9 articles tagged
Most design engagements are scoped in screens and delivered as pictures, which is why the handoff falls apart. Since the Design Tokens Specification stabilised in October 2025, the deliverable list has changed. Here are
OpenAI's Assistants API sunsets on 26 August 2026, 36 days from now. The replacement objects do not map one to one, prompts are dashboard-only, and OpenAI will not ship a thread migration tool.
GitHub reduced hosted runner prices by up to 39% on 1 January 2026, yet a macOS minute still costs $0.062 against $0.006 for Linux. Google found 84% of pass-to-fail transitions were flaky tests. Seven rules for a suite
Most AI agent projects fail on value, security and cost, not on the model. Here are five engineering lessons CTOs learn the hard way in 2026, backed by Gartner, MIT and OWASP data, from scoping ROI to controlling token
Building production AI agents taught three lessons the hard way: reliability comes from architecture, the model layer is a commodity you will swap, and evaluation is most of the work. Apple's third-generation Foundation
Five engineering lessons from shipping AI delivery: treat the model as swappable, start with evals not vibes, budget tokens and latency, ground outputs with retrieval, and build security in from day one.
The launch of eCorpIT Insights: five engineering lessons from shipping AI delivery work, covering amplification, evals as infrastructure, human review, token economics, and delivery stability.
Five engineering field notes from building AI features against the iOS 27 betas: the 4,096-token on-device context window, the device split, the Evaluations framework, native tools, and a moving beta target.
Gartner expects over 40% of agentic AI projects to be canceled by 2027, and production agents succeed about 56.6% of the time. Three engineering lessons from shipping enterprise AI agents in 2026.
