Doing digital learning stuff in Humanities at the University of Manchester | Learning Technology 👨💻 | Education 🎓 | Manchester 🐝 | ADE (lapsed!)
Liverpool, England
Joined November 2017
- Tweets4.1K
- Following719
- Followers322
- Likes452
Pinned Tweet
PODCAST - The new Digital Learning Podcast from the Humanities eLearning Team at the University of Manchester features me talking about @cadmus_io with Jeannie Anderson. Check it out! youtube.com/watch?v=oXodeW-U…
Three Years of GenAI in Education: What Changed Between Derry and Belfast? digitaltardis.substack.com/p…
Graham Holland 🐝 retweeted
In 24 hours, this hall will be flooded with thinkers, builders, and educators. Right now, it's just empty booths and swag waiting for someone.
Tomorrow, that changes. See you here to kick off #InstructureCon2026.
#EdTech #CanvasLMS #Instructure
Graham Holland 🐝 retweeted
stop asking Claude one question and thinking you understand the topic. you don't.
Stanford proved a better way. it's called STORM. peer reviewed. 25% more organized output. open source.
the trick: don't ask one question. ask five. from five different experts.
>the practitioner: what do they know that academics miss?
>the skeptic: what's the strongest counterargument?
>the economist: who profits from the current narrative?
>the historian: what pattern has played out before?
>the academic: what does the evidence actually say?
4 prompts. 5 minutes. no software. no GitHub. just paste into Claude.
single prompts give you what everyone already knows.
STORM gives you what nobody else found.
this article has all 4 prompts ready to copy. pick your hardest topic. paste prompt 1. you'll know more in 5 minutes than people who spent days reading.
Graham Holland 🐝 retweeted
🚨 BREAKING NEWS: I asked Claude to optimize my LinkedIn profile.
He didn’t just “optimize” it.
He transformed it into a profile that recruiters actually notice.
Here are the exact prompts I used:🧵
Graham Holland 🐝 retweeted
BREAKING: CLAUDE can now run your entire social media on autopilot mode like a $700/hour social media manager for free.
Here are 7 CLAUDE prompts that you should try:
Graham Holland 🐝 retweeted
Introducing 30 days of AI.
For the next 30 weekdays, I’m going to share one observation per day from the frontlines of AI.
I have the privilege of co-running an enterprise AI transformation firm, where I experience the edges of this technology, see the biggest challenges the biggest companies are facing, and have deep relationships with companies on the frontier (Anthropic, OpenAI, Lovable, Cursor, Perplexity, Vercel).
I get to live in the future for free, and I want to bring that future to those trying to disrupt themselves before they get disrupted.
There’s just two rules:
1) Each observation is actionable & understandable to the non-technical leader.
2) I can’t miss a day.
Post 1 coming soon.
Greater Manchester AI in Education Day: Insight, Inspiration… and a Few Loose Ends open.substack.com/pub/digita…
Graham Holland 🐝 retweeted
I broke my own rule to never post about AI detection as it is fraught in many ways.
The problem is that if you use AI a lot, you know AI writing on sight, which makes the difficulty of objectively proving that AI use to others very frustrating
I've written my first Substack post!
Stop rewriting documents: use Copilot Create to reshape them instead
digitaltardis.substack.com/p…
University of Manchester hits major sustainability milestone, with Main Campus becoming 100% ‘Zero Landfill’
greenergreatermanchester.com…
Graham Holland 🐝 retweeted
This 2-hour Stanford lecture breaks down how models like ChatGPT and Claude are actually built, clearer than what many people in top AI roles ever get exposed to.
Save this and set aside two hours today. It might end up being the most valuable thing you learn all week.
Graham Holland 🐝 retweeted
Prompt engineering is dead.
Anthropic recently released the real playbook for building AI agents that actually work.
It’s a 30+ page deep dive called The Complete Guide to Building Skills for Claude and it quietly shifts the conversation from “prompt engineering” to real execution design.
Here’s the big idea:
A Skill isn’t just a prompt.
It’s a structured system.
You package instructions inside a SKILL.md file, optionally add scripts, references, and assets, and teach Claude a repeatable workflow once instead of re-explaining it every chat.
But the real unlock is something they call progressive disclosure.
Instead of dumping everything into context:
• A lightweight YAML frontmatter tells Claude when to use the skill
• Full instructions load only when relevant
• Extra files are accessed only if needed
Less context bloat. More precision.
They also introduce a powerful analogy:
MCP gives Claude the kitchen.
Skills give it the recipe.
Without skills: users connect tools and don’t know what to do next.
With skills: workflows trigger automatically, best practices are embedded, API calls become consistent.
They outline 3 major patterns:
1) Document & asset creation
2) Workflow automation
3) MCP enhancement
And they emphasize something most builders ignore: testing.
Trigger accuracy.
Tool call efficiency.
Failure rate.
Token usage.
This isn’t about clever wording.
It’s about designing an execution layer on top of LLMs.
Skills work across Claude.ai, Claude Code, and the API. Build once, deploy everywhere.
The era of “just write a better prompt” is ending.
Anthropic just handed everyone a blueprint for turning chat into infrastructure.
Download the guide here: resources.anthropic.com/hubf…
Graham Holland 🐝 retweeted
"This sounds like AI" is now easily fixable 🤯
There is a new Claude Code Skill that removes signs of AI-generated writing from text using 24 detection patterns.
Just type /humanizer and paste your text.
100% Open Source.
Graham Holland 🐝 retweeted
Cardiologist wins 3rd place at Anthropic's hackathon. Out of 13,000 applications. Built in 7 days by Michał Nedoszytko MD. Coded day and night - in the hospital, in the cloud, while flying from Brussels to San Francisco.
A few years ago, it would have been impossible for a doctor to build this alone in just a couple of days. AI changed that.
The project is called postvisit.ai. It is an AI agentic care platform for patients. Including reverse AI scribe it is a companion that guides the patient from the moment they leave the doctor's office.
Powered by the massive context window of Opus 4.6, it allows patients to explore their full medical history, connected devices, Evidence Based resources and external data sources — all in one place.
Today, the barrier to entry has vanished; even a practicing physician can build an application from scratch.
Graham Holland 🐝 retweeted
You know what the biggest problem with pushing all-things-AI is? Wrong direction.
I want AI to do my laundry and dishes so that I can do art and writing, not for AI to do my art and writing so that I can do my laundry and dishes.
Today on International Day of Women & Girls in Science @WomenScienceDay I'm highlighting Prof Julie Williams CBE, a leading advocate for women in STEMM, and founder of the UK Dementia Research Institute (UK DRI) at Cardiff, one of the UK’s flagship dementia research hubs.
