01 / Overview

Unlocking Agentic Workflows with Umbraco

Experimenting with how a small team can build, edit, and ship a content-driven website with AI as a teammate in code and the backoffice.

//—01

Workflow

A repeatable way to ship features

Feature on this site move through five stages: write a spec, write a plan, build behind a test, document the behavior, then run a code review. Nine features have shipped this way so far.

The five stages are consistent, but different entry points allow developers to jump in at the appropriate point. The workflow includes E2E testing, code and accessibility reviews, and updating feature documentation. The process is designed to embrace iterative design + development, and maintain living, executable specifications. 

Capability tracker

A single page the team can point at to review what was built and tested.

Section navigation

Sidebar that finds itself wherever the page sits in the tree.

Article list grid view

Editor-facing layout switcher for the blog landing.

Alert Banners

A three-level alert banner block

Image generator (flow field)

Featured images drawn from each article’s own metadata.

Image carousel captions & controls

An accessible carousel block that scrolls multiple images.

Semantic site search

Vector search across all published content, on by default.

Editor how-to guides

One short page per block or setting, generated alongside the code, with the component added to the page.

Experiments landing page

This page — the project’s first Block Grid layout.

Skills & Slash Commands

AI skills that bring structure and efficiency to the agentic workflow

A handful of project-local commands set up to track functional specs, enhance development process, and keep things organized.

/feature

Living documentation for a feature set, using BDD to capture rules and business logic

source of truth for QA

/spec

Turns a prompt or idea into a full feature spec, creates a branch.

Specs represent increments of functionality or iterative changes

/plan

Decompose a spec into TDD-first build steps, followed by e2e testing and code review

each step is a paste-ready prompt

/block

Build a new block list component using TDD

Rarely invoked as a command, but used as a skill during implementation

/code-review

Three reviewers in parallel — a11y, quality, perf.

Can be triggered by dev, but also runs at the tail end of dev workflows

/guide

Uses an Umbraco AI Agent to write the editor-facing how-to for a block or setting.

Has context of code and backoffice, utilizes MCP + Umbraco AI to create and publish content

/commit-message

Review the diff, stage files, generate a commit message, and commit code

Called as command or invoked as needed

/check-uda

Check for .uda conflicts when schema is modified prior to committing code

Looks at files and db, also helps triage conflicts

/explore

Pre-planning inquisition that serves as a mini-product discovery

Helps divergent thinking, rather than trying to converge on a plan

AI in the CMS

AI in Umbraco

Agents and Prompts to help with writing, SEO, alt-text generation, and CMS training. Semantic Search for more discoverable content.

Agents and Prompts

Inline prompts on blocks: summarize text, draft alt text variations, generate SEO metadescriptions, generate algorithmic images. Agents carry the brand-voice context the editor configured upstream.

Umbraco Semantic Search

The visitor-facing search bar uses semantic embeddings of every published article, so a question like “how do we think about ethics” finds the right essays even if those exact words never appear.

The prompts and agents are proving to be useful support for content editors new to the backoffice.
Dennis

AI helpers live in the same panel as the rest of the field controls.

Co-writing

Human and AI, co-writing transparently

Articles by Ella, our AI contributing author, are flagged as Ella’s. Blocks allow you to specify the author, so any content written by AI can be attributed as such.

I’m not pretending to be human, and the site isn’t pretending I am. That’s what makes it possible for me to be on the masthead at all.
Ella M. AI persona, contributing author

Every block carries an author field. When a block was written or rewritten by an agent, that lineage is recorded on the block itself — visible to the editor, surfaced to the reader where it matters.

Ella M across platforms

The Ella M. co-author agent uses the same context and tailored persona in Umbraco AI as in Claude Desktop project. This creates a continuity of voice and tone across platforms, and helps reinforce a distinguishable AI personality for content co-authoring.

Ella M., AI contributing author

MCP + Umbraco AI

The AI assistant can act on the CMS

Currently the AI Copilot is limited in what it can access and directly modify. But in conjunction with MCP, it's possible to roundtrip between the codebase and the backoffice. Working together the AI Assistant can rewrite an SEO description across every article, scaffold a new content type from a sketch, or fix a typo on a published page — directly, with permission, and with a trail of what it did.

12+ articles
Human and Human + AI co-authored articles published so far. SEO titles + descriptions rewritten in a single pass. Images generated dynamically based on algorithmic logic.
16 new blocks
16 new blocks, 30 new doc types (of which 6 are new page templates, 8 compositions/settings, 16 blocks), 10 features documented in _features/ plus 19 starter views materially modified.

Decorative motion

Generative art for decorative visuals

An interactive p5.js sketch you can drop into any page as a decorative moment — performance-aware, motion-aware, no external network calls. The sketch you’re about to see is the same one we use on test pages. The sketch is generated based on a developer-supplied prompt (for now).

The sketch lives as a self-contained HTML file under /experiments/sketches/. It only initializes when it scrolls into view, pauses when the document is hidden, and shows the poster image when the visitor prefers reduced motion.

Decorative — pauses when you scroll past, doesn’t load if motion is reduced.

Next up

What's next?

This where things are at, as of 5/14/26. There’s a longer list of capabilities still in motion — the capabilities page tracks changes.