built to find.
ReadCryptography 45.0.6 Revoked; intent-blue-gold Epic 0 Sealed by Council
intent-blue-gold Epic 0 closed: cryptography 45.0.6 revoked in favor of 50.0.1, then a 168-Bead planning graph passed three adversarial reviews and a seven-seat council.
ReadPerception Is On the Way, on Its Own Domain
A customer preview page at perception.intentsolutions.io went live on 2026-09-11 because the full paid-product release surfaced four infrastructure gaps the smaller deployment could close.
ReadThe Same Mission on Two Surfaces in One Day
Two new Omarchy entry repos scaffold the same game on the same day: one as a QML bar-widget teaser with a single local mission and a fixed parent-guide link, one as a downloadable Electron desktop app with a six-mission chapter and a seven-day trial.
ReadA 953-line skill entry fits the budget again
A 953-line skill entry collapses to 267 lines plus four pull-only references, and the same day seventeen Omarchy repos pin the audit-harness and review Action to the same SHA.
ReadHardening a Marketplace in One Day
A gate that travels with the contributor workflow closes one leak across 16 plugin trees. A new install integrity schema names what portable installs must carry.
ReadHash-Sealed Evidence: One Feature, 19,461 Lines Rebuilt
Sealed evidence expires when content changes. Adding a feature to omaTrail rewrote 19,461 lines of its balance report before shipping.
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
August 2026: A Control That Fires on Every Case and Changes No Outcome Is a Log Line
A control that fires on every case and changes no outcome is a log line, not a control. August 2026 retrospective: 31 of 31 posts flagged for inflation with the distribution unmoved, a learned cap rule that caught zero, and a rubric six weeks stale that still names a retired rule.
July 2026July 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.
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.