A new convention is emerging in the open-source ecosystem: AGENTS.md, a straightforward and open format designed to assist AI coding agents in software development. Already adopted by more than 20,000 repositories on GitHub, the format is being positioned as a companion to traditional documentation, offering machine-readable context that complements human-facing files like README.md.
This article discusses practical AI adoption, focusing on how AI should serve people and how to move from the current state to an ideal future state. It highlights examples of companies like Smartsheet and Western Governors University seeing ROI from Grammarly, and announces Grammarly's acquisition of Superhuman. It also introduces a 'Big Rocks' ritual for quarterly planning and discusses the three phases of productivity (digitization, collaboration, and agentic AI).
**Key Points:**
* **AI as a Workflow Redesign:** Mehrotra sees AI moving beyond simple automation to fundamentally redesigning work, becoming an active participant alongside humans.
* **Rituals for AI Integration:** He emphasizes the importance of establishing work "rituals" to effectively integrate AI, citing examples like AI-powered email triage and new hackathon formats. He introduces the "Big Rocks" method for prioritizing initiatives.
* **Grammarly's Success with AI:** The article highlights Grammarly's ROI for clients like Smartsheet (283% ROI, 1600 hours saved) and Western Governors University (146,000 hours saved, $2.5M savings).
* **Grammarly's Acquisition of Superhuman:** This acquisition is presented as a step towards a unified, AI-powered productivity suite.
* **Three Phases of Productivity:** Mehrotra outlines three phases: digitization (faster work), collaboration (real-time work), and now, agentic AI (AI participating in work). He argues organizations need to prepare for this shift by viewing AI as a tool to *augment* human work, not replace it.
* **Further Reading/Resources:** The article links to additional content, including a Fast Company piece by Mehrotra and links to relevant news articles about Grammarly, Figma, and other companies.
**Overall:** The article advocates for a thoughtful, ritual-based approach to AI adoption, focusing on how AI can enhance existing workflows and empower employees rather than simply automating tasks. It showcases Grammarly's position as a leader in this space.
**Key Points:**
* **AI as a Workflow Redesign:** Mehrotra sees AI moving beyond simple automation to fundamentally redesigning work, becoming an active participant alongside humans.
* **Rituals for AI Integration:** He emphasizes the importance of establishing work "rituals" to effectively integrate AI, citing examples like AI-powered email triage and new hackathon formats. He introduces the "Big Rocks" method for prioritizing initiatives.
* **Grammarly's Success with AI:** The article highlights Grammarly's ROI for clients like Smartsheet (283% ROI, 1600 hours saved) and Western Governors University (146,000 hours saved, $2.5M savings).
* **Grammarly's Acquisition of Superhuman:** This acquisition is presented as a step towards a unified, AI-powered productivity suite.
* **Three Phases of Productivity:** Mehrotra outlines three phases: digitization (faster work), collaboration (real-time work), and now, agentic AI (AI participating in work). He argues organizations need to prepare for this shift by viewing AI as a tool to *augment* human work, not replace it.
* **Further Reading/Resources:** The article links to additional content, including a Fast Company piece by Mehrotra and links to relevant news articles about Grammarly, Figma, and other companies.
**Overall:** The article advocates for a thoughtful, ritual-based approach to AI adoption, focusing on how AI can enhance existing workflows and empower employees rather than simply automating tasks. It showcases Grammarly's position as a leader in this space.
Interact with opencode server over HTTP. The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.
The article explores how modern AI agents are fulfilling the vision of the Semantic Web by combining AI's learned intuition with the logical structure of semantic technologies, creating intelligent agents that can understand and act on behalf of users.
Grammarly is evolving into a full productivity platform with the launch of eight specialized AI agents designed to assist users throughout the writing process. These agents offer targeted help with tasks like source verification, originality checks, predicting reader reactions, and evaluating work against rubrics. Integrated within a new AI-native writing surface called “docs,” and eventually across 500,000+ platforms, these tools aim to provide context-aware support, replacing the need for complex prompt engineering and empowering both students to develop AI literacy and professionals to maintain authentic communication. The launch signifies a shift towards agentic AI, anticipating user needs and delivering intelligent assistance directly within their workflow.
Grammarly is launching nine AI agents for writing and grading assistance, available for Free and Pro users. These agents aim to help students improve their writing, predict grades, and detect plagiarism, while also assisting educators in reviewing submissions.
This blog post explains that Large Language Models (LLMs) don't need to understand the Model Context Protocol (MCP) to utilize tools. MCP standardizes tool calling, simplifying agent development for developers while the LLM simply generates tool call suggestions based on provided definitions. The article details tool calling, MCP's function, and how it relates to context engineering.
ScreenCoder — Turn any UI screenshot into clean, editable HTML/CSS with full control. Fast, accurate, and easy to customize.
The Azure MCP Server implements the MCP specification to create a seamless connection between AI agents and Azure services. It allows agents to interact with various Azure services like AI Search, App Configuration, Cosmos DB, and more.
Take a deep dive into how the Model Context Protocol (MCP) works and solidify your understanding by building an agentic system that uses it.
