#agent workflows

agent workflows

2 篇論文

A researcher rehearses at a lectern while a supervisor and peer compare an annotated report passage with a projected chart and context note.

政策 / 倫理2026年9月16日

Product news: Claude merges chat and Cowork while adding document and slide creation in beta

Anthropic

AI Product and Learning Report

Anthropic's September 16 announcement begins merging Claude chat and Cowork and introduces Docs and Slides alongside Design inside conversations. Rollout starts with Pro and Max, while the creation tools remain in beta on paid plans. OpenAI's agent infrastructure and Gemini's educational tools provide comparison points. For academic work, the convenience of turning one conversation into several artifacts makes it especially important to check how evidence and uncertainty survive each revision.

product newsClaude DocsClaude Slides

閱讀 500 字摘要 →

A librarian, graduate student and student developer check printed source records against a three-stage source-to-notes-to-table workflow on a monitor.

政策 / 倫理2026年9月10日

政策 / 倫理 147

Product news: OpenAI's Agents API brings managed execution to research and educational applications

OpenAI

AI Product and Learning Report

OpenAI launched the Agents API in public beta on September 10, offering managed execution, context handling, tools, and subagents for longer tasks. Educational developers can explore more sustained workflows, but need to define what happens when work stops, resumes, or changes direction. Anthropic's shared memory and Gemini's selective video analysis provide comparisons. The central design task is to preserve evidence and human responsibility across the whole activity.

product newsAgents APIresearch software

閱讀 500 字摘要 →