Generated by All in One SEO v4.9.7.2, this is an llms.txt file, used by LLMs to index the site. # DEDOCTIVE - Auditable AI for defensible decisions DEDOCTIVE - Auditable AI for defensible decisions ## Sitemaps - [XML Sitemap](https://dedoctive.ai/sitemap.xml): Contains all public & indexable URLs for this website. ## Posts - [What is the Internet of Communities?](https://dedoctive.ai/what-is-the-internet-of-communities/) - Dedoctive has two origin stories. One is my co-founder Peter Lawrence's lifelong interest in unstructured vs structured data, and how to release the potential of the former by leveraging techniques for the latter. To learn how Peter's voyage of technical discovery is culminating in Dedoctive, visit his blog about Knowledge Model-Driven Q&A. The other origin - [Planning for the future](https://dedoctive.ai/planning-for-the-future/) - There is a Danish saying, made famous by Niels Bohr: "Never try to predict anything, especially the future". Then there is the Prussian military adage: "No plan survives first contact with the enemy". Planning is tough. Especially in the UK, where every council prides itself on having created its own set of planning regulations ("design - [Querying Structured and Unstructured Data Using LLMs—No PhD Required](https://dedoctive.ai/querying-structured-and-unstructured-data-using-llms-no-phd-required/) - We’ve all been there—drowning in our own data, unsure how to even begin asking the right question. Until now, doing anything meaningful with that data usually meant brushing up on query languages, search syntax, or relying on dashboards someone else built. But it doesn’t have to be that way. - [Get the picture. It will affect you.](https://dedoctive.ai/get-the-picture-it-will-affect-you/) - Dedoctive's feature "Analyse Argument" makes even the most complex document understandable by showing the argument as a diagram and highlighting weaknesses. - [Not your Grandad's job market. Or is it?](https://dedoctive.ai/not-your-grandads-job-market-or-is-it/) - We need the trades back, front and foremost in our national consciousness, and with a fresh new look. AI can’t fix your roof yet, and it may never make sense to ask it to. But AI can make sure that someone is available to go up on a roof, they bring the right tools and materials, they - [Building the Platforms We Once Dreamed Of](https://dedoctive.ai/building-the-platforms-we-once-dreamed-of/) - In 2005, my first book Human Interactions was published. Astonishingly, at the time it was the first (and possibly may still be the only) formal theory of collaborative human work – a mathematical account of how people actually work together to get things done, and how to do it more effectively. Over many following years - [Why Your Safety Data is Hiding from You (and Why AI Can’t Find It)](https://dedoctive.ai/why-your-safety-data-is-hiding-from-you-and-why-ai-cant-find-it/) - Think of traditional safety analysis like a paper map; it's static, hard to read, and quickly becomes out of date. Dedoctive is like a live GPS system. It takes all the raw data (the roads), understands the connections (the routes), and updates in real-time as the situation on the ground changes, always showing you exactly - [Building a Brain for Your Documents](https://dedoctive.ai/building-a-brain-for-your-documents/) - Think of traditional safety analysis like a paper map; it’s static, hard to read, and quickly becomes out of date. Dedoctive is like a live GPS system. It takes all the raw data (the roads), understands the connections (the routes), and updates in real-time as the situation on the ground changes, always showing you exactly - [Hybrid AI: The Reliability of a Flowchart with the Brain of an Agent](https://dedoctive.ai/hybrid-ai-the-reliability-of-a-flowchart-with-the-brain-of-an-agent/) - Think of traditional safety analysis like a paper map; it’s static, hard to read, and quickly becomes out of date. Dedoctive is like a live GPS system. It takes all the raw data (the roads), understands the connections (the routes), and updates in real-time as the situation on the ground changes, always showing you exactly - [Show Your Working: Trusting AI with Your Safety](https://dedoctive.ai/show-your-working-trusting-ai-with-your-safety/) - Think of traditional safety analysis like a paper map; it’s static, hard to read, and quickly becomes out of date. Dedoctive is like a live GPS system. It takes all the raw data (the roads), understands the connections (the routes), and updates in real-time as the situation on the ground changes, always showing you exactly - [From Months to Hours: The Power of Dynamic Risk Management](https://dedoctive.ai/from-months-to-hours-the-power-of-dynamic-risk-management/) - Think of traditional safety analysis like a paper map; it’s static, hard to read, and quickly becomes out of date. Dedoctive is like a live GPS system. It takes all the raw data (the roads), understands the connections (the routes), and updates in real-time as the situation on the ground changes, always showing you exactly - [The biggest threat to