From managing work to managing context
Context Engineering | Meetup
"Context engineering is the delicate art and science of filling the context window with just the right information for the next step" - Andrej KarpathyLearn about tools, frameworks, and code that is in service of context engineering from practitioners in this space.Dive into the set of strategies fo
Who’s the Admin, Me or Claude?
Credit: Museums Victoria / Unsplash There’s a lot of conversation right now about “context engineering” for dev work; structuring what you feed an LLM so it can do useful things. …
Luke Wroblewski on Twitter / X
If context engineering is the new hotness for engineering, context management is the new UI hotness/challenge for designers. pic.twitter.com/iXNTYnVRIi— Luke Wroblewski (@LukeW) July 10, 2025
The Architect of Constraints: Why Context Engineering Is the Human Skill That Matters
“If I had an hour to solve a problem, I’d spend 55 minutes defining the problem and 5 minutes solving it.” — Albert Einstein
Context Constitution
Today we are releasing the Context Constitution: a set of principles governing how AI agents manage context to learn from experience.
Context Engineering
Context engineering strategies for AI agents: write, select, compress, and isolate context to optimize performance and manage long-running tasks.
The rebel alliance
This blog is co-authored with Zoe Weinberg and Matt Hawes at ex/ante, and is a follow-up to our first blog post on the topic, 'You don't own your memory.' We need an open architecture that puts us in control of our memories while making their exploitation technically impossible. But how will this shift happen? In order to discover possible implementations, we must understand how our data informs LLMs. The three predominant context engineering techniques are prompt design, retrieval-augmented ...
Working Minds: A Practitioner's Guide to Cognitive Task Analysis
How to collect data about cognitive processes and events, how to analyze CTA findings, and how to communicate them effectively: a handbook for managers, tr
REINVENTING ORGANIZATIONS
Based on three years of research, the book Reinventing Organizations describes the emergence of a new management paradigm, a radically more soulful, purposeful and powerful ways to structure and run businesses and non-profits, schools and hospitals.
Understanding memory management
Learn MemGPT memory management techniques for controlling LLM context windows with in-context and external storage.
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.
An LLM wiki changed how I work
And everything else I learned about productivity this year
