Collections: Logistics, How Did They Do It, Part III: On the Move

Collections: Logistics, How Did They Do It, Part II: Foraging

This is the second part of a three part (I, II, III) look at some of the practical concerns of managing pre-industrial logistics. In our last post we outlined the members of our ‘campaign com…

Collections: The Logistics of Road War in the Wasteland

This week, we’re doing another ‘silly’ topic, but this being me, it is a silly logistics topic, because – as the saying goes – amateurs talk tactics, professionals tal…

Misreading as Foraging: How Systems Get Used for Things They Weren't Made For - Astral's Blog

What Happens to All the Stuff We Return?

Online merchants changed the way we shop—and made “reverse logistics” into a booming new industry.

Collections: Bread, How Did They Make It? Part IV: Markets, Merchants and the Tax Man

Thanks to our helpful volunteer narrator, this entire post series is now also available in audio format! As the fourth and final part (I, II, III) of our look at the basic structure of food product…

Collections: Bread, How Did they Make it? Part III: Actually Farming

Thanks to our helpful volunteer narrator, this entire post series is now also available in audio format! As the third part (I, II, III, IV, A) of our look at the basic structure of food production …

Collections: Clothing, How Did They Make It? Part II: Scouring in the Shire

This post is also available in audio form, thanks to the efforts of our volunteer narrator. This is the second part of our four part (I, II, III, IVa, IVb) look at the production of textiles (parti…

A guide to the anatomy of effective commerce agents | Claude by Anthropic

The architecture, latency & cost techniques, and eval practices for agents that make it easier to buy and sell online.

Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems

Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outputs. Agents drown in their own accumulating history while paying a token cost that grows every turn, producing missing recalls within and across conversations. The incumbent response treats this as a storage-and-retrieval problem. We argue that framing is too narrow. Actively managing what an agent holds in mind is a lifecycle, not merely a store: it spans deciding what to remember, extracting and structuring it, choosing the right store per data type, consolidating and forgetting while preserving provenance, deciding what is relevant now, anticipating what is needed next, and compacting context to a budget without losing what matters. In serious production this operates not over a single user but across an organizational scope hierarchy. We name this discipline Agentic Context Management (ACM) and decompose it into five primitives: architecting, ingesting, scoping, anticipating, and compacting & consolidation. We then make the economic case: naive context accumulation grows token cost quadratically in conversation length, crude summarization buys linear cost at the price of an accuracy cliff, and only validated compaction achieves linear cost with preserved fidelity. We describe a reference implementation, Maximem Synap, that realizes the five primitives as a multi-tenant service and reports 92% on LongMemEval and 93.2% on LoCoMo under the configuration detailed in Section 6. We close with dimensions existing benchmarks do not yet capture, latency, token efficiency, and context-rot resistance, and the frontier of decision-level and organization-level context the category points toward.

tonk-labs/carry

Carry — a local-first knowledge tool by Tonk

Research Report 6: Agentic Shopping is Complicated and Contingent

This is the sixth in a series of short reports that help business, education, and policy leaders understand the technical details of working with AI through rig

Collections: Bread, How Did They Make It? Part I: Farmers!

Thanks to our helpful volunteer narrator, this entire post series is now also available in audio format! This essay will hopefully be the first post in a series (II, III, IV, A) covering some of th…

Dark Factories: Rise of the Trycycle – Dan Shapiro's Blog

Companies are now producing Dark Factories – engines that turn specs into shipping software. The implementations can be complex and sometimes involve Mad Max metaphors. But they don’t have to be like…

Squire

the task-sorting assistant for the modern adventuring knight