Ideas worth putting to work.
Practical notes on building software, AI chatbots, and AI agents, and connecting AI to the systems a business already runs.
Smart if-statements: using Jev to route, score and sort work
How a small business could use Jev, a fast typed decision model, to route tickets, score leads and check invoices, with thresholds and a handoff to people.
Read insight → AI ModelsThe open-weight models worth knowing in late 2026
Size, licence and hardware notes for the open-weight model families worth knowing in late 2026, from DeepSeek and Kimi K3 to Gemma 4, gpt-oss and Llama 4.
Read insight → AI Models
Xiaomi MiMo-V2.6-Pro: a phone maker's open frontier model
What Xiaomi's MiMo-V2.6-Pro is, what its MIT-licensed open weights allow, the benchmarks Xiaomi reports, and why most businesses would use it hosted.
Read insight → AI ModelsDeepSeek V4 and V4-Pro: what changed this year
DeepSeek's 2026 releases from its own changelog, what V4 and V4-Pro are, what the MIT-licensed weights mean for a business, and where your data may go.
Read insight → AI ModelsWhat Jev is, and why it never writes a sentence
Jev, TypeSafe AI's first System One model, returns typed decisions with confidence scores, not text. Its claims, its place beside an LLM and open questions.
Read insight → AI Models
Open weight is not the same as open source
Open weight and open source AI are not the same. Learn what model weights are, what the Open Source Initiative requires, and which licence terms matter.
Read insight → Integrations
What we learned connecting a real app to AI through MCP
Lessons from giving AI access to a live business app through MCP, covering permissions, approvals, accurate figures, and protecting sensitive data.
Read insight → IntegrationsHow to Audit a Business Process Before Automating It
How to audit a business process before automating it, with a practical 5-step framework to find bottlenecks, measure ROI, and pick what to automate.
Read insight → Field NotesLearning marketing from a technical starting point
Two technical people share how they are learning marketing by building a thoughtful, AI-assisted process around real conversations and useful work.
Read insight → Learning
Start with the work, not the tool
A practical way to introduce AI to your team: start with work people already know, practice together on small real tasks, and build confidence step by step.
Read insight →