product updateGitHub

GitHub Brings Agentic Copilot CLI Capabilities to Slack in Public Preview

TL;DR

GitHub has released a new integration bringing GitHub Copilot's agentic CLI and app capabilities into Slack via public preview. Users can now interact with @GitHub directly in Slack channels to trigger Copilot actions.

2 min read
0

GitHub has launched a new Copilot experience inside Slack, now available in public preview. The update integrates the agentic capabilities of GitHub Copilot CLI and the GitHub Copilot app directly into Slack, allowing users to invoke @GitHub within Slack channels and direct messages.

What's changing

According to GitHub, the new Slack integration lets users work with @GitHub to trigger Copilot's agentic functions without leaving Slack. This builds on GitHub's existing Slack integration, which previously focused on notifications and basic repository updates, by adding the same agentic task-execution capabilities found in the standalone Copilot CLI and app.

GitHub has not disclosed specific details on which agentic tasks are supported at launch, pricing implications for existing Copilot subscribers, or a timeline for general availability beyond the current public preview status.

Confirmed vs. unconfirmed

GitHub confirms the integration is live in public preview as of August 21, 2026. The company has not published benchmark data, adoption numbers, or a full list of supported commands. Specific capabilities — such as whether users can trigger pull request reviews, code generation, or issue triage directly from Slack — are implied by the reference to "agentic capabilities" but not itemized in the announcement.

Why this matters

GitHub Copilot has steadily expanded beyond the IDE into CLI tools, a standalone app, and now team collaboration platforms. Slack is widely used as an operational hub for engineering teams, and embedding Copilot's agentic features there reduces context-switching between chat, terminal, and code editor. This follows a broader industry pattern of AI coding assistants moving into chat-based interfaces, similar to how other developer tools have integrated bot-driven workflows into Slack and Microsoft Teams.

This is a product integration rather than a new model release — no new underlying AI model or version is introduced. The change affects how existing Copilot capabilities are accessed, not the capabilities themselves.

What this means

For engineering teams already using Slack as their primary communication tool, this reduces friction in invoking Copilot for quick tasks without switching to an IDE or terminal. The public preview status signals GitHub is still gathering feedback before a full rollout, and specifics on cost, rate limits, and supported agentic actions remain unclear. Teams evaluating this should treat it as an early-access feature subject to change rather than a finalized product offering.

Related Articles

product update

OpenAI to watermark ChatGPT and Codex text in the EU with textGrain; API watermarking is opt-in worldwide

OpenAI will switch on invisible text watermarks called textGrain for ChatGPT and Codex users in the EU over the coming weeks. API watermarking will be opt-in worldwide, unlike Anthropic's mandatory approach for Claude. OpenAI's own data shows detection drops sharply when text is edited.

product update

Claude Opus 5.5 and Sonnet 5.5 now on Amazon Bedrock in AWS GovCloud (US), with Claude Code support

Claude Opus 5.5 and Claude Sonnet 5.5 are available on Amazon Bedrock in AWS GovCloud (US) Regions. AWS published a setup guide for running Anthropic's Claude Code against them for regulated workloads, including ITAR. Pricing, context window and benchmark figures were not disclosed.

product update

AWS ships aws-ai-ml skill so Kiro, Claude Code and Codex can benchmark SageMaker inference endpoints

Amazon SageMaker AI has released the aws-ai-ml skill, distributed through the Agent Toolkit for AWS. It lets MCP-compatible coding agents such as Kiro, Claude Code and Codex benchmark endpoints, recommend deployment configurations and generate executable SageMaker Python SDK v3 code.

benchmark

GitHub launches ReviewBench, an open benchmark for AI code review agents built on real pull requests

GitHub has launched ReviewBench, an open benchmark for evaluating AI code review agents. According to GitHub, it uses representative pull requests, multi-source ground truth, calibrated evaluation, and production-aligned metrics. Dataset size, scores, and licensing were not included in the announcement excerpt.

Comments

Loading...