Principal AI Solutions Engineer44 posts
Cho Yin Yong
Cho leads how XY Space's systems are engineered. He has lectured at the University of Toronto for five years, the youngest sessional lecturer his department has promoted, and still teaches Engineering Large Software Systems.
He is a co-author of two patents and winner of two competitive AI awards. Nine years of regulated engineering leadership included leading a team of more than 20 developers at Verto Health. That combination, teaching the theory while shipping the production system, is why XY Space's builds survive contact with a compliance review.
Credentials
- University of Toronto lecturer, five years, teaching AI and software engineering (Engineering Large Software Systems)
- The youngest sessional lecturer his department has promoted
- Co-author of two patents, and winner of two competitive AI awards
- Led a team of more than 20 developers at Verto Health
- Nine years of regulated engineering leadership
- Speaker, FHIR North 2025
Writing
Sep 2, 2026Running Open Models at Frontier LevelSep 2, 202688.2 and 28.3 Are the Same Model: Read the Version NumberSep 1, 2026The Cheapest Model Is the One That Finishes: Cost Per Solved TaskSep 1, 2026Claude Fable 5.1: The Cache Price Moves More Money Than the BenchmarksAug 30, 2026GLM-5.3-Flash vs GLM-5.3: Four Points for Nine Times the PriceAug 29, 2026GLM-5.3 vs GLM-5.2: The Same Model, Trained BetterAug 28, 2026Grok 4.6 vs GLM-5.3: Where the Open Model LandsAug 27, 2026DeepSeek-V4-Pro vs Qwen3.8-Max: Two Giants, One LicenceAug 19, 2026OpenClaw vs OpenCode: Two Agents That Share a Prefix and Nothing ElseAug 18, 2026IRAP Funding for Canadian Corporations: Get Up to 80% of Your R&D Salaries BackAug 18, 2026SR&ED for Canadian Corporations: Turn Innovation Costs Into a 35% RefundAug 17, 2026Human-on-the-Loop vs Human-in-the-Loop: Supervise or ApproveAug 17, 2026On-Premise vs Client Cloud vs Managed Cloud: Where Your AI System Should RunAug 15, 2026OpenCode vs Pi: How Much Should a Harness Do?Aug 11, 2026OpenCode vs deepagents: Is a Human Waiting?Aug 8, 2026Runtime, Harness, Product: How to Read the Agent Tooling LandscapeAug 5, 2026Strands Agents vs Flue: Who Owns the Environment?Aug 5, 2026Token-Based vs Scale-to-Zero vs Scale-to-One: How to Run Your Model LayerJul 29, 2026Strands Agents vs Mastra: Agent Runtime or Application Framework?Jul 21, 2026Strands Agents vs LangGraph: Who Decides the Next Step?Jul 17, 2026Kimi K3 vs Claude Opus 4.8: Open Frontier Meets Proprietary FrontierJul 17, 2026Kimi K3 vs GLM-5.2: The Two Open Flagships ComparedJul 17, 2026Kimi K3 vs Kimi K2.7 Code: What Moonshot's New Flagship ChangesJul 14, 2026Loop Engineering vs Subagent-Driven ExecutionJul 14, 2026Migrating from Claude Code to CodexJul 8, 2026Superpowers vs OpusplanJun 22, 2026GLM-4.7 Flash vs GLM-5.2: Which Z.ai Model Should You Run?Jun 19, 2026How to Run Kimi K2.7 Code in the opencode Desktop App (via AI Space)Jun 19, 2026How to Run Kimi K2.7 Code in VS Code with the opencode Extension (via AI Space)Jun 18, 2026GLM-5.2 vs Claude Sonnet 4.6: Which Is Better for Coding in 2026?Jun 18, 2026How to Run GLM-5.2 in VS Code with the opencode Extension (via AI Space)Jun 18, 2026How to Run Kimi K2.7 Code in opencode (CLI Setup via AI Space)Jun 17, 2026How to Run GLM-5.2 in the opencode Desktop App (via AI Space)Jun 16, 2026How to Run GLM-5.2 in opencode (CLI Setup via AI Space)Jun 16, 2026Kimi K2.7 Code vs Claude Opus 4.8: A Developer's ComparisonJun 14, 2026GLM-5.2 vs Kimi K2.7 Code: Which Open Model Should You Use?Jun 13, 2026CrewAI vs LangGraphJun 10, 2026How to Use GLM-5.2 with Claude Code (Step-by-Step)Jun 10, 2026n8n vs custom AI agentsJun 7, 2026OpenAI Agents SDK vs LangGraphJun 4, 2026MCP vs A2AJun 1, 2026LangGraph vs Pydantic AIMay 29, 2026Mastra vs FlueMay 26, 2026LangGraph vs LangChain
Also writing
Work with us
Book a call.We'll come back with specifics.
Start with the map of your organization, or with the one job that hurts. Measured in hours and money, and everything we build stays yours.
Loading form…