OpenAI brings multi-agent tag teaming to GPT-6 Astra Pro
OpenAI just supercharged GPT-6 Astra Pro inside ChatGPT with faster response times and smoother tool execution. The biggest addition is parallel multi-agent support, letting several agents divide and tackle complex tasks at once while you track their progress live. The update is now rolling out to ChatGPT Pro subscribers.
If waiting for a single AI model to grind step-by-step through a sprawling task feels slow, OpenAI wants to divide the labor.
The company just rolled out an upgrade to GPT-6 Astra Pro inside ChatGPT, delivering faster response times and improved handling of plugins and tools. But the headline change is the arrival of native multi-agent task support.
Parallel agents in your chat feed
Instead of tackling a prompt sequentially, multiple agents can now break down a task and work on different sections simultaneously in parallel.
Users can track the real-time progress of each individual agent directly inside the Chat tab. Once a subtask wraps up, you can open it up to review the work and verify the outputs. The upgrade is live now for ChatGPT Pro subscribers.
Why it matters
Bringing parallel multi-agent execution right into the main chat window is a smart play. Linear tool calls often hit bottlenecks, drag out execution times, or derail mid-prompt when tasks get messy. By fanning out work across specialized agents, Pro users who rely on heavy research and plugin automation can eliminate serious wait times while keeping full visibility into what the AI actually touched.
The real test will be synthesis. Splitting jobs across agents is the easy part; ensuring those parallel outputs merge back together cleanly without tripping over conflicting tool data is where these systems typically get tested.
Sources (1)
- x.com(opens in a new tab)Originalx.com