Skip to main content

Blog

Ideas and lessons from the field on building AI-native engineering orgs.
Liatrio Named a SpaceX Super Intelligence Transformation Partner
FEATURED

Liatrio Named a SpaceX Super Intelligence Transformation Partner

Liatrio is now a registered SpaceX Super Intelligence Transformation Partner, pairing Grok with Forward Deployed Engineers who embed in client teams to turn AI pilots into measurable ROI at scale.

Team Liatrio•October 22, 2026
AI Coding Tool Adoption Doesn't Equal Value Delivered: Why Productivity Stalls and How to Fix It

AI Coding Tool Adoption Doesn't Equal Value Delivered: Why Productivity Stalls and How to Fix It

Robert Kelly
Robert Kelly•November 14, 2026

AI coding tools usually aren't the problem. Adoption stalls when the tools land in workflows, repositories, and policies that nobody changed to use them. Stalled adoption looks like seats that are assigned but unused, or used heavily without changing how fast work ships.

How to Train Developers to Use AI Coding Assistants Effectively: A 4-Week Plan

How to Train Developers to Use AI Coding Assistants Effectively: A 4-Week Plan

Robert Kelly
Robert Kelly•November 13, 2026

Effective AI coding assistant training is structured practice on real work, not a tool overview or a one-day workshop. A four-week plan works well: two weeks of coached practice on a shared workflow, then two weeks applying that workflow to real backlog items, measured against a baseline.

What Is Spec-Driven Development? A Practical Guide for AI-Assisted Engineering Teams

What Is Spec-Driven Development? A Practical Guide for AI-Assisted Engineering Teams

Robert Kelly
Robert Kelly•November 13, 2026

Spec-driven development is a workflow in which engineers write a clear, reviewable specification before an AI coding assistant generates or changes code.

The First Agent Worth Running in Your Pipeline
AI

The First Agent Worth Running in Your Pipeline

Blake Webb
Blake Webb•November 12, 2026

Pipeline-failure triage is a practical first job for an AI agent. Start with deterministic checks, then roll it out crawl-walk-run so the agent proves its diagnosis before it's allowed to change code.

A Tuned vLLM Semantic Router Drastically Reduced Our Anthropic Bill

A Tuned vLLM Semantic Router Drastically Reduced Our Anthropic Bill

Amber Beasley
Amber Beasley•October 30, 2026

Liatrio benchmarked a tuned vLLM Semantic Router against Claude Opus and Sonnet on 62 agentic tasks. The router cut cost by about a third versus Opus alone, but solved nine fewer tasks (80 vs 89). Tuning took three rounds; results reflect work the router was tuned against, not a held-out test set.

Stop Measuring AI by Tokens. Measure It by Outcomes.

Stop Measuring AI by Tokens. Measure It by Outcomes.

Team Liatrio
Team Liatrio•October 5, 2026

How Liatrio and SpaceXSI turn Grok, Cursor, and Grok Bot into enterprise throughput — with Forward Deployed Engineers who build with your teams, not for them.

Evaluating AI Systems Like Engineers, Not After the Fact
AI

Evaluating AI Systems Like Engineers, Not After the Fact

Paul Henson
Paul Henson•September 3, 2026

AI evaluation usually starts after something breaks. This post argues for engineering it instead: name failure modes first, run cheap checks before expensive judgment, and build the habits Liatrio teaches inside its AI Evaluation Bootcamp.

Silence Isn't Safety: What We Learned From Vetting AI Skills
AI

Silence Isn't Safety: What We Learned From Vetting AI Skills

Alex Ramsay
Alex Ramsay•August 27, 2026

What two months of building a vetting pipeline for AI skills taught us.

Five Scanners, 5,000+ AI Skills: What We Learned About Skill Security
AI

Five Scanners, 5,000+ AI Skills: What We Learned About Skill Security

Jaydon Kellum
Jaydon Kellum•August 12, 2026

Liatrio tested five AI skill scanners against real malicious and benign corpora. Static tools never beat a simple keyword grep. LLM-backed scanners (Snyk, Cisco, SkillSpector) scored far higher, and requiring three of them to agree gave the cleanest high-confidence results.

Tokens to Outcomes: Why Our Partnership With SpaceXSI is Different

Tokens to Outcomes: Why Our Partnership With SpaceXSI is Different

Team Liatrio•July 28, 2026

Turn AI adoption into measurable business impact. Discover why Liatrio's partnership with SpaceXSI goes beyond faster coding by embedding AI into workflows, metrics, and operating models that scale across the enterprise. Read how we connect tokens to outcomes, not just usage.

Code Gauntlet Rewrite to Claude Workflows
AI

Code Gauntlet Rewrite to Claude Workflows

Lee Hopper
Lee Hopper•July 23, 2026

We built a benchmark, measured our AI code reviewer against the market, then let Fable rewrite it over a four-day autonomous session. The new version tops every tool we scored.