Omar Solano is an AI engineer at Towards AI in Montréal. He builds LLM applications, retrieval pipelines and agents, and teaches practical AI engineering through workshops and technical resources.[1]
Start with Context Engineering in 2026: Compaction, Memory & Cost →
X · omar_solano1 Background
Solano’s owned biography describes client-oriented LLM applications, fine-tuned models and hands-on developer workshops. He completed undergraduate study at École de technologie supérieure. [1]
Contributions
His joint workshop compares a course tutor’s retained history with compaction policies, measuring answer quality, fact retention, cost and latency. Full cached history wins the reported initial experiments; policy triggering and hardware limits affect interpretation.[3]
Tools, writing & talks
Writing, research & talks
Start here
A joint tutor-architecture and context-policy workshop.
Start with the baseline experiment. Tool calling and retrieval familiarity help; check whether the configured policy actually ran.
Co-presenter and tutor developer[3]- Context Engineering in 2026 — Louis-François Bouchard, Omar Solano & Samridhi Vaid, Towards AIyoutube.com
Across 11 context presets measured on an open source AI tutor, sending the full history beat every compaction technique on recall, cost and latency at once, because rewriting context invalidates the prompt cache that serves most of the tokens.
Catalog workOriginal source