Anapoly AI Labs

Category: diary

A public record of the development of our ideas

  • How we flag AI involvement in what we publish

    transparency label: AI-assisted

    Most of what we publish here is written with the help of AI. That’s part of the point. Anapoly AI Labs is about trying these tools out on real work and seeing what they’re good for.

    To keep things transparent, we label every post to show how much AI was involved. The label links to our transparency framework. This doesn’t try to assign percentages. Instead, we use a straightforward five-level scale:

    • Human-only: Entirely human-authored. No AI involvement at any stage of development.
    • Human-led: Human-authored, with AI input limited to suggestions, edits, or fact-checking.
    • AI-assisted: AI was used to draft, edit, or refine content. Human authors directed the process.
    • AI-heavy: AI played a large role in drafting or synthesis. Human authors curated and finalised the piece.
    • AI-only: Fully generated by AI without human input beyond the original prompt. No editing or revision.

    We sometimes add the following:

    • Justification: A brief note explaining why we chose a particular label.
    • Chat Summary: A short summary of what the AI contributed to the piece.
    • Full Transcript: A link to the full chat behind a piece, lightly edited for clarity and privacy, when it contains something worth reading.

    Transparency Label Justification. This post was developed collaboratively. The human author defined the purpose, structure, and tone; the AI assisted with drafting, tightening prose, applying style conventions, and rewording for clarity. The final version reflects a human-led editorial process with substantial AI input at multiple stages.

  • Working Towards a Strategy

    In the last few weeks, we’ve been thinking more clearly about how to describe what Anapoly AI Labs is for and how we intend to run it.

    The idea, from the start, was not to teach AI or to promote it, but to work out what it’s actually good for. Not in theory, but in the real day-to-day work of people like us. We’d do this by setting up simulated work environments (labs) and running real tasks with current AI tools to see what helps, what doesn’t, and what’s worth doing differently.

    To sharpen that thinking, I used ChatGPT as a sounding board. I gave it access to our core documents, including the notes from a deep dive discussion in NotebookLM about what we’re trying to build. Then I asked it to act as a thinking partner and help me write a strategy.

    The result is a good working draft that sets out our purpose, stance, methods, and measures of success. It’s a helpful starting point for discussion. One thing we’ve been clear about from the start: we don’t claim to be AI experts. We’re practitioners, working things out in public. That’s our stance, and the strategy captures it well.

    We’ve published the draft as a PDF. It explains how Anapoly AI Labs will work: how the labs are set up, what kind of people they’re for, how we plan to run sessions, and what success would look like. We now want to shift focus from shaping the idea to working out how to make it happen.

    Download the full document if you’d like to see more. We’d welcome thoughts, questions, or constructive criticism – we’re still working it out.

  • First lab note published

    We’ve just posted our first lab note.

    It documents an internal experiment to refine the custom instructions we use with ChatGPT – what we expect from it, how it should respond, and how to keep it useful across different tasks. The aim is to define a persona for the AI assistant that is more consistent and can adapt to the different types of assistance required of it.

    It’s a good example of how we’re using the Labs: not to explain AI, but to find out what it’s actually good for.

    Read the lab note → Custom Instructions for ChatGPT

  • Sense from confusion

    Early in the process of developing Anapoly Online, our website, I asked ChatGPT to help me create a diary dashboard: a page acting as a central point for diary posts. Amongst other things, I wanted the page to let us select a tag and see only the posts thus tagged. I was unsure how to implement the filltering control this needed, so asked ChatGPT for a step by step guide. The AI confidently produced a procedure, and I put it into action. It soon became clear, however, that the procedure did not reflect the reality of the software I was using. ChatGPT tried to correct things in response to my complaints, but things simply became more confused.

    When all else fails, I said to myself, read the documentation. 

    The software’s documentation proved to be like the curate’s egg: good in parts. Soon, I was as muddled as ChatGPT had been, and it took me some trial and much error to work out the correct procedure for what I wanted to do. 

    Conclusion: current AI can’t create sense out of confusion. That’s still a task for humans.

  • The concept

    Purpose: To model and investigate how non-technical people can make good use of general-purpose AI in their work, using experimentation to understand the strengths and limitations of current AI tools.

    Why does this matter? AI is now widely available, but there’s a credibility gap between hype and reality. Many people are unsure how to use AI effectively.

    What is Anapoly AI Labs? Not a research lab, nor a tech incubator. A collection of small, hands-on labs simulating real-world contexts to explore the practical use of general-purpose AI tools.

    How it works

    A lab is a simulated workspace: a model of an office or home environment, set up to reflect the tasks and tools typical of a real working situation. It is equipped with one or more PCs and other internet-connected devices.

    For some labs, the devices are physically co-located in one office, together with a large, touchscreen display. This setup is designed for when we want better interaction through face to face contact and shared viewing of experiments. In other labs, the devices may be distributed over two or more locations for remote working.

    For all labs, digital files are held in cloud storage. Standard software such as Microsoft Office is used to create and edit documents, manage data, communicate by email, and support typical workflows. General-purpose AI tools like ChatGPT, Perplexity, and NotebookLM are accessed online.

    The participants in a lab carry out realistic tasks in a simulated working context – researching a topic, drafting a proposal, analysing correspondence, writing a report – just as they might in their professional life.

