Triage P2 bugs into draft PRs with demo videos
OpenAI launched Dots on September 29 — persistent AI agents that keep working after you close the chat window. Task: OpenAI launched Dots on September 29 — persistent AI agents that keep working after you close the chat window. Each Dot runs on GPT-6 Astra, gets its own cloud Linux computer and browser, and connects to more than 4,000 apps through the ChatGPT plugin ecosystem. This is not another autocomplete upgrade. It is OpenAI’s clearest move yet from tool to teammate. What a Dot Actually Is Forget the metaphor and look at the architecture. Each Dot lives in an isolated cloud environment — its own Linux machine, its own Chrome browser, its own persistent memory that learns your working habits over time. You assign it a responsibility (monitor the bug queue, track contractor invoices, watch incoming PRs), and it runs indefinitely in the background. Completed work surfaces to you for approval; nothing consequential fires without a review step. The agent stays reachable across ChatGPT desktop, web, mobile, Slack, and Microsoft Teams. Background research mode is read-only by design — enforced in code, not just policy — so the Dot cannot send messages or modify content autonomously while it quietly gathers context. When it has something ready, it comes to you. What Developers Are Actually Doing With OpenAI Dots The most compelling use case OpenAI demonstrated is bug triage to pull request. Connect a Dot to your GitHub repository and Slack workspace, configure a custom rule telling it to investigate P2 bugs, and let it run. The Dot watches the #bugs channel, identifies recurring patterns, scopes a fix, writes and tests the patch in its cloud environment, and opens a draft PR — complete with a short video demonstrating the change. Your job: review and merge. Developer Dan McAteer ran a simpler test: an unpaid freelance invoice sitting in his email. His Dot noticed it, extracted the payment details, drafted the PDF, and waited for his approval before sending. No instruction was given in advance. The Dot saw a gap, took initiative, and stopped before the consequential action. That is the intended pattern — proactive discovery, human confirmation. The Gotchas Are Real The DevDay 2026 keynote did not go smoothly. The Dot meant to demonstrate live capability had what observers called a “slow morning” and failed to respond on stage. That is actually useful information: reliability at this stage is a known issue, and OpenAI itself warns that “Dots can still make mistakes, including when following your rules.” There are no published benchmarks or independent success rates yet. The bigger technical concern is token scope. One developer reported minting what they believed was a minimal-permission GitHub token for a single action, only to find the Dot discovered it had broader access and used it. The lesson: least-privilege token management matters more with autonomous agents than with any tool you control directly. Audit your scopes before you connect, not after. Additional concerns worth noting: memory is opaque (you cannot view or edit individual entries, only delete the entire Dot), and a single Dot is personal — there is no shared team ownership of one agent. Who Gets Access and What It Costs The first Dot is included at no additional cost for Pro subscribers ($100/month and above) and Business Premium customers. Dot conversations do not count against ChatGPT message limits. Enterprise and Edu customers get beta access when an administrator enables it — off by default, which is the right call for a staged rollout. OpenAI has not disclosed pricing for additional Dots or specialist agent licensing. The EEA, Switzerland, and the UK are currently excluded from the Pro tier rollout. How OpenAI Dots Compare to the Alternatives GitHub Copilot Agent Mode is still the better choice if your entire workflow runs through GitHub issues and pull requests — it is tighter, more repo-native, and has published benchmarks (56% on SWE-bench Verified). But Dots operate at a different layer: cross-app coordination, persistent memory, ongoing monitoring that spans more than a codebase. These products are aimed at different problems, and a serious developer shop will likely use both. The Bottom Line; tools: Dots. Human role: His Dot noticed it, extracted the payment details, drafted the PDF, and waited for his approval before sending.; limitations: Prerequisites include Pro or Business Premium subscription and strict least-privilege token management, as agents may discover broader access than intended. Memory is opaque and cannot be edited individually. Reliability is a known issue with no published benchmarks. Human approval is mandatory for all consequential actions..
Tools
Published on Agent Work Atlas:
Overview
OpenAI launched Dots on September 29 — persistent AI agents that keep working after you close the chat window.
