Blog

Guides, products &
practical AI.

Deep-dives on the tools we build, and hands-on takes on AI and cloud — written to be genuinely useful.

AgentLab: build and ship AI agents in an afternoon, not a quarter

Everyone wants to build AI agents. Almost nobody enjoys the part where you spend two weeks wiring up tools, memory, and guardrails just to find out the idea doesn't work. AgentLab is the low-code playground we built to skip that slog: design an agent on a canvas, watch it reason, score it against real tests, and ship it as an API when it's ready.

Read article 6 min read

FeaturedProduct

Conduit: move files straight between clouds, no downloads, no waiting

Moving data between Google Drive, S3 and other clouds usually means downloading gigabytes and uploading them all over again. Conduit skips that. It moves files straight from one cloud to the other, so terabytes transfer in the background while you get on with your day.

Read article 6 min read

Find what's relevant to you

AI· For builders

Advanced RAG: what to add when basic retrieval isn't good enough

Naive RAG is easy to build and easy to outgrow. It embeds your question, grabs the nearest chunks, and hopes. When that starts returning noise, these are the upgrades that fix it: query rewriting, hybrid search, reranking, and when you need them, GraphRAG and agentic retrieval. Here's what each one does and when it's worth adding.

Read 9 min read

AI· For builders

AI agent memory: how agents actually remember

A language model forgets everything the moment a session ends. So how does an AI agent remember your name, your preferences, and what it did last Tuesday? The answer is a memory system borrowed almost directly from cognitive science: working memory for the now, and episodic, semantic, and procedural stores for the rest.

Read 9 min read

Sales· For leaders

AI for sales: a practical playbook for revenue teams

The AI-for-sales pitch usually oversells one magic tool that closes deals for you. That's not how it works. The real gains come from a specific assist at each stage of the pipeline, from building the list to forecasting the number. Here's what actually moves revenue, backed by what teams are seeing.

Guides, products &practical AI.

AgentLab: build and ship AI agents in an afternoon, not a quarter

Conduit: move files straight between clouds, no downloads, no waiting

Find what's relevant to you

Advanced RAG: what to add when basic retrieval isn't good enough

AI agent memory: how agents actually remember

AI for sales: a practical playbook for revenue teams

What 'AI maturity' really means, and how to assess your team honestly

Build vs buy AI: when to build custom and when to just buy a tool

The CXO's 8-hour AI literacy plan: what leaders actually need to know

The environmental cost of AI: energy, water, and the green-tech response

The future of human-AI collaboration in the workplace

Generative AI in cybersecurity: defending against AI-driven attacks

How local LLMs work: running open-source models on your laptop

How to actually drive AI adoption across your organisation

Building an internal AI policy your people will actually follow

How legal teams are using AI for contract analysis and compliance

LLM security basics: the full threat model

Measuring ROI on AI training: what to track beyond 'everyone attended'

The complete guide to modern OCR: from heuristics to hybrid VLM pipelines

Open-source vs closed AI models: which should you actually build on?

Prompt injection: what it is and how to actually prevent it

How to set up Claude Cowork so your whole team actually uses it

How small businesses can implement AI automation to cut costs

SQL-of-Thought: teaching AI to write correct SQL from plain English

What is MCP? The Model Context Protocol, explained

Why 95% of enterprise AI pilots fail, and the boring reason the rest succeed

How to write a CLAUDE.md (and skills) that actually make AI useful

Prompt engineering vs context engineering: what changed and why it matters

RAG vs fine-tuning vs long context: which one do you actually need?

Semantics vs ontology vs context engine: what they are and when to use each

Spec-driven development: writing the spec before the code with AI

AI detectors don't work, and the em-dash panic proves it

How to make AI-written text actually sound human

Want to write for us?

Give your business the AI edge — trained, or built for you.

Guides, products &
practical AI.