Vibeleaderboard
← All Intel
Intel / video

Context Engineering in 2026 — Louis-François Bouchard, Omar Solano & Samridhi Vaid, Towards AI

Source
youtube.com
Author
AI Engineer
Date

Context

Shortening an 's conversation history can increase its bill if the rewrite discards useful cached text. In the reported AI-tutor experiments, the presenters found that retaining the full history beat their configurations on cost, latency and recall. They attribute the result to extensive reuse of cached input.

Caching lets a service reuse work on repeated text at a discounted rate; rewriting that text can lose the advantage. The caching documentation explains how reusable prefixes and provider-specific rates affect billing. The tutor result supports checking cache behavior before summarizing by default. When the conversation exceeds the model's input capacity, keeping everything is no longer an available choice.

Terms in this piece · Glossary
  • AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
  • context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
  • context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
  • token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Read the source www.youtube.com
More from AI Engineer
Recommended reads
Comments

Checking sign-in…

Loading comments…