Tag
Cognition announces the acquisition of TierZero, a team focused on incident detection and system health automation, to enhance their AI software engineer Devin.
A Devin and ElevenLabs sponsored hackathon in Dubai on August 8, offering free credits and prizes to build voice-first AI agents.
Niall Dabit explains a mental model for cloud agents as infinitely cloned laptop environments accessible via HTTP, and describes an experiment using a fork of Hermes Agent with DevinAI for automated fork maintenance.
Lightning Orchestrator is an agent skill that uses fast subagents (SWE-1.7 Lightning) for implementation, achieving ~5x faster execution while keeping a frontier model as planner and reviewer. It works with Devin and supports parallel execution for larger tasks.
Jeff Wang recounts the chaotic 72 hours leading to Windsurf's acquisition and how it accelerated development of the Devin platform, unifying agentic IDE and cloud agent into a single product with new event-driven agent capabilities.
Cognition replaced the Opus model with Fable in Devin's Fusion architecture, achieving higher performance at lower cost despite Fable's higher per-token price, through better delegation and reduced lead model turns.
A developer shares that the best current agent setups use a mix of tools: Kimi, GLM, cloud agents, Fable, and Frontier for orchestration, with DevinAI's ACP running agents locally or in the cloud.
Cognition introduces Devin Security Swarm, a new tool for finding security vulnerabilities using an Agentic MapReduce architecture, achieving higher accuracy and lower cost than alternatives.
This post discusses Devin's new 'Security Swarm' feature using Agentic MapReduce to scale AI-driven code security analysis, illustrating the need for 100× more AI inference and the strategic deployment of diverse models across industries.
Claude Fable 5 is now available in Devin's Ultra agent, Devin Desktop, and Devin CLI.
Devin Cloud launches Security Swarm, using Agentic MapReduce to find security vulnerabilities in codebases, with remediation and fleet management in the Desktop app.
Claude Sonnet 5, a new AI model with frontier-level coding performance at a more affordable price, is now available in Devin Desktop and Devin CLI, outperforming Opus 4.8 on FrontierCode Extended.
MetaviewAI used Devin AI agent to complete SOC2 audit in two days instead of weeks.
The tweet highlights that GLM 5.2 and Kimi 2.7 are available without limits in a Devin subscription, describing it as a gold mine.
Cognition moved its domain from cognition.ai to cognition.com, maintaining Devin as the first autonomous software engineer.
An engineer at Cognition shares internal tips for using Devin, including the 'Agent Fan Out' technique where a master agent spins up parallel child agents to solve tasks independently.
Today Devin receives a huge security upgrade, allowing it to review every pull request with the depth of a security engineer.
Promotional tweet showing how easy it is to create automations with the AI coding agent Devin, highlighting quick setup and one-click examples.
Cognition announces a $10M productivity guarantee for Devin, its AI coding agent, backed by a new measurement system validated on enterprise data showing 4x engineering output.
This tweet promotes Devin, an AI coding tool that works autonomously in the cloud and can produce pull requests without user supervision, linking to a tutorial video.