A series of essays argues that AI agents do not eliminate the need for human teams but shift their work earlier into the decision-making process, where teams must define what is worth building before …
Measuring individual output like pull requests or closed tickets has become a misleading proxy for value creation now that AI agents can produce code faster than teams can review it, argues a post by …
Companies are losing money and knowledge as engineers individually optimize their own AI agent setups without centralized oversight, creating invisible token spend and siloed expertise. The author arg…
A technical analysis maps emerging AI tools—Tessl, Goose, Archestra, Kestra, Modelplane, RAG, and MCP—onto distinct layers of an agent loop architecture, revealing that while tools will change, the un…
A solo developer using AI agents can out-ship a small team, but working alone creates blind spots because the only thing checking the work is an agent built to agree. The author argues that a team of …
A software development team adopts a 'Spec Session' practice where engineers, product owners, and designers align on a shared mental model of a task before any code is written, aiming to prevent misal…
A pattern called the XY problem is emerging where junior engineers use AI to solve the wrong problem without learning, as AI removes the medium of implementation through which knowledge transfer occur…
Anthropic engineers ship eight times more code than a few years ago, but the team has become so isolated that they now schedule lunches and hackathons to foster interaction. Fiona Fung, who leads the …
A senior engineer observes that AI tools are replacing the first-order conversation about whether code works, but not the second-order judgment about architectural direction and long-term trade-offs. …
The Agentic AI Foundation (AAIF) announced its ambassador program to bring order to the fragmented agentic AI ecosystem, drawing parallels to the early container ecosystem and the CNCF's role in stand…
The traditional Product Owner role is evolving as AI agents and spec-driven development shift engineering processes left, with product thinking becoming a team competency and stakeholder management em…
A software engineer argues that AI tools amplify the quality of human thinking rather than replacing it, warning that teams skipping collaborative planning sessions will produce faster but worse work.…
Most companies integrate AI into development by giving developers AI assistants without changing their process, leading to review bottlenecks. The author proposes shifting engineering work to spec-dri…
A blogger launched a site to collect and structure ideas using AI, aiming for concise yet meaningful posts that spark peer discussion. The site now includes GoatCounter for visitor tracking and Giscus…
Current observability strategies generate noise by instrumenting everything, and proposes an adaptive approach where the system decides what to observe based on its own state. By combining OpenTelemet…
Observability tooling built for humans is unnecessary for AI agents, which need clean, structured data with low latency rather than dashboards or SaaS layers. The OpenTelemetry Collector can route dat…