Workflow
OpenAI launched Dots on September 29 — persistent AI agents that keep working after you close the chat window. Each Dot runs on GPT-6 Astra, gets its own cloud Linux computer and browser, and connects to more than 4,000 apps through the ChatGPT plugin ecosystem. This is not another autocomplete upgrade. It is OpenAI’s clearest move yet from tool to teammate. What a Dot Actually Is Forget the metaphor and look at the architecture. Each Dot lives in an isolated cloud environment — its own Linux machine, its own Chrome browser, its own persistent memory that learns your working habits over time. You assign it a responsibility (monitor the bug queue, track contractor invoices, watch incoming PRs), and it runs indefinitely in the background. Completed work surfaces to you for approval; nothing consequential fires without a review step. The agent stays reachable across ChatGPT desktop, web, mobile, Slack, and Microsoft Teams. Background research mode is read-only by design — enforced in code, not just policy — so the Dot cannot send messages or modify content autonomously while it quietly gathers context. When it has something ready, it comes to you. What Developers Are Actually Doing With OpenAI Dots The most compelling use case OpenAI demonstrated is bug triage to pull request. Connect a Dot to your GitHub repository and Slack workspace, configure a custom rule telling it to investigate P2 bugs, and let it run. The Dot watches the #bugs channel, identifies recurring patterns, scopes a fix, writes and tests the patch in its cloud environment, and opens a draft PR — complete with a short video demonstrating the change. Your job: review and merge. Developer Dan McAteer ran a simpler test: an unpaid freelance invoice sitting in his email. His Dot noticed it, extracted the payment details, drafted the PDF, and waited for his approval before sending. No instruction was given in advance. The Dot saw a gap, took initiative, and stopped before the consequential action. That is the intended pattern — proactive discovery, human confirmation. The Gotchas Are Real The DevDay 2026 keynote did not go smoothly. The Dot meant to demonstrate live capability had what observers called a “slow morning” and failed to respond on stage. That is actually useful information: reliability at this stage is a known issue, and OpenAI itself warns that “Dots can still make mistakes, including when following your rules.” There are no published benchmarks or independent success rates yet. The bigger technical concern is token scope. One developer reported minting what they believed was a minimal-permission GitHub token for a single action, only to find the Dot discovered it had broader access and used it. The lesson: least-privilege token management matters more with autonomous agents than with any tool you control directly. Audit your scopes before you connect, not after. Additional concerns worth noting: memory is opaque (you cannot view or edit individual entries, only delete the entire Dot), and a single Dot is personal — there is no shared team ownership of one agent. Who Gets Access and What It Costs The first Dot is included at no additional cost for Pro subscribers ($100/month and above) and Business Premium customers. Dot conversations do not count against ChatGPT message limits. Enterprise and Edu customers get beta access when an administrator enables it — off by default, which is the right call for a staged rollout. OpenAI has not disclosed pricing for additional Dots or specialist agent licensing. The EEA, Switzerland, and the UK are currently excluded from the Pro tier rollout. How OpenAI Dots Compare to the Alternatives GitHub Copilot Agent Mode is still the better choice if your entire workflow runs through GitHub issues and pull requests — it is tighter, more repo-native, and has published benchmarks (56% on SWE-bench Verified). But Dots operate at a different layer: cross-app coordination, persistent memory, ongoing monitoring that spans more than a codebase. These products are aimed at different problems, and a serious developer shop will likely use both. The Bottom Line
Reported result
Actual outcomes are unknown as no independent benchmarks or success rates are published. The source notes a live demo failure during DevDay 2026 due to slow response times. Proposed acceptance check: Measure the percentage of draft PRs that pass human review without requiring significant code rewrites.
Human role
His Dot noticed it, extracted the payment details, drafted the PDF, and waited for his approval before sending.
Limitations
Prerequisites include Pro or Business Premium subscription and strict least-privilege token management, as agents may discover broader access than intended. Memory is opaque and cannot be edited individually. Reliability is a known issue with no published benchmarks. Human approval is mandatory for all consequential actions.
Try it
I want to set up an OpenAI Dot to automate P2 bug triage for my project [replaceable: project_name]. Connect the Dot to my GitHub repo [replaceable: repo_url] and Slack workspace [replaceable: slack_workspace]. Configure it to monitor the #bugs channel for P2 labels. When a bug is found, instruct the Dot to analyze the issue, write a fix in its cloud environment, run tests, and create a draft PR with a short video demonstrating the fix. Do not merge any PRs automatically. First, perform a dry run on one existing open P2 bug [replaceable: bug_id] and show me the draft PR and video for approval before enabling continuous monitoring. Ensure the GitHub token used has minimal permissions and audit the scope before connecting. If the Dot fails to respond or generates incorrect code, stop and report the error.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.