Nebula

Overview

Nebula is a Slack-inspired AI agent platform designed for autonomous workflows. Instead of treating AI agents as one-off chatbots, Nebula organizes work into channels, where each channel can host an agent capable of writing code, calling APIs, and executing multi-step tasks across connected services. In demos covered in the newsletter, Nebula agents were shown creating Google Slides decks, generating images, publishing blog posts to Ghost, integrating with analytics tools like PostHog, and coordinating recurring workflows through scheduled triggers.

For AI Product Managers, Nebula matters because it points toward a more operational model of AI products: agents that do work inside persistent workspaces, not just answer prompts. Its channel-based structure makes it easier to imagine teams assigning dedicated agents to functions like content creation, analytics, growth, or lead generation. That makes Nebula especially relevant as an example of how AI-native workflow tools may evolve from assistants into autonomous systems that own ongoing business processes.

Key Developments

• 2026-01-27: Nebula was highlighted in Greg Isenberg's conversation with Furqan Rydhan as a Slack-style AI agent platform where each channel hosts an agent that can write and run Python code, call APIs, retry failed tasks, and automate workflows across services including Google Slides, Ghost, PostHog, GitHub, and Notion.
• 2026-01-28: The platform was again featured in coverage of the same demo, emphasizing Nebula's ability to build slide decks, generate images, publish blog posts, integrate with multiple tools, and schedule autonomous workflows for one-person businesses.

Relevance to AI PMs

• Designing agentic product experiences: Nebula is a useful reference for AI PMs exploring how to structure agent interactions beyond chat. Its channel-based model suggests a product pattern where agents are assigned to persistent contexts, teams, or business functions.
• Evaluating orchestration and reliability: The demos emphasized code execution, API calls, scheduled tasks, and retry behavior. AI PMs can use Nebula as a benchmark when thinking about what makes an AI workflow product actually useful in production: integrations, observability, persistence, and recovery from failure.
• Prototyping autonomous workflows: Nebula shows how agents can chain together content, analytics, and publishing tasks across tools like Ghost, Google Slides, and PostHog. For AI PMs, this is practical inspiration for defining end-to-end workflows that save users time rather than offering isolated AI features.

Related

• Furqan Rydhan: Featured as the person demoing Nebula alongside Greg Isenberg, suggesting a close connection to the product's positioning and capabilities.
• Greg Isenberg: Helped bring attention to Nebula through a video conversation focused on AI agent systems and business automation.
• Google Slides: Used in Nebula demos as an example of agents creating and updating presentation decks programmatically.
• Ghost: Highlighted as a publishing destination for autonomous blog workflows managed by Nebula agents.
• PostHog: Mentioned as an analytics integration, showing Nebula's potential to connect agent workflows with product and growth data.
• GitHub: Referenced as part of Nebula's integration surface, relevant for code-driven and developer-oriented workflows.
• Notion: Included among connected tools, indicating Nebula's applicability to knowledge and operations workflows.