Skip to main content
Craft, learnings, and thinking behind the work. From our team
All blogs
All topics
AI
Drupal
Design Process
Culture
JavaScript
DXP
More topics
Quality Engineering
BizTech
Events
Open Source
Podcast
Non-Profits
Healthcare
Higher-Ed
Clear all
AI
How knowledge graphs take RAG beyond retrieval
Retrieval-Augmented Generation (RAG) enhances AI by integrating large language models (LLMs) with real-time knowledge retrieval, reducing reliance on pre-trained data and improving response accuracy. But retrieval alone has limits. Vecto...
AI
Voice activity detection in text-to-speech: how real-time VAD works
Voice Activity Detection (VAD) is the backbone of modern speech systems. In Text-to-Speech (TTS) pipelines, it trims silence, reduces compute, and improves conversational flow. Without VAD, assistants lag, call centres sound robotic, and...
AI
How to run DeepSeek-R1:1.5b LLM on android using Termux
Large Language Models (LLMs) have revolutionized natural language processing, unlocking capabilities that were once unimaginable. However, deploying these models on mobile devices has remained a complex challenge, requiring solutions tha...
AI
What's after ChatGPT? 5 AI shifts that will define the next generation
The race that began with ChatGPT is evolving. Chat interfaces were the first big wave of consumer AI, but the landscape is changing fast. AI is moving beyond general-purpose chat into more specialised, capable systems. As thi...
AI
How we implemented Machine Learning on Slack for detailed analytics and optimized communication
We are living in the age of data and to thrive in this era we need to turn this data into knowledge. Data in an organization is scattered over lots of different mediums, whether in an email, dropbox, or on your Slack. In an attempt to cr...
AI
Where Legal Aid breaks and how AI helps
More people are coming to legal aid — with urgent needs, layered issues, and no time to wait. Housing, custody, immigration, benefits. It rarely fits into one category anymore. And legal aid teams, already stretched thin, are forced to t...
AI
Human-centered AI: aligning tech with human priorities
Every few years, a new wave of technology changes how we work. AI is one of those shifts, but its impact is different because it interacts so closely with the decisions people make—doctors diagnosing patients, farmers planning their crop...
AI
Why legal teams are moving past generic chatbots
AI that’s trained to please, not verify, puts clients, staff, and cases at risk Mainstream chatbots like ChatGPT and Grok are built for conversation, not casework. They often hallucinate sources, invent citations, and avoid saying “I don...
AI
7 potential AI breakthroughs improving legal access
Legal systems shape critical aspects of life and business—from housing and family stability to workplace protections and corporate compliance. In 2025, AI is becoming part of that foundation—not through disruption, but through integratio...
AI
LLM evaluation metrics
Evaluating a language model is a lot like reviewing how a digital platform performs after launch. You wouldn’t just measure if pages load quickly, but also whether users can find what they need easily, the design feels intuitive, and the...
AI
Why Use the AI Vercel SDK? simplifying LLM integration for Developers
Integrating Large Language Models (LLMs) like OpenAI’s ChatGPT, Google Gemini, and Anthropic Claude into web applications has unlocked a new class of user experiences, ranging from chatbots that feel like friends. AI writing tools that h...
AI
AI Guardrails: building safe and reliable LLM applications
Deploying Large Language Models in production without guardrails is like launching a website without security—it might work until it doesn't. Guardrails are control mechanisms that ensure LLMs remain safe, accurate, and aligned with orga...
AI
LLM masking: protecting sensitive information in AI applications
1. Introduction to LLM masking Large Language Models (LLMs) like GPT-4, Claude, and BERT have transformed natural language processing applications, enabling sophisticated text generation, summarisation, and analysis capabilities. However...
AI
Why your AI might be easier to hack than we thought
A groundbreaking study reveals that poisoning LLMs requires surprisingly few malicious documents, regardless of how big the AI gets. Imagine baking a massive cake for thousands of people. You'd think that to ruin it, someone would need t...
AI
Building NextGen design systems with AI assistance
As the digital world grew, design systems became essential allies, bringing consistency and scalability. They helped streamline workflows, unify experiences, and accelerate delivery. Design systems have been transformative in many ways, ...
AI
Model context protocol - the docking hub for AI tools
AI models are getting smarter, but they’ve long worked in silos. Each one typically knows only what’s been hardcoded into its prompt or training data. That’s changing with the Model Context Protocol (MCP), a new standard designed to help...
AI
Choosing the right agentic AI framework: SmolAgents, PydanticAI, and LlamaIndex AgentWorkflows
AI agents have redefined automation, data structuring, and knowledge retrieval, making them essential across industries. From streamlining real-time support to handling large-scale data processing, they’re changing how systems operate. S...
AI
Real-Time Voice Detection with Vector TTS in Gemini Live API
The convergence of Voice Activity Detection (VAD), real-time Text-to-Speech synthesis, and contextual vector retrieval is an important step forward in conversational AI. Picture an AI tutor that waits until you finish speaking before rep...
