GenAI PMDevin
Cognition's AI software engineer product. In this item it is referenced through a new feature, Outposts, for running and testing apps on external computers.
Key Highlights
- Devin is evolving beyond code generation into an AI software engineering platform spanning testing, QA, security, and pull request workflows.
- The Outposts launch extends Devin’s ability to run and test applications on external computers, making execution environment support a key differentiator.
- Security Swarm and codebase-level reasoning position Devin as relevant for PMs focused on secure software delivery, not just developer productivity.
- Native support for GitHub Stacked PRs shows Devin is targeting real-world engineering collaboration patterns, not only single-shot code tasks.
- Features like /handoff and Windows support make Devin more practical for asynchronous teams and enterprise modernization use cases.
Overview
Devin is Cognition’s AI software engineer product, designed to help teams plan, implement, test, review, and ship software work with increasing autonomy. In the newsletter coverage, Devin appears not just as a coding assistant but as a broader execution platform: it can work in cloud environments, support CLI handoff, operate on Windows, run QA workflows, assist with security remediation, and manage complex GitHub review patterns such as stacked pull requests. Most recently, Cognition introduced Outposts, a feature that lets Devin natively run and test apps on any computer, extending its reach beyond a single hosted environment.
For AI Product Managers, Devin matters because it points to a shift from “AI that suggests code” toward “AI that owns chunks of the software delivery workflow.” That includes verification, security validation, PR orchestration, audit support, and cross-environment execution. PMs evaluating agentic development tools should view Devin as an example of how AI engineering products are moving closer to end-to-end software operations rather than isolated pair-programming.
Key Developments
- 2026-05-22: Cognition launched Devin on Windows, positioning the product for mapping, building, and modernizing Windows applications.
- 2026-05-25: Ryan Carson showcased using cloud-based Devin with OpenClaw and Codex to automate executive assistant workflows, nightly prospecting, recurring test playbooks, and high-volume PR shipping.
- 2026-05-30: Cognition highlighted a technical breakdown from ido_pesok on Devin’s VM-based end-to-end testing framework, emphasizing scalable verification.
- 2026-06-12: Cognition open sourced /handoff, a Devin CLI feature that allows agents to keep running in the cloud after a user disconnects.
- 2026-06-19: Cognition described Devin’s ability to reason across an entire codebase to uncover deep business-logic security flaws that static pattern-matching scanners can miss.
- 2026-06-25: Cognition shared an automated QA workflow in Devin where humans approve a test plan before PR review, then receive a screen recording and visual step-by-step QA checklist.
- 2026-06-27: Cognition showed how MetaviewAI used Devin to help complete a normally weeks-long SOC2 audit in two days.
- 2026-07-02: Cognition launched Security Swarm, a Devin-for-Security capability that bundles tools to find vulnerabilities, validate them at runtime, and ship remediation PRs.
- 2026-07-31: Cognition added native support for GitHub Stacked PRs, enabling Devin to break large changes into smaller reviewable diffs, address comments across stacks, and automatically rebase downstream changes.
- 2026-08-01: Cognition launched Outposts, a new Devin feature that lets it natively run and test apps on any computer.
Relevance to AI PMs
1. Design better human-in-the-loop workflows. Devin’s QA flow shows a practical pattern: let the agent draft and execute, but require human approval at key checkpoints such as test-plan signoff and PR review. PMs can use this as a blueprint for balancing speed with accountability.
2. Evaluate AI tools on operational depth, not just code generation. Devin’s expansion into testing, security validation, audits, stacked PR management, and external execution via Outposts gives PMs a framework for comparing tools based on workflow coverage and reliability, not only coding quality.
3. Accelerate delivery for complex enterprise environments. With support for Windows, cloud handoff, runtime testing, and security remediation, Devin is relevant for PMs managing legacy modernization, regulated environments, or distributed engineering systems where deployment context matters as much as authoring code.
Related
- Cognition: The company behind Devin and the source of major launches including Outposts, Security Swarm, Windows support, and /handoff.
- Outposts: A new Devin feature for running and testing apps on external computers; important for real-world validation beyond a single hosted environment.
- /handoff: Devin CLI capability that keeps agents running in the cloud after the user leaves, reinforcing async workflows.
- Security Swarm: A security-focused Devin pillar for vulnerability discovery, runtime validation, and remediation PR generation.
- GitHub / github-stacked-prs / Linear: Connected to Devin’s role in code review, issue flow, and developer workflow orchestration.
- Windows: A notable platform expansion that makes Devin more relevant for enterprise modernization use cases.
- Codex, Cursor, Claude Code, Windsurf-20, Lovable, ChatPRD: Adjacent AI product-building and coding tools that PMs may compare against Devin when evaluating agentic development stacks.
- OpenClaw and Ryan Carson: Example ecosystem usage showing Devin as part of a broader automation stack.
- MetaviewAI, Evinova, AstraZeneca, Rivian, Volkswagen, Infosys, ITA, Slack: Related organizations mentioned in the broader ecosystem that may matter when tracking enterprise adoption patterns around AI tooling.
Newsletter Mentions (24)
“Cognition launched Outposts, a new Devin feature that lets you natively run and test apps on any computer.”
#8 𝕏 Cognition launched Outposts, a new Devin feature that lets you natively run and test apps on any computer.
