AI memory lock-in works until it blocks your own product
Anthropic merged Claude chat and Cowork memory on August 25, 2026. AI memory lock-in is a moat until it stands between a vendor and its own next product.
Context Portability
The Wire Blog
Practical context engineering for AI agents: how to structure, deliver, and manage the context that determines whether AI systems actually work.
Written by Jitpal Kocher. Every post, guide, and answer grouped by topic is in Learn.
Agentic retrieval techniques that hold up in production
Six agentic retrieval techniques backed by 2026 benchmarks: read enforcement, query decomposition, routing, split routers, verification, and step budgets.
Agentic Retrieval
Pruning context made agents more accurate, not just cheaper
Pruning an agent's tool history raised task completion from 71% to 91.6%. What the summary rescued was not content but the agent's place in its own work.
Context Pruning
What chunk size should you use for RAG?
Studies disagree on the best chunk size for RAG: one found 100 tokens with zero overlap won. What the research supports, and the bigger lever most guides miss.
Chunking
Context window blindness: agents can't see their limits
Context window blindness: four frontier models misjudged their own context size by 43 to 84%. Why compaction drops the wrong things, and what fixes it.
Context Window
Ghost memory: why agents can't tell what's true now
Ghost memory is when old, current, and changed facts sit in an agent's memory and get retrieved together. Deleting loses history. Labeling the edge works.
Epistemic Provenance
Agentic RAG fails before the reasoning starts
A 12,000-trajectory study finds agentic RAG agents finalize answers without reading retrieved evidence. Forcing one read gains up to 19.9 accuracy points.
RAG (Retrieval-Augmented Generation)
JSON mode changes what your model answers
Across 44 language models, asking for JSON collapsed answer diversity: distinct answers fell from 52 to 36 and the top answer rose from 41% to 64% of responses.
Structured Context
Kimi K3's 1M context runs mostly on linear attention
Kimi K3's 1M-token window runs on Kimi Delta Attention: hybrid linear attention with a fixed-size state. Why cheap long context still needs context curation.
Context Window
GPT-5.6 subagents: context isolation in the weights
GPT-5.6 Sol's Ultra mode gives each subagent its own context window. It solves context isolation but not handoff, and it multiplies your token bill fast.
Multi-Agent System