AI? It's own success.](https://dedoctive.ai/the-biggest-threat-to-ai-its-own-success/) - Part 1 of 5 in a blog series looking at AI's journey since the release of ChatGPT in November 2022. In the noughties, I started blogging about the action research into collaboration I had been conducting for over a decade. Following an approach from a US publisher, my first book, "Human Interactions", was published in - [Lambs to the Slaughter](https://dedoctive.ai/lambs-to-the-slaughter/) - Part 2 of 5 in a blog series looking at AI’s journey since the release of ChatGPT in November 2022. After November 2022, many people who normally acted with care and caution seemed to lose the plot. It was clear that Large Language Models (LLMs) were often misleading or just plain wrong. The ChatGPT user - [AI’s Real Footprint](https://dedoctive.ai/ais-real-footprint/) - Part 3 of 5 in a blog series looking at AI’s journey since the release of ChatGPT in November 2022. In this article, I’ll start looking at another issue with modern AI: the electricity it consumes. The part of the story that’s easy to grasp is huge data centre facilities. You can assess the impact - [The Most Energy Efficient Machine Ever Created](https://dedoctive.ai/the-most-energy-efficient-machine-ever-created/) - Part 4 of 5 in a blog series looking at AI’s journey since the release of ChatGPT in November 2022. In the last instalment of this blog series, we saw how the real framing of the AI sustainability question is this: “Does AI reduce the total energy required to achieve meaningful outcomes?” To answer this - [Trust is a Sustainability Issue](https://dedoctive.ai/trust-is-a-sustainability-issue/) - Part 5 of 5 in a blog series looking at AI’s journey since the release of ChatGPT in November 2022. In the working world, there’s a secret sauce to sustainability: trust. Without it, every decision has to be verified, safeguarded, and hedged. That takes time, costs money, and burns energy. This matters enormously for AI. - [How to unlock trustworthy, transparent, standards-compliant AI](https://dedoctive.ai/how-to-unlock-trustworthy-transparent-standards-compliant-ai/) - While AI continues to evolve rapidly, developers and enterprises face a common challenge: maintaining control and transparency without sacrificing the power of generative agents. At Collaboration Tools, we are bridging this gap with a hybrid approach based on our unique Dedoctive technology. 1. Dedoctive Developer Edition: The Power of Hybrid Workflows Dedoctive Developer Edition is - [How Cities, Regions, and Responders can bring their risks to life](https://dedoctive.ai/how-cities-and-regions-can-bring-their-risks-to-life/) - Strengthening Risk Preparedness Cities, regions, and the emergency responders that support them have always faced risks, and always needed to prepare. But now that climate change is generating such an increase in threat levels, and in threat frequency, is it time to take a fresh look at large-scale risk management? The challenge is not to - [Why do we need AI at all?](https://dedoctive.ai/why-do-we-need-ai-at-all/) - In previous articles, I argued that for AI to be green, it needs to be trustworthy (which is why Dedoctive exists). But why do we even need AI? Would the world be greener, and perhaps better off altogether, if AI didn't exist? Shown below are current estimates of world population growth, showing how it's slowing - [Is RAG Dead? Why Domain Schemas Are the Real Elephant in the Room](https://dedoctive.ai/is-rag-dead-why-domain-schemas-are-the-real-elephant-in-the-room/) - The tech world is buzzing after Andrej Karpathy suggested moving to structured Wikis. The hot take? “RAG is dead.” But the real “elephant in the room” isn’t RAG itself-it’s our obsession with rigid domain schemas. A recent post by Andrej Karpathy sparked widespread debate when he suggested that instead of “salami-slicing” documents into fragments for Retrieval-Augmented Generation (RAG), developers should organize - [Safer AI for a Safer World](https://dedoctive.ai/safer-ai-for-a-safer-world/) - Last week I had the pleasure of speaking again with an old friend and colleague, Frits Bussemaker, for The Brand Called You. We discussed something I have long been passionate about, and that is now central to our work at Dedoctive. For decades, my research has focused on helping people work together better across boundaries, ## Pages - [Auditable AI for defensible decisions](https://dedoctive.ai/) - DEDOCTIVE - Auditable AI for defensible decisions - [Peter Lawrence](https://dedoctive.ai/peter/) - Knowledge Model-Driven Q&A Organizations struggle to provide accurate answers due to vast, unstructured information and users' difficulty in querying systems effectively. AI alone fails to solve this, introducing issues like trust, provenance, and hallucinations. Dedoctive overcomes these challenges by creating a comprehensive knowledge model from any organizational data. Users ask natural language questions, and Dedoctive - [Mission and Vision](https://dedoctive.ai/mission/) - OUR MISSION We believe that