Tag
Discusses the shift from token-based productivity metrics to output, impact, and value measurement in AI adoption, highlighting Cognition's solutions: adaptive routing, spend attribution, automations, and a productivity guarantee.
Cognition released the first evaluation suite for Devin, offering up to 100-hour enterprise evals with a financial guarantee. The dataset includes real-world Java/TypeScript/Python/C# tasks from 126 enterprise users, aiming to measure engineering productivity more accurately than existing benchmarks.
A survey of memory implementations across major AI agent harnesses (Claude Code, Codex, Copilot, etc.) reveals common boundary failures including bounded local storage, keyword retrieval, harness scoping, weak staleness handling, and 57-71% cross-user contamination rates, highlighting unsolved problems in agent memory infrastructure.
Devin Desktop allows users to manage fleets of local and cloud AI agents from a single interface.
Cognition's Ido Pesok shares lessons from building autonomous end-to-end testing into Devin, noting that for the first time, more Devin sessions are now triggered asynchronously than interactively, making verified-before-merge results a hard requirement rather than a nicety.
Cognition CEO Scott Wu discusses that AI coding agents like Devin are designed to assist, not replace, human programmers, emphasizing human-AI collaboration over job displacement.
A deep dive into building cloud agents with Walden Yan (Cognition) and Cole Murray (OpenInspect), covering VM setup, computer use, memory, and the rise of async agents in the AI engineering landscape.
Devin now provides an admin dashboard that automatically clusters each session by what it actually did (feature work, bug fixing, migrations, tests, docs), broken down by cost, sessions, users, and PRs merged.
This article synthesizes three independent reports (the internal retrospective from Cognition's engineering lead, the industry panorama report by Manning author Micheal Lanham, and the metaswarm project), pointing out that only three patterns of multi-agent systems truly survive in production: pipeline, orchestration, and generator-validator, while peer collaboration patterns fail due to implicit decision conflicts and cascading errors.
A developer used Devin Terminal CLI with a multi-model subagent setup to build a full multiplayer drawing game from scratch, demonstrating the agent's capability.
A Cognition employee describes how Devin automations monitor Slack channels, triaging and solving issues autonomously, making engineering progress almost entirely autonomous while engineers focus on big bets.
Nader Dabit predicts that by end of year, over 95% of agent sessions will be triggered by automations and events, and demonstrates how to build event-driven agentic systems using Devin, starting with Slack as a control plane.
Devin is positioned as an AI Engineering platform covering the entire software development lifecycle, from planning to documentation, with integrations and features that enhance developer experience.
Scott Wu, CEO of Cognition, discusses Devin, an AI software engineer built on Claude, aiming to accelerate software development by 10x for engineering teams.
The user is trying Devin, an AI coding tool from Cognition Labs.
Cognition has released Devin Auto-Triage, a feature that automates the monitoring and triaging of bugs, alerts, and incidents, allowing the AI coding agent to proactively work before the user logs on.
Cognition announces Devin Auto-Triage, an AI agent designed for on-call engineers that monitors incidents and provides context and automated responses via Slack.
The next era of AI software development moves coding agents into production; Cognition introduces Devin Auto-Triage for automated incident response and PR generation.
Cognition introduces Devin Auto-Triage, a new feature for Devin that adds long-term memory and autonomous monitoring of bugs, alerts, and incidents, with the ability to investigate and propose fixes or pull requests.
A quick guide highlights features of Devin AI, an autonomous AI software engineer from Cognition, including integrations with Slack, terminal, and project management tools.