AI
MiniMax-01: long-context and multimodal AI insights
MiniMax-01, created by MiniMax AI, is an important development in the area of large language models (LLMs), especially when you talk about long-context processing and multimodal AI functionality. MiniMax-01 in Series 2 introduces a...
AI
Simplifying RAG evaluation with Ragas
Retrieval-Augmented Generation (RAG) has redefined how large language models (LLMs) operate, bridging the gap between raw computational power and domain-specific accuracy. RAG systems combine generative capabilities with retrieval ...
AI
Enhancing Claude with In-conversation reasoning - the sequentialThinking MCP server
In today's AI-powered workflows, assistants like Claude offer remarkable capabilities, but certain limitations can disrupt productivity. One significant challenge is accessing Claude's deeper reasoning capabilities without interrupting t...
AI
Supercharge your Drupal editorial workflow with AI content suggestions
Artificial intelligence is steadily moving from experimental add-ons to core enablers of digital operations, and Drupal’s latest update reflects that shift with real clarity. In version 1.2, Content Suggestions becomes part of the natura...
AI
From CMS to AI middleware: how I connected Drupal's content to a custom MCP server
MCP, or Model Context Protocol, is gaining serious traction as organizations race to improve the performance and responsiveness of AI agents. Behind the scenes, many are building their own MCP servers, custom middleware systems designed ...
AI
Supercharge your knowledge management - integrating Obsidian MCP with Claude
Staying organised in Obsidian can feel like a full-time job, especially when your notes start multiplying across projects, ideas, and domains. Imagine you’re working on a long-term research project. You’ve got dozens of notes scattered a...
AI
From trial to tailored fits- AR’s role in eyewear shopping
The process of selecting glasses has long been a mix of trial and error. Rows of frames may catch the eye, but uncertainty about fit and style often leads to hesitation. Virtual try-on technology is transforming this experience. Us...
AI
The Claude you’ll never need to remind: MCP in action
Ever had a deep, productive conversation with Claude—only to lose all that context when you start a new chat? Or wish Claude could remember details about you and your projects from one session to the next? Maybe you’ve wanted Claude to m...
AI
Gen AI and ethics | addressing privacy, bias, and transparency
Amongst all the other things that keep us up at night, one of them has to be the effect that AI has over us and how it’s becoming a significant part of our decision-making, influencing everything from loan approvals to job recruitment.&n...
AI
How GenAI is transforming front-end workflows
As a front-end developer, I have seen a lot of changes this year. A dramatic shift occurred with the arrival of generative AI (GenAI). This shift impacted both clients and developers. On the client side, expectations have risen—the...
AI
Genspark super-agent: the rise of next-generation AI assistants and how it compares to Manus AI
Autonomous AI agents are taking centre stage in 2025. No longer limited to basic automation or scripted interactions, these agents now operate independently, make decisions, and handle complex workflows across diverse domains. Among the ...
AI
Model Context Protocol: the universal AI connector
AI assistants are drafting legal briefs, debugging code, writing emails, and helping manage workflows across companies. But even the most capable models like Claude, GPT-4, or Gemini struggle with one thing: actions! Most AI assist...
AI
Harnessing AIBrix for business-grade Generative AI
A technical overview of AIBrix Generative AI is reshaping industries, from customer service to content creation. As organisations adopt these applications, they face a common challenge: how to build AI infrastructure that scales smoothly...
AI
The role of AI in shaping public health
From assisting with surgeries and pharmaceutical development to improving patient communication and disease tracking, Artificial Intelligence is shaping how we address public health’s toughest challenges all while transforming care deliv...
AI
How AWS is reimagining AI integration with Model Context Protocol
I was deep in another AI research rabbit hole. YouTube tabs everywhere, notes piling up, when something unexpected grabbed my attention. A new video from AWS featured three Solutions Architects walking through what could be a breakthroug...
AI
AI Agents: types, architecture, and business impact
AI agents are changing how systems operate. They don’t just follow instructions; they make choices, adapt to situations, and get better with every interaction. For companies building modern, connected workflows, that shift moves automati...
AI
Create your own AI agents for Drupal Canvas
Build a custom AI agent in Drupal Canvas to score news article engagement and suggest readability improvements.
AI
Building simple & effective prompt-based Guardrails
Build simple, effective prompt-based AI guardrails to prevent hallucinations, improve relevance, and create safer, more trustworthy RAG and chatbot systems.
AI
EventHorizon: the Drupal code intelligence app that changes how we analyse codebases
Analyze Drupal codebases smarter with EventHorizon, a code intelligence app that delivers deep insights, faster audits, and better maintainability.
AI
I taught a small AI model to learn my style (and you can too)
A local RAG system that uses reinforcement learning to adapt responses to individual user preferences—personalised output, fast inference, and no fine-tuning required.
Sorry! No items found.
load more
