AI Enablement with Claude Cowork
How Hamilton and Waikato Tourism is turning AI chat windows into repeatable marketing workflows.
The Client
Hamilton & Waikato Tourism (HWT) is the official Regional Tourism Organisation for the Waikato, providing regional tourism services to Hamilton City, Waipā, Waikato District and Matamata-Piako district councils.
The team promotes the region to domestic and international leisure and business visitors and works with the tourism industry to support a thriving visitor economy. From the magic of Hobbiton Movie Set and Hamilton Gardens to Raglan's surf beaches and unique regional experiences, the HWT team showcases what makes the mighty Waikato a destination worth discovering.
Like most teams, they were already using AI. Also like most teams, they were using it one conversation at a time. Open a chat, ask for a draft, close the chat, start again tomorrow.
The Challenge
Natasha Chevtchenko leads digital marketing within HWT's small team. She produces six to ten posts a week across social channels that each have a different audience and voice, written for two brands: Mighty Waikato for visitors, and HWT for industry, members and stakeholders. Reporting takes her about a day, pulling and interpreting numbers from Google Analytics and Meta while the platforms keep changing underneath her.
She had taught herself AI by using it. With no training and no developer, she had built custom AI workflows, one for LinkedIn posts, and an agent wired into Asana to sort out her tasks and set her day. Every attempt ran into the same wall:
Every tool started from nothing, and none of them knew anything about each other.
The brief, the personas and the brand guidelines had to be re-explained in every session.
The copy still came back off brand, so the time saved drafting went straight back into rewriting.
Everything Natasha and her team had built lived in a browser tab, in tools that could not see their files or each other's work.
She wanted practical advice on three things: what agentic automation actually looks like in a marketing workflow, what it takes to get there, and whether any of it is possible with no developer and no plan to hire one. Natasha was after a single setup that already knew the brand, could reach the team's files and could be built and run by a marketer.
"I’d been trying to understand it on my own, but realised I needed to develop my knowledge further.”
The Journey
Enlighten Designs' Principal Technologist, Sam McKoy, worked directly with Natasha on why her existing setup kept hitting the same wall.
The first move was to diagnose why the existing tools were stalling. The AI could produce copy; the challenge was each session lacked the brand guidance, audience information and task details needed to make it consistently useful. Natasha had to provide context repeatedly. The opportunity was to make it available whenever she needed it.
Sam also showed Natasha his own everyday use of Claude, and how he takes the repetitive parts out of his week using Claude, Claude Cowork, connectors and skills. Everything he demonstrated was something he had built for his own work.
The Solution
From there, the two of them worked through the four building blocks that turn Claude from a chat window into working infrastructure, each one mapped against Hamilton & Waikato Tourism's own workflows rather than a demo:
A written brief Claude reads every time. So it already knows the organisation, the region and the brand guidelines before anyone types a word. The context gets written down once, not re-explained daily.
Skills. Repeatable instructions for the tasks that come round every month, written once and reused, so the tenth LinkedIn caption is as good as the first.
Projects. Keeping the work for a campaign together, with its own context, so nothing gets lost when someone else picks it up next month.
Scheduled tasks. Work that runs without anyone opening a laptop. That is where time is returned for work needing personal input.
Because every block was worked against the team's own jobs, the question was never "what could this do" but "which of these is worth doing first".
Enlighten did not take the work away. Sam gave Natasha the four building blocks, and Enlighten Designs Marketing Associate Drishti Ratna showed her what they look like inside a marketing role, so she could apply them to the rest of her work herself.
"I came in thinking we were already doing this fairly well. I left with a list of things we should have set up a year ago."
"It gave me a great guide on where to start and what to do next."
The Results
Natasha moved to the paid plan within a week, wrote her first skill and put her first scheduled task into production. Both are still running. The time savings outlined below reflect improvements in repetitive, time-consuming tasks, allowing the team to redirect time towards other priorities and activities adding value to the region.
Reporting. The monthly report that took a full day, pulling and interpreting numbers from Google Analytics and Meta by hand, now takes around 3 hours. Roughly 60% less time spent on the task, freeing up around 7 working days a year to focus on analysing performance, identifying insights and applying those learnings to future marketing activities.
Content. Of the 6 to 10 posts a week Natasha produces, her 2 or 3 LinkedIn posts now run through a skill that already holds the brand guidelines, the channel voice and the personas. First drafts take 15 minutes instead of 45. They are now more closely aligned with the brand and channel voice, so they need less editing before final review.
Newsletters. Natasha built dedicated projects for drafting and proofreading newsletters, one per audience. Each project already held the brand’s tone of voice and knew who it was writing for. Proofreading and rewriting supplied content used to take around 4 hours. It now takes about 30 minutes and comes back polished and newsletter-ready. The same projects turn rough notes into polished first copy, so the wider team can send bullet points instead of writing full drafts Natasha would otherwise need to edit and refine, freeing up time to focus on their other priorities. Content preparation that took a full working day now takes about 2 hours.
Work that's ready when she starts. One scheduled task helps organise Natasha's priorities before she starts work, reducing time spent on routine planning by around 6 hours a month and allowing her to focus sooner on the day's key activities.
The context that used to be re-explained in every session now lives in the skill. Nothing about the setup depends on a developer: Natasha built all of it herself, in the week after the session with Enlighten Designs.
She came back with sharper questions too, the kind that only surface once you are building. Could Claude connect safely to the organisation's SharePoint, how should she bring the wider team in, and where should context live, an instruction or a shared skill. Those are the questions of someone building, not someone still deciding whether to start.
AI has helped reduce time spent on repetitive tasks like compiling reports, preparing first drafts and proofreading. Time can now be redirected towards other priorities, including campaign planning, creating quality destination content, improving the website and working with tourism operators across the region. It's about making better use of existing resources, with AI supporting the team's expertise rather than replacing the people, local knowledge and relationships that destination marketing depends on.
What happens next
Natasha is building against the shortlist. The written brief and the skills for the weekly jobs come first, because those pay back fastest.
Enlighten is working through her questions on settings, desktop security, SharePoint and organisation-wide guidelines. That is the groundwork for bringing the wider team on, so the gains sitting with one person start reaching the rest of the team.
We are measuring the next full monthly cycle against the numbers above. The next cycle tells us which of the remaining blocks earn their place, and how much further the content load can move through skills. We will report back with the numbers.
"AI hasn't changed what we're responsible for. It's changed how much of my week goes on production, and how much goes on the work that moves the region forward."
"We were already using AI every day. Enlighten help me make it more useful in my role and showed us how we could bring those benefits to the wider team.”
Project Overview
Client: Hamilton & Waikato Tourism
Sector: Regional Tourism Organisation
Region: Waikato, New Zealand
Team: Six people, one digital marketing lead
Purpose: Claude enablement
Claude products: Claude, Claude Cowork, skills, projects, scheduled tasks, connectors
Features used: Skills, projects, scheduled tasks, connectors
Account Manager: Doug Wilman
Delivered by: Enlighten Designs. Sam McKoy, Principal Technologist, and Drishti Ratna, Marketing Associate
Enlighten Designs has achieved the Select partner tier in the Claude Partner Network Services Track. We help New Zealand organisations move from experimenting with Claude to running on it: enablement, deployment and ongoing engineering support.