A recent Harvard study of 718 firms, using the Jellyfish analytics platform, finds that although AI coding assistants and agents increase code volume, this does not translate into a corresponding increase in completed work, partly because AI-generated code increases the workload in later stages of development, particularly code review. By Sergio De Simone
Manju Rajashekhar explains how the actor model solves the complex runtime challenges of production AI agents. By treating agents as distributed systems, he discusses state ownership, message passing, write-through state, and supervision boundaries to manage failures, continuations, and mutable execution graphs, moving agentic workflows beyond fragile demos to resilient architecture. By Manju Rajashekhar
Vercel Labs has released fx, an experimental open-source coding agent written in Zig. It runs as a CLI, a script component, or an embedded library, including a WebAssembly build. Early feedback questioned its model-agnostic claim and a name conflict with an existing tool. Vercel says the project is pre-1.0 and changing quickly. By Daniel Curtis
Docker announced that Harbor, the open-source agent evaluation framework, now works with Docker Sandboxes. This change allows each evaluation task to run in its own microVM. So, instead of sharing a container, tasks are isolated for better performance By Claudio Masolo
This article presents a disaster-recovery analytics workflow in which an AI agent generates constrained SQL or Python, DuckDB computes reproducible facts from Parquet, and the agent interprets the results. It explains the determinism split, replayable analysis, and four signals for deciding when an embedded engine is sufficient or a managed lakehouse is justified. By Peihao Yuan
