The evolution of Codex, a coding assistant, to manage general computer tasks and documents indicates a broader trend: the structured, agentic workflows of programming are being applied to all knowledge work. This reframes tasks like reporting and data entry as forms of 'coding'.
Codex's new 'Heartbeats' feature allows AI agents to function as a Chief of Staff. These recurring automations maintain context within a single thread, scan sources like email and Slack, and proactively brief users on priorities, moving beyond reactive Q&A to active workflow management.
The new Codex app encourages a 'monothread' pattern where a single AI conversation is kept alive for weeks. Improved context compaction allows the thread's value to increase over time, moving beyond the old model of starting fresh for each task and creating a persistent, learning assistant.
Unlike previous models that benefited from iterative guidance, Anthropic's team suggests Opus 4.7 delivers higher quality results when treated like a capable engineer. Users should provide the full goal and constraints upfront, as multi-turn clarification can actually reduce output quality.
OpenAI's Codex bets on a single, unified interface where the AI handles any task from one input, reducing friction. Conversely, Anthropic's Claude app bets that different work modes (Chat, Cowork, Code) are distinct enough to require separate, specialized interfaces, akin to traditional native apps.