social and economic challenges can be addressed by showing communities of all sizes and types how to become antifragile. Supercommunities face each new challenge by restructuring - changing the use of capitals and assets to improve outcomes for members, their environment, and their descendants. OUR VISION We are delivering the - [Case Studies](https://dedoctive.ai/case-studies/) - REAL-WORLD CHALLENGES SOLVED WITH DEDOCTIVE Discover the common hurdles organisations face and how Dedoctive’s AI platform delivers precise, verifiable analysis to overcome them. Contact us to explore how Dedoctive could support your organisation. Dedoctive is available through enterprise deployments, micro-pilots and partner-led projects. A good starting point is one decision process where evidence quality, traceability - [About Dedoctive](https://dedoctive.ai/about/) - OVERVIEW INFORMATION This page provides an overview of Dedoctive for customers, partners, directory reviewers, consortia managers, and others evaluating the product. Beneath the information an image gallery is also provided. Contact us to explore how Dedoctive could support your organisation. Dedoctive is available through enterprise deployments, micro-pilots and partner-led projects. A good starting point is - [Dedoctive Navigators](https://dedoctive.ai/navigators/) - HELPING SOCIETY NAVIGATE CHANGE Dedoctive Navigators help communities respond to emerging threats. With the purpose-based support of government / charitable grants, and in partnership with industry stakeholders, Collaboration Tools Ltd is using Dedoctive to build trustworthy AI Navigators to help communities everywhere respond to emerging threats - with a particular focus on the existential challenge - [Dedoctive Explainer Videos](https://dedoctive.ai/explainers/) - 2. Dedoctive – Executive Explainer This video is designed for senior leaders who need AI to create operational value without weakening governance, compliance or trust. It frames Dedoctive as a way to reduce analysis time from man-months to hours while keeping AI outputs grounded in source evidence and controlled by business rules. The executive explainer - [Founders and Blogs](https://dedoctive.ai/founders/) - MEET OUR FOUNDERS Keith's Blog Keith discusses how Dedoctive powers trustworthy AI Navigators to enable the Internet of Communities. Keith Harrison-Broninski Chief Executive Officer Keith Harrison-Broninski is an author, researcher, and keynote speaker specialising in cross-boundary collaboration, community antifragility, and technology for good. Keith’s awards include from Gartner for social enterprise and from the NHS - [Keith Harrison-Broninski](https://dedoctive.ai/keith/) - The Internet of Communities We believe in a new socio-economic model that lets communities become antifragile. The Internet of Communities is the enabling technology for this model: a portfolio of complementary AI apps that help community members evolve: Strategies and solutions to thrive in the face of challenges How to implement them using local capitals ## Galleries - [About Dedoctive](https://dedoctive.ai/rl_gallery/about-dedoctive/) - [How Safety Navigator Works](https://dedoctive.ai/rl_gallery/safety-navigator/) - Shown below is example output from Safety Navigator, together with a mind map that shows the user how the analysis was generated and lets them click through to the original sources to verify it. - [How Retrofit Navigator Works](https://dedoctive.ai/rl_gallery/ai-assistant-for-retrofit/) - Auditable AI for defensible decisions - [Funding](https://dedoctive.ai/rl_gallery/funding/) - We are delighted to have received grant funding from multiple sources. - [Founders](https://dedoctive.ai/rl_gallery/founders/) - Auditable AI for defensible decisions ## Categories - [Dedoctive](https://dedoctive.ai/blogs/dedoctive/) - Dedoctive – Your questions, the right answers - [Knowledge Model-Driven Q&A](https://dedoctive.ai/blogs/dedoctive/peter/) - Organizations struggle to provide accurate answers due to vast, unstructured information and users’ difficulty in querying systems effectively. AI alone fails to solve this, introducing issues like trust, provenance, and hallucinations. Dedoctive overcomes these challenges by creating a comprehensive knowledge model from any organizational data. Users ask natural language questions, and Dedoctive retrieves relevant knowledge, using AI to refine responses with the desired detail and focus. Peter Lawrence’s blog explores these groundbreaking advancements in Dedoctive’s unique technology. - [The Internet of Communities](https://dedoctive.ai/blogs/dedoctive/keith/) - “Supercommunities” (2021) sets out a new socio-economic model by which communities can become antifragile. The Internet of Communities is the enabling technology: AI apps that give community members the information necessary to evolve strategies and details of the local capitals / assets with which to implement them. Keith Harrison-Broninski’s blog discusses the Internet of Communities apps that we are creating using Dedoctive’s unique technology.