“Cognition : Devin now natively supports GitHub Stacked PRs, breaking large changes into smaller, reviewable diffs, addressing and fixing comments across stacks, and automatically rebasing downstream changes.”
#16 𝕏 Cognition : Devin now natively supports GitHub Stacked PRs, breaking large changes into smaller, reviewable diffs, addressing and fixing comments across stacks, and automatically rebasing downstream changes. #17 𝕏 Cognition updated FrontierCode 1.1 with new discounts for GPT-5.6 Terra and Luna, positioning the GPT-5.6 series on the Pareto curve for price/performance efficiency.
“Cognition launched Security Swarm—a new pillar of Devin for Security that bundles tools to find vulnerabilities, validate them at runtime, and automatically ship remediation PRs.”
#8 𝕏 Cognition launched Security Swarm—a new pillar of Devin for Security that bundles tools to find vulnerabilities, validate them at runtime, and automatically ship remediation PRs.
“Cognition shows how @s16h_ and the @MetaviewAI team leveraged Devin to complete a typically weeks-long SOC2 audit in just two days.”
#9 𝕏 Cognition shows how @s16h_ and the @MetaviewAI team leveraged Devin to complete a typically weeks-long SOC2 audit in just two days.
“Cognition : Devin built an automated QA workflow where you review and approve a test plan before PR review, then receive a screen recording with a visual, step-by-step QA checklist.”
The newsletter highlights Devin as an automation layer for QA and PR workflows. It emphasizes human approval before review and visual evidence after execution.
“Cognition ’s Devin tool reasons across your entire codebase to uncover deep business-logic flaws—like an unauthenticated password-reset endpoint—by tracing request flows through auth layers that pattern-matching scanners miss.”
📝 𝕏 Cognition ’s Devin tool reasons across your entire codebase to uncover deep business-logic flaws—like an unauthenticated password-reset endpoint—by tracing request flows through auth layers that pattern-matching scanners miss.
“#15 𝕏 Cognition open sourced /handoff, the Devin CLI feature that lets your agents keep running in the cloud even after you close your laptop.”
#15 𝕏 Cognition open sourced /handoff, the Devin CLI feature that lets your agents keep running in the cloud even after you close your laptop.
“Cognition dives into @ido_pesok’s technical breakdown of how Devin’s VM-based end-to-end testing framework was built to handle verification at scale.”
#10 𝕏 Cognition dives into @ido_pesok’s technical breakdown of how Devin’s VM-based end-to-end testing framework was built to handle verification at scale.
“Ryan Carson demonstrates how he leverages OpenClaw's ClawChief cron jobs and markdown skills together with Codex and cloud-based Devin to automate his executive assistant workflow, nightly sales prospecting via the Firecrawl API, and ship over 10 pull requests per day.”
▶️ How This 5x Founder Runs His Startup Solo With AI Agents (OpenClaw, Codex, Devin) | Ryan Carson Peter Yang Ryan Carson demonstrates how he leverages OpenClaw's ClawChief cron jobs and markdown skills together with Codex and cloud-based Devin to automate his executive assistant workflow, nightly sales prospecting via the Firecrawl API, and ship over 10 pull requests per day. In a cloud-based Devin environment, Ryan runs scheduled automations with playbooks—such as weekly end-to-end user journey tests—and applies a “land PR” skill to review and merge code, resulting in at least 10 pull requests shipped per day.
“Cognition launched Devin on Windows, letting PM Builders map, build, and modernize Windows applications.”
#15 𝕏 Cognition launched Devin on Windows, letting PM Builders map, build, and modernize Windows applications.
Related
An Anthropic coding tool that supports session-to-session messaging and agent-like workflows. In this newsletter it’s discussed in the context of multi-session coordination and managed agent behavior.
An AI code editor mentioned as one of the tools used alongside Codex, Manos, and Claude in the Total Recall workflow example.
An AI coding tool used by the speaker in the Total Recall example. It is part of the stack of agent tools used for coding-session memory and workflow recovery.
An AI company behind Devin. It’s mentioned for running Devin Outposts on Vercel Sandbox for isolated app build/test workflows.
A plugin included with TencentDB Agent Memory. It appears to be part of the framework's integration layer for agent memory workflows.
A model used as an automated judge in Claire Vo’s benchmark. It contributes 30% of the scoring alongside her manual evaluation.
A workplace messaging tool used for alerts and human-in-the-loop actions in AI workflows. Here it receives notifications from the PR-review agent.
A product/task management tool used in the newsletter as part of an AI triage workflow. It is one of the systems Codex checks and integrates with to prioritize work.
A software collaboration platform central to code review, PRs, and developer automation. It’s the event source and review surface for the Merge Mommy agent.
An AI-first product management tool or startup referenced by Claire Vo. The newsletter uses it in a discussion of shipping an AI-first version of an app without traditional PM tooling.
A model used in the newsletter as a reasoning and execution engine for product experimentation. It is described as generating daily A/B test ideas and implementing winners for a mobile game economy.
A no-code AI app builder referenced here as the platform used to build a production-grade SaaS product. For PMs, it illustrates how agentic coding is changing build-vs-buy and software creation economics.
Stay updated on Devin
Get curated AI PM insights delivered daily — covering this and 1,000+ other sources.
Subscribe Free