Resources
Zartis Tech Blog
From software industry research and insights to practical how-to guides — discover the tools you need to succeed in software development.
Highlights
How Zartis Helped Create Real-Time Power Management for a UK Smart EV Charging Company
Discover how Zartis engineers are helping a cleantech leader enable dynamic, data-driven EV charging solutions.
Zartis Makes Deloitte Fast 50 for the Sixth Year Running
We are thrilled to share that Zartis has ranked in Deloitte Technology Fast 50 Ireland for a sixth year running. A huge thanks to everyone!
Evaluating Generative AI Development Services for Custom Enterprise Applications
How to evaluate generative AI development services for custom enterprise applications: a three-part framework covering technical depth, delivery and governance.
Search
The Agentic AI Implementation Guide For Banking: Governance Architecture And Delivery
How banks are building agentic AI governance from day one, covering SR 26-2, the EU AI Act, and FCA rules. See what CTOs need in place
Evaluating Generative AI Development Services for Custom Enterprise Applications
How to evaluate generative AI development services for custom enterprise applications: a three-part framework covering technical depth, delivery and governance.
Evals and Observability: The Two Things Every Enterprise Asks About Before an AI System Goes Live
Why evals and observability are now baseline requirements for production AI agents, and how to build both into your delivery pipeline. A technical guide
Context Engineering: The Discipline That Decides Whether Your AI Agent Actually Works
AI agents fail on bad context, not bad prompts. Learn the five disciplines of context engineering, from retrieval design to CLAUDE.md, with real examples.
Your AI Pipeline Is Fast. Your Review Gate Need to Catch Up.
AI speeds up code generation, but naive review gates create a new bottleneck. Learn how to design risk-tiered, async human-in-the-loop checkpoints that scale.
Verification Is Not The Tax On AI Autonomy – It Is The Price Of Admission
Autonomy isn’t earned by a smarter model. It’s earned by permissions, hooks, sandboxes, and CI gates an AI agent can run against. See how Zartis can help.
Claude for Coding: How Engineering Teams Move From Autocomplete to Agentic Delivery
Claude coding means more than autocomplete. See what it takes to move engineering teams to governed, agentic delivery with Zartis
Adopting Claude Across the Enterprise: What a Preferred Services Partner Handles That a Licence Alone Does Not
A Claude enterprise licence isn’t a rollout plan. See what governance, integration and evaluation work closes the gap, and talk to Zartis.
Claude Code for Enterprise Engineering Teams: Beyond Developer Productivity Into Organisational Capability
Individual coding speed doesn’t reach the business. Discover the three organisational capabilities that make Claude Code adoption pay off at scale.
Building Trustworthy Agentic AI in Financial Services: A Compliance-First Implementation Framework
A compliance-first framework for deploying agentic AI in financial services, covering governance design, observability, and lifecycle controls.
Why AI-Driven Legacy Code Modernisation Is Now a Board-Level Risk Management Priority
Legacy code is a board-level risk, not just an engineering backlog. Learn how CTOs can frame AI-driven modernisation as a risk management priority before it becomes a crisis.
AI Governance Best Practices: Moving From Abstract Guidelines To Engineering Reality
Most organisations publish AI governance frameworks. Few translate them into running engineering controls. Here is how to close that gap in production systems.
AI Team Structures: Embedded vs Centralised
Centralised AI teams build foundations. Embedded squads drive speed and relevance. This guide breaks down both models, when each works, and how mature organisations combine them into a hybrid operating model that scales.
The Semantic Layer: Turning Raw Data into Trusted AI Insights
A semantic layer gives BI tools and AI systems a shared definition of business metrics, removing conflicting reports and building trust in analytics.
Human-in-the-Loop UI Patterns: Designing Intentional Friction For Safer AI Products
Human-in-the-loop AI design keeps humans involved in automated decisions. Explore the UI patterns that make oversight intentional.
Insights
In-depth Research and Whitepapers by the Zartis Team
Check out our resources page, and access our insights on AI & software engineering.
Newsletter
Zartis AI Review
Your monthly source for AI and software related news.