Learning at the edges of Applied AI—at Deriv
Live Last read · last published · next check
Inside an AI-native development pipeline using specs, Planner and Builder agents, independent verification, GitHub Actions, automated quality gates, and human-controlled production releases.
AI can already write code. The bigger shift is what happens when code stops being the primary artefact of software development.
11–12 August, The Campus at Ampang
A technical analysis of a live Google Ads malvertising campaign abusing Claude AI, Base64-obfuscated shell commands and trusted domains to deliver the MacSync infostealer.
Inside Deriv’s prompt-caching architecture: deterministic context, longer reusable prefixes, and measured cost reduction at scale.
How the Agent Auth Hub uses federated identity and human-context verification to control autonomous tool access across clouds
What employees see as a simple Slack assistant is actually a managed Linux VM with connectors, memory, network controls, and enterprise security trade-offs.
How a discovery agent walks user journeys across web and mobile, finds bugs, proves them with generated tests, and hands confirmed defects to a development agent. No one prompts any of it.
The authentication and secrets management problem nobody in the agentic AI hype cycle is talking about, and the architecture we built to solve it.
Technical analysis of a Rust loader and RAT targeting orgs via compromised vendor communications.
