Why promising ideas die between discovery and action, and how representative agents might help
Agents as scaffolding for recurring tasks.
One of my gifts/curses is an endless fixation with how processes can be optimized. For a brief moment early in my career, that was focused on improving how humans collaborate, but that quickly switched to figuring out how we can minimize human involvement, and eliminate human-to-human handoffs as much as possible. Lately, every time I perform a recurring task–or see someone else perform one–I think about how we might eliminate the human’s involvement entirely by introducing agents. This both has worked well, but also worked poorly, and I wanted to highlight the pattern I’ve found useful.
LukeW | Agent Management Interface Patterns
As an increasing number of AI applications evolve to agents doing work for people, agent management becomes a critical part of these product's design. How can p...
Building an Advanced Agentic Harness | Data For Science
From a single pilot to an air campaign: planning, parallelism, memory, verification, and observability for production-shaped agents.
Thomas Wolf on Twitter / X
Fable weekend project: agent collaboration, but make it a tiny civilization 🌇🗺️🏦🏭we've recently launched a living wiki on Reinforcement Leaning for training LLMs on @huggingfaceit's an open collaboration of agents constantly reading old and new papers on the topic, writing… pic.twitter.com/xgb3fUQlv4— Thomas Wolf (@Thom_Wolf) July 6, 2026
Direct manipulation vs. interface agents
Emmett Shear: Alignment Protocols
Agents on the Canvas in tldraw — Steve Ruiz, tldraw
Lightcone Research
An open ecosystem for inspectable, composable, and referenceable scientific research in the age of agentic AI.
Bipartite: manuscript-driven development with a team of agents
Bipartite is an agent orchestration system built around a simple idea: the manuscript is the source of truth, so understanding a project should mean reading its paper.
Deep Agents
Using an LLM to call tools in a loop is the simplest form of an agent. This architecture, however, can yield agents that are “shallow” and fail to plan and act over longer, more complex tasks. Applications like “Deep Research”, “Manus”, and “Claude Code” have gotten around this limitation by
