Field notes, primers, and case-tested patterns from Rangle on agentic systems, design systems, frontend, and AI strategy.
Showing 1–11 of 511 posts
Portals have always been about delegation: partners acting for customers, admins acting for their organizations. Agents are the next delegate, and that changes what a portal needs and who should own it.
Customer and Partner Portals
AI made generating work cheap and left checking it expensive. When a team's output outruns its capacity to review, the most experienced people stop building and start clearing a queue that refills overnight. The fix starts with the environment, and the people come last.
Build Engineering Capability
An agent that drafts a communication and an agent that sends it may use similar technology. They do not carry the same responsibility. Six decisions to make before you choose a model, a framework, or a platform.
Ship AI Features
Across regulated industries, the AI roadmap stalls at the same wall: a managed-service stack that cannot host the operational layer agentic workflows need. What sovereign infrastructure means, why AI makes now the moment, and what the actual work looks like.
Agentic Platform Studio
AI has made implementation dramatically faster, but software delivery hasn't sped up to match. The bottleneck didn't disappear, it moved from writing code to everything surrounding it: clarity, alignment, architecture, and validation.
Align Product Strategy
Agentic AI is software that pursues goals across multiple steps using tools, planning, and judgment. What it is, how it works, when to use it, and when not to, from a team that builds it for enterprise clients.
Agentic Platform Studio
73% of enterprises exceeded their AI cost projections this year. The fix isn't rationing tokens. It's changing what you use them for.
Agentic AI
The industry agrees on where developer time goes now: more planning, more review. But that story leaves the unit of work untouched. The real shift is appetite and controls: each builder owning bigger, fuzzier scopes and building the systems that make them safe to trust.
Build Engineering Capability
Anthropic analyzed 400,000 AI coding sessions and found that domain experts succeed almost as often as software engineers. Here's what that means for operations, marketing, and business leaders who haven't considered vibe coding as an option.
Agentic Product Engineering
Five weeks of buildout, 850 pieces of content off Sanity, one engineer plus Claude. What rebuilding rangle.io for agentic search taught us.
Escape CMS & Commerce Lock-In
Your team shipped an AI feature and someone asked if it's EU AI Act compliant. Here's how to figure out if it applies to you, what you'd actually need to build, and how long you have.
Ship AI Features