ai-agents-2-2 Agent Engineering: A New Discipline Useful mental model for iterative quality improvement of non-deterministic agent systems. Leo Parker 9 Jun 2026 · 1 min read
ai-agents-2-2 Code as Agent Harness Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is... Leo Parker 18 May 2026 · 1 min read
ai-agents-2-2 Beyond Quantity: Trajectory Diversity Scaling for Code Agents As code large language models (LLMs) evolve into tool-interactive agents via the Model Context Protocol (MCP), their generalization is increasingly limited by low-quality synthetic data and the diminishing returns of qua... Leo Parker 3 Feb 2026 · 1 min read
ai-agents-2-2 TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture While integrating tools like Code Interpreter and Search has significantly enhanced Large Language Model (LLM) reasoning in models like ChatGPT Agent and Gemini-Pro, practical guidance on optimal tool use is lacking. The... Leo Parker 30 Sep 2025 · 1 min read
ai-agents-2-2 Building effective agents Excellent practical patterns for deciding when to use workflows vs autonomous agents, with implementation tradeoffs from production teams. Leo Parker 19 Dec 2024 · 1 min read
ai-agents-2-2
