Legal AI tools built on coding-agent scaffolding fail to meet the evidentiary and workflow requirements of legal practice, argues Alan Yahya in a technical critique. Yahya calls for purpose-built lega…
Alan Yahya compares how Claude Code, Codex, and OpenCode handle context compaction to prevent context rot in AI agents. Claude Code avoids unnecessary summaries through mechanical reductions, Codex tr…
Alan Yahya explains that agent telemetry is critical for monitoring non-deterministic LLM agents, which can break things unpredictably. Telemetry tracks tool calls, latency, guardrail triggers, and ev…
Alan Yahya details how Microsoft Word's multi-document agent workflows separate agent sessions, active documents, turn documents, and document versions to prevent errors when users move between docume…
Alan Yahya outlines the evolution of LLM agents from fine-tuning to optimizing agent workflows, emphasizing the need for features like session management and in-line editing. He notes that vertical ap…