SAN FRANCISCO, CA / AMES, IA
Tyler Mestery
AI/ML EngineerComputer Science student building agentic AI, ML pipelines, and systems software.ABOUT
I'm a Computer Science student at Iowa State University and an AI/ML Engineer Intern at Cisco, where I build agentic AI systems that turn security intel into mitigation policies. I like working across the stack, from LLM pipelines and RL fine-tuning to the Kubernetes and infra that ships them.Who I am
FEATURED
Published on the Cisco blog
Cisco Blogs · We Are Cisco · July 28, 2026 · 3 min readMore Than Just Code: My Two-Week Crash Course in Cisco Culture(opens in new tab)I wrote about spending my first two weeks as an ML intern exploring Cisco offices across the Bay Area instead of sitting at one desk, and what that taught me about the culture behind the code.
WRITING
Latest posts
All posts →August 24, 2026 · 1 min readWhat My Professor Taught Me on Day OneA positive first day of classes.
#internships#early-career#computer-science
August 7, 2026 · 2 min readFrom Cisco to FarmChemMy summer journey, into my future challenge.
#cisco#farmchem#artificialintelligence
August 6, 2026 · 1 min readThe Rise of Open Weight ModelsQuestions that could shape the future of open weight AI.
#open-models#ai-governance#ai-safety
READING
Latest reading
All reading →Connor O'Keefe, Yuri Volkov · 2026 · Added August 17, 2026How Cursor Router chooses the right model for the task(opens in new tab)Cursor's new router skips the guesswork: a classifier called Compass checks if a task is simple enough for a cheap model, and if not, a learned taxonomy picks whichever frontier model (Grok, Sol, Opus, or Fable) tends to win at that kind of work. Results so far: Auto Intelligence matches Fable-tier quality at 68% less cost, and Auto Balance beats Opus 4.8 while spending 41% less.
#fronteir-models#routing#performance
Mohamad Abou Ali, Fadi Dornaika · 2025 · Added July 27, 2026Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions(opens in new tab)This survey untangles what people mean by “agentic AI” by framing systems as either symbolic/classical or neural/generative, then mapping the major architectures and applications across the literature. It also calls out governance and safety gaps and argues that the most practical path forward is intentional hybridization, not picking one paradigm and stopping there.
#agentic-ai#survey#governance