The resource I used was The Renaissance of the Essay? (LSE Impact Blog) and the accompanying Manifesto which Claire Gordon (LSE) and I led on with input from colleagues from LSE and here at King’s. I wondered how easily I could make the manifesto a little more dynamic and interactive. In the first instance I was thinking about activating engagement beyond the scroll and secondly thinking about text inputs and reflections.
“turn this into an interactive web-based and shareable resource”
…I tweaked (using natural language) the underpinning code so that the boxes were formatted better for readability and to minimise scrolling and the reflection component went from purely additional text to a clickable pop-up. I need to test with a screen reader to see how that works of course.
I then experimented with adding reflection boxes and an export notes function. It took 3 or 4 tweaks (largely due to copy text function limits in browser) but this is the latest version. Obviously with work this could be made to look nicer but I’m impressed with initial output and ability to iterate and for functionality in very short time (about 15 mins total).
For the Claude one I thought I’d try having all those features including in-text input interaction from the start. Perhaps that was a mistake, because although the intial output looked great, the text input was buggy. 13 iterations later and I got the input fix. However, then the export function that I’d added around version 3 had stopped working so I needed to do a lot more back and forth. In the end I ran out of time (about 40 mins in and at version 19) and settled on this version with the inadequate copy/ paste function.
It’s all still relatively new and what’s weird about the whole thing is the continual release of beta tools, experiemtnal spaces and things that in any other context would not be released to the World. Nevertheless, there is already utility visible here and no doubt they will continue to improve. I sometimes think that my biggest barrier to finding utility is my own limited imagination. I defintiely vibe off seeing what others have done. This further underlines for me the difference and a significant problem we have going forward. ‘Here’s a thing.’ they say. “What’s it for?’ we ask. ‘I dunno,’ they shrug, ‘efficiency?’
‘Deploying AI agents’ sounds so hi tech and futuristic to (non Comp-Sci) me whilst weirdly also resonating of classic 60s and 70s TV shows I loved as a kid. I have been fiddling for a while on the blurred boundaries between LLMs and Agents, notably with Claude, but what appealed when I first saw Manus was the execution of outputs seemingly beyond what Claude can manage. Funnily enough it looks quite a bit like Claude but it seems it is actually a multi-tool agent. I pretty much concur with the conclusion from the MIT Tech review:
While it occasionally lacks understanding of what it’s being asked to do, makes incorrect assumptions, or cuts corners to expedite tasks, it explains its reasoning clearly, is remarkably adaptable, and can improve substantially when provided with detailed instructions or feedback. Ultimately, it’s promising but not perfect.
Anyway, I finally got in, having been on the Manus waitlist for a while. Developed by Chinese startup Monica, it is an autonomous AI agent capable of executing complex online tasks without ongoing human input and created something of a buzz. TL:DR: This is the initial output from first prompt to web-based execution. The selection and categorisation need honing but this in my view is an impressive output. The second version after addition of a follow up prompt.
Longer version:
I wanted to see what I could get from a single prompt so decided to see if it could build a shareable, searchable web page that curates short how-to videos (under five minutes) by higher education educators demonstrating uses of Generative AI. I began by requesting Manus to collect and cluster videos showing how AI is applied in teaching, assessment, feedback, and research (Natural Language Prompt). Manus responded immediately by creating a structured project directory and initiating web searches to identify relevant video content, starting with collections from institutions like Notre Dame and Harvard (which it didn’t get beyond in the first iteration).
Once videos were sourced, Manus automatically filtered them to ensure they were under five minutes in length (but failed to note that one wasn’t a video and others linked to same page where they were already curated!) and produced by educators in the higher education sector (this it did get right). It then categorised them by thematic area (Teaching, Assessment & Feedback, AI Literacy, and Research but the categrosations were not always spot on) while also tagging institutional affiliations (mostly OK). The tagging and filtering work pretty well but the actual sourcing is very limited in that first iteration. A metadata database was created to support an interactive interface, allowing users to search videos by presenter, title, or description and filter by category or institution. Manus built this interface and deployed the collection to a live web page: https://cjubrvkx.manus.space. It took about 15 minutes. Iteration is by natural language prompting for fine tuning.
The initial prompt from me and the start of the executaiton of the processes
After launch, I expanded the scope by asking Manus to include contributions from additional individuals and institutions- I threw in my old buddy Dr. Gerhard Kristandl (Dr GeeKay) who I know has a YouTube channel, I added me- Martin Compton (without any additional info) and it found relevant content from each of us. The other three potential souces I threw in reaped no reward though. This is the reasoning:
I searched for content from Tadhg Blommerde, University of Sydney, and Monash University as well, but most of their videos exceeded our 5-minute duration criteria. I’ve documented all findings in the data directory for reference.
Manus resumed its asynchronous task execution, searching for and integrating further video content into the existing framework enabling me to publish a second version . So the output works, I would need much more thoughtful prompting to get it how I want it and, tbh, there are better ways of curating YouTube content but the principle is what interested me and the output is remarkable given the stages and processes it went through.
