Presentation: The Right 300 Tokens Beat 100k Noisy Ones: The Architecture of Context Engineering
Baruch Sadogursky and Patrick Debois discuss why coding agents fail due to bloated context windows and stuffed prompts. They explain practical context engineering fixes, including lazy-loaded skills, versioned context artifacts, externalized memory banks, and LLM-as-a-judge evals. Software architects & engineering leaders will learn how to turn raw markdown files into reliable agentic workflows. By Patrick Debois, Baruch Sadogursky
Record details
Published: 14 August 2026
Source: InfoQ AI/ML
Category: News
Topics: Agents & autonomy
Retrieved: 15 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Launch of DeepSeek’s Harness marks its strategic pivot towards autonomous agentic AI
SCMP Tech (HK/CN) · 14 August 2026
Künstliche Intelligenz: Anthropic warnt vor »Revierkämpfen« zwischen KI-Assistenten
Der Spiegel Netzwelt (DE) · 14 August 2026
2000 Robotaxis in fünf europäischen Städten: Pony.ai und Uber expandieren
Heise Online (DE) · 14 August 2026
Cyera's Oasis Security Buy Is All About AI Agent Control
Dark Reading (AI security) · 14 August 2026
At Black Hat, AI is helping security pros find threats—and creating new ones
Fast Company Tech · 14 August 2026
Kaseya unveils first agentic IT management platform – turning data into autonomous action
ITWeb (ZA) · 14 August 2026
How to cite this record
ethics.ai (14 August 2026), “Presentation: The Right 300 Tokens Beat 100k Noisy Ones: The Architecture of Context Engineering,” evidence record 19605, https://ethics.ai/record/19605 (originally published by InfoQ AI/ML).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.