AWS re:Invent 2025 - Slack Platform: Build with AI-Powered Development (AIM111)

Source: Dev.to

Overview

AWS re:Invent 2025 – Slack Platform: Build with AI‑Powered Development (AIM111)

In this video, a Slack developer demonstrates how to supercharge AI‑assisted development using Slack’s platform and deploy AI agents. The presentation covers Slack’s event‑driven architecture, showcasing how multiple agents (GitHub Copilot, Claude, Cursor, Codex) can coexist in channels and be invoked like team members. A live demo shows GitHub Copilot automatically creating PRs and providing asynchronous updates. Key features highlighted include:

• Out‑of‑the‑box UI
• Contextual APIs
• WebSocket support for local development without endpoint setup
• Ability to build functioning Slack apps in under 67 minutes using AI‑assisted coding tools

The speaker emphasizes Slack’s platform simplicity, enabling rapid prototyping and user testing over lengthy development cycles.

---

Supercharging AI‑Assisted Development with Slack: Platform Overview and Live Demo

Watch the video (start)

Watch the video (20 s)

Introduction

Slack’s platform, launched eight to ten years ago, is fundamentally event‑driven. What were once called “bots” are now referred to as agents—bots enhanced with large language models (LLMs). The underlying architecture remains the same, but the integration of AI has created a natural fit for modern development workflows.

Why Slack for AI Development?

• Unified UI – Developers can focus on business value rather than building custom interfaces.
• Contextual Awareness – Slack provides real‑time APIs that expose who is talking, relationships between users, channels, and objects, and recent activity (last week, last five minutes). This context enables agents to act intelligently.
• Permission‑Aware Calls – API calls respect the invoking user’s permissions, ensuring agents only see data the user is allowed to see.
• Automation & No‑Code Options – For teams that prefer configuration over code, Slack offers automation tools that require no programming.
• Developer‑Friendly UX Patterns – Features like streaming responses, shimmer states, and “thinking” indicators are built into the platform, reducing cognitive load.

Watch the video (100 s)

Live Demo: Using Agents in a Payments Channel

The demo showcases a typical developer workflow within a Slack channel dedicated to a payments app. The channel includes:

• GitHub integration (notifications, PR updates)
• A GitHub Copilot agent that can be invoked like a human teammate

Watch the video (260 s)

Watch the video (270 s)

Invoking the Copilot Agent

1. A developer mentions an issue in the channel.
2. They call the GitHub Copilot agent by name, just as they would ping a teammate.
3. The agent acknowledges the request, indicates it is “looking at” the problem, and begins processing.

Watch the video (320 s)

Agent Workflow

• The agent confirms receipt with an emoji or short message.
• It gathers relevant context (e.g., channel members, recent messages).
• It performs the assigned task—such as generating a pull request—while providing status updates in the channel.

Watch the video (350 s)

Takeaways

• Rapid Prototyping – Slack’s built‑in UI and APIs let teams spin up functional AI‑enhanced apps in minutes.
• Context‑Rich Interactions – Agents can leverage Slack’s conversation history and permission model to act intelligently and securely.
• Scalable Agent Ecosystem – Multiple agents can coexist in a single channel, each invoked by name, enabling collaborative AI workflows.

The content above reflects the original presentation and may contain minor transcription errors.