SINGAPORE, SG / ACCESS Newswire / September 24, 2026 / Qoder, the agentic coding platform, today introduced Projects and Discussion in beta, giving engineering teams a shared place to organize work, resolve questions, and collaborate with AI agents. The new capabilities address a growing coordination challenge: while agents can help individuals write code, investigate problems, and run tests faster, teams still spend time carrying decisions and context between meetings, messages, tasks, and separate agent sessions.

With Projects, teams can break engineering goals into Issues, assign priorities and statuses, and track progress on a board. Discussion bring teammates and agents together to clarify requirements, review technical approaches, and investigate defects. Qoder is also introducing Custom agents and Custom agent teams for work that calls for reusable specialist roles.

Keeping the work and its context together

A typical engineering task may begin in a meeting or group chat, then move into several people's agent sessions. Each person has to restate the agreed approach for their own agent. As the work develops, decisions, code changes, test results, and pull request links can end up scattered across those sessions.

With Projects, teams have a shared view of the work. An Issue can capture the goal, background, priority, status, and acceptance criteria for a task, whether the team is building a feature, fixing a defect, or updating a system. When a question needs broader input, team members can start a Discussion from the Issue, carrying its title and description into the conversation.

Bringing people and agents into the same discussion

In Discussion, teammates can add documents and other context, reply to specific points, and ask an agent to analyze material or compare options. For example, a developer can explain an implementation constraint, a tester can identify failure cases, and an agent can compare proposed approaches using the material provided.

Teams can mark agreed conclusions as key messages so agents can find the decisions that matter. After a discussion, they can record the chosen approach, open questions, and follow-up owners in the relevant Issue, then update its status as the work progresses. This gives product, engineering, and testing teams a common reference when they review results and decide what happens next.

Matching agents to the task

Custom agents let users save instructions, model settings, permissions, and tools for recurring work such as implementation planning or code review. For work requiring several specialties, Custom agent teams bring those agents together under a lead agent that coordinates the work and consolidates their contributions. People remain responsible for reviewing the results and making the final decisions.

The core idea: let discussion happen on the spot where the work happens. People and models share context, and discussion history and discussion assets accumulate on the task itself, so people no longer have to act as the agent's "courier." Together, these two features greatly improve the efficiency of human-agent collaboration.
- Ding Yu, Founder of Qoder, speaking at the Apsara Conference.

Availability

Projects, Discussion, Custom agents, and Custom agent teams are currently in beta for customers on Qoder's Teams and Enterprise plans. Broader availability will follow.

For more information, visit Qoder Projects and Qoder Discussion.

About Qoder

Qoder is an agentic coding platform for everyone. Across desktop, mobile, IDE, JetBrains Plugin, and CLI, it helps individuals and teams build software and tackle work beyond coding with AI agents. Qoder also offers enterprise solutions and agent integration through its Agent SDK and Cloud Agents. Qoder serves more than 6 million builders worldwide. For more information, visit https://qoder.com.

Media Contact

Organization: Qoder
Contact Person Name: Leroy Zhang
Website: https://qoder.com
Email: contact@qoder.com
City: Singapore
Country: Singapore

SOURCE: Qoder