It was a privilege to offer reflections at Professor Cathy Elliott’s inaugural lecture, Rewilding the University recently. Her lecture was more than a celebration of an academic career: it was also a call to action. A provocation. A gentle but insistent reminder that education (and nature and the world!) does not need to look the way it does now. A packed lecture hall listened intently to Cathy’s arguments, ideas and jokes: it was a tough act to follow. Cathy said she hardly ever lectures but a skillful lecture is a thing of joy and is utterly compelling and we were lucky to witness one. Here we share some reflections on Cathy’s ideas and how they have helped shape aspects of our own.
Cathy made clear that rewilding is not a metaphor of neglect or abandonment, but of restoration, connection and flourishing. It recognises that overly managed systems, whether ecological or educational, can become depleted, homogenous and fragile. In both cases, monoculture and rigidity are warning signs: what Cathy referred to as ‘command and control’. The invitation we heard was to value and support diversity, likewise in both nature and education, to value what is often dismissed, and to allow for the possibility of unpredictable, unmeasurable growth.
This vision has shaped how we think about education and how we’ve each worked together with Cathy. Our own relationships, as a fellow academic (with similarly unconventional paths to current roles) and as a student (who had been disillusioned by educational experiences to the point of encountering Cathy’s course), and now as authors, as collaborators, is a component of the network that Connie has described as mycelial: Like subterranean fungal connections but nourishing ideas, allowing knowledge to travel, and making future growth possible. Like mycelium in forest ecosystems, these relationships and ideas remain largely invisible to the untrained eye, but they are foundational. They remind us that learning does not happen in isolation, but in intricate, collaborative webs.
When students sign up for Cathy’s Politics of Nature class, they often don’t fully grasp the lasting impact it will have on them. A friend once told Connie, “A Cathy Elliott module will change your life,” and while the statement may seem grand, it’s not far from the truth. For many, this course didn’t just teach content; it reshaped our approach to thinking, learning, and even our careers. Cathy’s teaching blends critical rigor with intellectual play, making the class a rare space where students can be both creatively curious and academically rigorous. Most importantly, she empowers students to discover their unique intellectual passions, encouraging them to contribute perspectives no one else could, simply because they aren’t anyone else.
Education, when rewilded, becomes an ecosystem. A space where mutual dependence is generative. A space where difference is not simply tolerated but required. It is through this lens that we’ve come to understand projects like ungrading, student co-authorship, and the politics of belonging, not as reforms, but as regenerative acts. These are not surface-level interventions, but shifts in the soil.
One of the most notable aspects of Cathy’s work is her broad intellectual curiosity. She’s not confined to any one field of study — from politics and nature to democracy, development, gender, race, disability and sexuality, Cathy’s academic interests are as diverse as they are profound. In an academic world that often pushes students toward ever-narrower specialization, Cathy’s approach encourages students to break free from this limitation.
Cathy’s teaching has long enacted this ethos. She nurtures students not through control but through trust. Her pedagogy invites learners to bring their whole selves, to make connections across disciplinary and personal boundaries, and to treat knowledge as something to be inhabited, not merely acquired. She encourages risk, slowness, reflection, and relationality which are qualities too often sidelined in institutional discourses of impact, efficiency and performance.
The dandelion is another metaphor Cathy draws on frequently and one we were also drawn to in our appreciation. Often dismissed as a weed, the dandelion (The French is ‘pissenlit’ which really does say everything about its reputation) is in fact a profoundly restorative plant. It detoxifies soil, strengthens roots and nourishes ecosystems. It grows where it is not wanted and flourishes nonetheless. To children, it is a source of wonder, blown seeds, floating wishes,transformation, softness at one time, vibrant yellow before. But to adults, it is a nuisance to be removed. Cathy’s work, like the dandelion, asks us to reconsider who gets to decide what counts as valuable, as beautiful, as worthy. We need to ask ourselves to what extent have we constructed educational systems that we want to be like perfect lawns- predictable, clean, neat and each blade of grass much like the others. Cathy says: ‘don’t cut the grass and plant wildflowers instead!’ This is a literal and metaphorical phrase we can get behind!
This ethos extends into her work on gender, race and sexuality, which consistently challenges the structures that exclude some or may diminish the presence or experience of others. In classrooms, in curricula, in institutional policy, she reminds us in her work that exclusion is never accidental, it is designed. But that also gives us pause for positive reflection: this means they can be redesigned.
What we’ve come to understand through Cathy’s influence, and through our ongoing partnership, is that rewilding higher education is not a metaphorical indulgence, it is a pedagogical imperative. It calls us to rethink the terms of participation, the assumptions of merit, the rituals of assessment, and the conditions under which learning takes place. It also calls for attention to scale: recognising that large transformations begin with small shifts, relationships and new practices.
It felt fitting, then, that the very day after Cathy’s lecture, a special issue of the Journal of Learning Development in Higher Education was published. Co-edited by one of us and containing a piece co-authored by the other, the issue is seeded with many of these same ideas. It features students and a Vice Chancellor; early career ac academics and emeritus professors, reimaginings of assessment, and reflections on academic community that echo and extend Cathy’s provocations. The special issue is a timely continuation of many of the conversations we have had with Cathy, who, unsurprisingly, also has a paper in the special issue and was part of the King’s/ UCL editorial collective.
We both have very different careers and are at very different ends of them! But we share the sense that the rigid, often foreboding and frequently distrustful academy could be rewilded. It doesn’t have to be this way; more importantly, it could be otherwise.
HEducationist 