    To create a lab, we configure the physical and digital parts to suit its purpose. This involves connecting the equipment to a dedicated area of file storage whose content is tailored to the work context being modelled by that lab. Thus all documents, data, and outputs in a lab are context-specific and separate from those in other labs.

    What Makes It Different? This isn’t a course, a product demo, or a sales pitch. It’s a testbed. The emphasis is practical: hands-on exploration of what general-purposeAI tools can and can’t do when pointed at everyday work.

    Intended audience: curious professionals, small business owners, writers, and community actors – anyone who works with words, data, or decisions.

    Mode of Operation: Small, in-person, hands-on sessions. Sometimes co-located, otherwise working remotely.

    Outcomes: Better understanding of what AI can and cannot do in everyday contexts. A growing library of real examples and honest reflections. A trusted local presence in the AI literacy landscape.

    Founders’ position: Experienced, local professionals not selling AI services but exploring their use. Not trying to be experts, but honest, curious testers of what’s actually useful. Hoping to pass on the baton to a younger team.

  • home

    Anapoly Notebook

    The public notebook for Anapoly AI Labs

    Anapoly Notebook is where we document our experiments in the day-to-day use of general-purpose AI. We reflect on what works (and what doesn’t), and share our thinking as it develops. You’ll find lab notes, use cases, and a diary that provides a narrative thread through our thinking and development. This is how it all started.

    Tag cloud

    acclimatisation lab agentic ai tools analogy briefing notes chatgpt chatgpt-5 collaboration concept context context-engineering context design contextual scaffolding contract-first credibility culture ethics ethos framework human-AI interaction instructions lab design lab ideas lab setup LLM model comparison monetising notebooklm obsidian participant roles prompt prompting quality regulation sandbox strategy structured prompting three-layer context model transparency use cases user interface value values worked workflow

    Latest diary entries

  • A pivot

    Our initial idea, prompted by Kamil Banc’s writing on practical AI use, was to run a small, local club. Somewhere people like us could meet in person, experiment with ChatGPT, and see what we could actually do with it. A “non-threatening, friendly environment,” we called it at the time.

    But the concept developed, and the name seemed too cosy. A reference to Google Labs brought up the idea of a lab as a place to experiment with tools and ideas. This resonated, so we pivoted to thinking of ourselves not as conveners of a club but as facilitators of a sandbox: a safe space to try things out and see what works.

    Our sandbox would be friendly and exploratory, but with a clear purpose: to model the use of general-purpose AI tools in everyday working environments. It would enable a number of labs, each modelling a different working situation, where we could try things out, see what helps and what doesn’t, and work out how to get better results.

    Hence Anapoly AI Labs: one sandbox, many lab setups.

    sandbox: a safe play area where computer programs can be used without affecting the operational system; useful for experimenting with or testing new software.

  • Our stance

    Stance: a way of thinking about something, especially expressed in a publicly stated opinion.

    We don’t claim to be AI experts. We’re practitioners exploring AI in real problems faced by professionals like us. We’re testing, documenting, and improving – in public. That’s our value.

  • Initial assumptions

    Having decided that the idea of an AI Club was worth pursuing, Dennis and I co-opted Ray into the initiative and set out its underlying assumptions.These are listed below.

    Assumption: there is a market for an AI Club amongst the local population of active and retired professionals, small business owners, and the like. These people are aware of AI’s potential, curious about it, but unsure how best to make use of it.

    Assumption: the social aspect of our club will make it a suitable, informal setting for people to learn how AI tools can improve the quality and productivity of their work.

    Assumption: Although different people will find different aspects of AI useful, there are some common purposes. These include:

    • supporting personal or professional development;
    • getting more done in less time;
    • creating better quality output;
    • improving the the quality of service offered to others; and
    • saving money.

    Assumption: a face-to-face, small-group format with peer interaction, real-time demonstrations, and a narrative focus will be more appealing than virtual courses or corporate-style workshops.

    Assumption: people will be willing to attend in-person sessions and contribute a modest fee once value is evident. They will think that the experience is more useful, trustworthy, and rewarding than online alternatives.

    Assumption: at present, no equivalent offering exists locally that blends live demonstration, peer learning, and practical AI support with such a low-barrier to entry.

    Assumption: Anapoly can deliver sessions using current, general-purpose AI tools such as ChatGPT, Perplexity and NotebookLM without a costly technical infrastructure, relying on existing facilities and minimal setup.

    Assumption: Anapoly, as a local consultancy run by experienced professionals, will be trusted by the audience and seen as non-threatening, practical, and thoughtful.

  • Exploring the idea with ChatGPT

    Once Dennis and I had come up with the idea of a small, local AI club, I used ChatGPT to help me explore its possibilities. I explained the idea to the AI and began the chat by asking: Is there a market for such a club in Plymouth? The answer was a helpful analysis of the main issues and a qualified yes; but the pitch would need to be “pragmatic rather than evangelical”. We would need to keep things down to earth.

    From there, we explored aspects ranging from possible niche markets to session formats. We talked about why people might want to use AI. We looked at different types of users and what each might want from a club like this.

    The conversation broadened my thinking about the viability of the idea and brought the issues into better focus. What started as a vague idea of “a club for people like us” grew into something I began to think we could actually try.

    As an aside, this research with AI was also research about AI: a simple use case, a small step on my path to AI proficiency.