Multiple sectorsCase study

AI & Automation Delivery

AI-enabled tools defined and coordinated across strategy, design, research, QA and development: an AI content-tagging agent, AI-assisted translation inside the CMS, AI-search (GEO) visibility, a voice concierge in definition and Notion AI agents.

Content tagging · translation · AI-search visibility · voice concierge · Notion agents

Key figures

  • ~80%

    tagging precision, with final human validation

  • ≈324 h

    estimated manual effort for the same tagging; the agent runs in seconds

  • 3

    Notion AI agents built for a client

  • Up to ~10 h

    estimated weekly saving from those agents

At a glance

My role
Defined and coordinated the initiatives
Scope
Content tagging · translation · AI-search visibility · voice concierge · Notion agents
Team
Client brand team, SEO, development and AI engineers
Period
2025 – present

Context

Applying AI where it saves time in content operations and findability, while keeping a human in control of the output.

Outcome

  • 4 AI initiatives delivered, 1 in definition
  • ≈324 h of manual tagging reduced to seconds per run
  • Human validation on every AI output
  • From a 45-market programme to a community platform

Use of AI

Defined and coordinated AI-enabled tools: content tagging, translation, AI-search visibility and a voice concierge.

Where each piece stands

Delivered

AI tagging tool

I defined the agent and coordinated strategy, design, research, QA and development. It tags a content library (articles, recipes, experts, chefs) against the brand’s taxonomies with ~80% precision and a final human validation. Estimated manual effort ≈324 h, calculated from the time a content manager takes per item × total content (2,150 articles, 650 recipes, 100 experts, 150 chefs); the agent runs in seconds.

AI content tagging: effort and flowEstimated manual tagging effort for the content library is about 324 hours, while the agent runs in seconds. The flow is: content library, AI agent, about 80 percent precision, human validation, published.Tagging the same content libraryManual (estimated)≈324 hAI agentin secondsHow it runsContentlibraryAI agent tagsagainst thetaxonomies~80%precisionHumanvalidationPublished
Estimated manual effort versus the agent, and the human-in-the-loop flow
Delivered

AI-assisted translation inside the CMS

An AI translation tool integrated into the Drupal CMS, so editors translate content for new markets without leaving the platform. A prompt set in the back end drives the translation, and the editor chooses the tone when translating. Every translation still goes through manual validation before publishing, so speed never replaces quality control. Result: shorter translation time for each market rollout.

AI-assisted translation flowSource content is translated by AI inside the Drupal CMS, validated manually, then published.SourcecontentAI translationinside the CMS(Drupal)ManualvalidationPublish
AI-assisted translation inside the CMS, always validated by a person
Delivered

GEO / LLM visibility

Generative search engines (ChatGPT, Gemini, Perplexity, Claude) answer questions by citing sources, so a site has to be readable and citable by them. On the 45-market programme I coordinated the platform-level work: schema markup, HTML landmarks, breadcrumb schema and an llms.txt file. On the community platform I coordinated a diagnostic of AI readability: llms.txt, JSON-LD, robots.txt rules for AI bots, server-side rendering, FAQ pages, content chunking and WebMCP readiness. Visibility is measured with prompt-based checks across the main AI assistants.

In definition

Voice-activated AI concierge

Product definition and roadmap of a voice-activated assistant for community members. It lets them find restaurants, listen to recipes while cooking and get guided through articles, using only the brand’s approved content through the CMS API (user → agent → CMS API). Planned in three phases: restaurants, recipes and articles first, then governed personalisation, then an access and benefits layer. Currently in definition (scoping, architecture and roadmap); not built yet. My role: project definition, technical alignment, data review, timeline, strategy and client contact.

Voice-activated AI concierge: data flow and roadmapA user speaks or types to a gated AI agent, which only reads approved content through the CMS API. The roadmap has three horizons: restaurants, recipes and articles first; governed personalisation next; an access and benefits layer later. It is at the scoping, architecture and roadmap stage and is not built yet.User → agent → CMS API, so the agent never leaves approved contentUservoice or textAI agentgated for communitymembersCMS APIApprovedcontentRoadmap in three horizonsHorizon 1restaurants, recipesand articlesHorizon 2governedpersonalisationHorizon 3access andbenefits layerScoping, architecture and roadmap stage. Not built yet.
Voice-activated concierge: controlled data flow and a three-horizon roadmap (in definition)
Delivered

Notion AI agents

Three Notion agents built for a client to cut manual admin: logging email messages into Notion, drafting replies and automating follow-ups. Estimated time saving: up to ~10 hours of manual work per week.

Skills shown

  • AI product definition
  • Cross-functional coordination
  • Human-in-the-loop design
  • GEO / AI search visibility

What I learned

  • At 80% precision, human validation is part of the product; the time saved is net of review.
  • AI is deployable for a brand when it is constrained to approved content.
  • Measure the manual baseline first: the tagging case was provable because we had the 324 hours.
  • For a new discipline like GEO, start with a diagnostic and measurement before investing.

Working on something like this?

Download my CV or message me on LinkedIn.

Related projects

FMCG

Global Website Programme (45 markets)

One redesigned platform rolled out to 45 markets through a Master site and eight waves.

45 markets · Europe, LATAM, APAC, MEA2022 – present
  • Website redesign
  • Enterprise rollout
  • Multi-market

Plan & delivery · How I ran it

FMCG

Global Food & Lifestyle Platform

A community webapp for a premium beverage brand, scaled from 4 to 8 markets.

8 markets · 4 continents2023 – present
  • Website redesign
  • Multi-market
  • Community platform

Plan & delivery · How I ran it

Personal lab

Your Notion Creator

An independent Notion product business: 25 templates, 50,000+ downloads and a 4.9/5 rating.

Independent digital product business · Notion templates, custom workspaces, AI agentsOct 2023 – present
  • Digital product
  • Notion
  • Workflow systems

Plan & delivery

All projectsHome