Alibaba Launches Qoder 1.0 Intelligent Agent Workspace: Introduces a Team Shared Knowledge Mechanism, Reducing Dialogue Turns by 33% in Testing

robot
Abstract generation in progress
AIMPACT News, May 15 (UTC+8), according to Beating Monitoring by Dongcha, Alibaba released Qoder 1.0 today, upgrading the product from an AI IDE to an autonomous agent development workspace. The new version upgrades the core Quest mode to a standalone window, running in parallel with the code editor. After developers define their goals, the intelligent agent can take over the complete task flow of execution, validation, and delivery.
In terms of multi-task support, Qoder 1.0 allows developers to run multiple agent tasks across different codebases simultaneously within a unified panel. Once tasks are completed, a delivery list containing documentation and code changes is automatically generated for manual review.
At the same time, the new version introduces a team-level knowledge engine for the first time, integrating previously scattered developer habits, project architecture, and technical stack standards. Alibaba’s official data shows that after the engine went live, code retention increased by 11%, and dialogue rounds decreased by 33%.
Additionally, an expert team composed of roles such as planning, coding, and testing has been officially introduced into the Quest window. Developers can also customize their own intelligent agent teams, configuring them with specific domain knowledge and external tool interfaces. (Source: BlockBeats)
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • 5
  • Repost
  • Share
Comment
Add a comment
Add a comment
UnderTheWisteriaBridge
· 5h ago
The Quest mode independent window design is quite clever; finally, no more toggling back and forth in the IDE.
View OriginalReply0
SentimentIndicatorHarvester
· 5h ago
Expert group + custom AI team, it feels like they're targeting enterprise-level sales.
View OriginalReply0
GateUser-cb789e81
· 6h ago
Parallel multi-projects across code repositories? This thing really understands the pain points of us workers.
View OriginalReply0
GateUser-55f70f75
· 6h ago
Automatic generation of delivery checklists, project managers are ecstatic, but who will do the code review?
View OriginalReply0
AvocadoYieldRate
· 6h ago
The 11% increase in code retention may not seem like much, but when the team size grows, it's real money in the bank.
View OriginalReply0
  • Pinned