Tarık Şenkal Architecture
5 posts
Architecture8 minCompaction or Reset? Managing Context in Long Agent Sessions
What to do when the context window fills up: context editing, the clear_tool_uses strategy, server-side compaction and full context resets — with a decision rule.
Architecture6 minAgent Harness Design: Generator–Evaluator and Context Anxiety
Why long-running agents wrap up early: context anxiety, why resets beat compaction, the generator-evaluator split and file-based handoff between agents.
Architecture6 minWith a 1M-Token Window, Do You Still Need RAG?
Does a 1M-token window make RAG obsolete? Context rot, the measured token cost of non-English text, and a third option: pushing long context into filesystem tool calls.
Architecture3 minContext Engineering: The Discipline That Replaced Prompt Engineering
Context engineering is the discipline of deciding which tokens earn a place in a limited context window at each step. Context rot, lost-in-the-middle, pruning and summarisation strategies.
Architecture2 minModel Routing and Cascades: Stop Sending Every Task to the Same Model
Routing sends each request to the model whose cost and capability fit it. Cascade architectures, confidence thresholds, escalation paths and measuring the real cost-quality curve.