{
  "@context": "https://schema.org",
  "@id": "https://aggr.aymericbeaumet.com/items/cognition-com/2024-12-10-devin-is-now-generally-available/#webpage",
  "@type": [
    "WebPage",
    "ArchiveComponent"
  ],
  "articleBody": "Today we’re making Devin generally available starting at $500 a month for engineering teams, which includes:\n\n- No seat limits\n- Access to Devin’s Slack integration, IDE extension, and [API](https://www.cognition.ai/blog/dec-24-product-update#for-repetitive-engineering-tasks-try-the-devin-api-with-structured-inputoutput)\n- Onboarding session & support from the Cognition engineering team\n\nAll engineering teams can now start working with Devin at [app.devin.ai](http://app.devin.ai).\n\n## **Where Devin Shines**\n\nWhile Devin can be an all-purpose tool, we recommend starting with:\n\n- **Small frontend bugs and edge cases** - tag Devin in Slack threads\n- **Creating first-draft PRs for backlog tasks** - assign Devin tasks from your todo list at the start of your day\n- **Making targeted code refactors** - use the Devin IDE extension (for VSCode and forks) to point Devin to parts of the code you want edited or upgraded\n\nDevin has helped teams with everything from building integrations to migrating and maintaining documentation. Devin is versatile, but works best when you:\n\n- Give Devin tasks that you know how to do yourself\n- Tell Devin how to test or check its own work\n- Keep sessions under ~3 hours and break down large tasks\n- Share detailed requirements upfront\n- Invest in coaching Devin by providing feedback in chat and accepting suggested [Knowledge](https://docs.devin.ai/Onboard_Devin/knowledge), or adding your own Knowledge manually\n\n## **Working with Devin**\n\nSlack is the primary interface for spinning up Devin sessions, so you can quickly tag @devin to offload smaller tasks and fix bugs when they’re reported.\n\nTry asking Devin to do the first pass on the next 3rd party integration, refactor, or codebase question you have. Devin messages you when it’s done, so you can review Devin’s PR whenever convenient. Devin responds automatically to your Github PR comments.\n\n[YouTube video](https://www.youtube.com/watch?v=xTbpGq09g88)\n\nHand off async work to Devin directly from your IDE with ⌘ G. The Devin extension (Beta Feature available for VScode and forks) allows you to checkout Devin’s PRs and review and accept Devin’s code directly in your IDE.\n\n[YouTube video](https://www.youtube.com/watch?v=0e6Vx4rngm8)\n\n## **Contributing to Open Source Repositories**\n\nTo showcase Devin in action, we’re sharing sessions where Devin resolves issues on a few of our favorite open-source repositories. Devin often needs guidance but we share these examples to show how we use Devin to speed our own workflows.\n\n**Anthropic MCP**\\\nIn this session, Devin identifies the cause of a user-reported issue. We liked how it read the MCP spec in the browser to understand “capability negotiation” and tested its changes end-to-end in the browser. The changes weren’t perfect, so the maintainers gave some feedback on the PR which we addressed with a second Devin session.\n\nFirst session: https://app.devin.ai/sessions/266955553baf40cfa7fdd32d42ab219d\n\nSecond session: https://app.devin.ai/sessions/807168f5f9874d47a4c1965bf7afc9df\n\nhttps://github.com/modelcontextprotocol/inspector/pull/105\n\n![Devin is now generally available](https://cdn.sanity.io/images/2mc9cv2v/production/c7c887019189c18355d40cf904fba5448f21d5f5-2014x168.png?w=1600&fit=max)\n\n**Zod**\\\nThis PR adds a new feature to the popular library Zod. Devin planned collaboratively with the user, implemented the feature across multiple files and wrote tests – we were very impressed! There was a merge conflict which we manually resolved because Devin tends to struggle with that.\n\nhttps://app.devin.ai/sessions/51826709fcd3457abc4be25e587c790c\n\nhttps://github.com/colinhacks/zod/pull/3893\n\n![Devin is now generally available](https://cdn.sanity.io/images/2mc9cv2v/production/3411a1a87aa611878f7658e15649177b428bf706-1736x168.png?w=1600&fit=max)\n\n**Google**\n\nA user of the Go Github client wished it propagated response objects even on HTTP errors. These small chores are annoying for human engineers because testing is often more effort than the fix itself. Devin required a few iterations to get it right and we manually cleaned up a few stray edits using the VS Code extension. The biggest timesaver here was Devin writing and running the unit tests.\n\nhttps://app.devin.ai/sessions/1b2f7ce6e3b44942b3ac1f518eac7c22\n\nhttps://github.com/google/go-github/pull/3369\n\n![Devin is now generally available](https://cdn.sanity.io/images/2mc9cv2v/production/18a73299e1ab51f155303433d963ed6069e18480-1854x168.png?w=1600&fit=max)\n\n**Llama Index**\n\nDevin fixes a bug where the implementation of the Anthropic tokenizer followed the protocol incorrectly. It found the correct fix first try and wrote a unit test too. A PR comment from the maintainer requested a small stylistic change which we fixed manually.\n\nhttps://app.devin.ai/sessions/3d66de6feed946efbadf8a58698caafc\n\nhttps://github.com/run-llama/llama_index/pull/17201\n\n![Devin is now generally available](https://cdn.sanity.io/images/2mc9cv2v/production/dc90640bf91bd47cdea29e98fc3b60aaf7cd8107-2042x168.png?w=1600&fit=max)\n\n**Karpathy’s nanoGPT\\**This change is just a one-liner. But we wouldn’t trust this change without testing – which Devin did nicely by writing an ad-hoc testing script.\n\nhttps://app.devin.ai/sessions/9e0c3255385c463f838f5b2f4413b92f\n\nhttps://github.com/karpathy/nanoGPT/pull/578\n\n![Devin is now generally available](https://cdn.sanity.io/images/2mc9cv2v/production/5a31675b672e516ea4fcb974ecfedb90b78a0c01-1712x168.png?w=1600&fit=max)\n\n## **Hire Devin**\n\nYou can start working with Devin today at [app.devin.ai](https://cognition.com/blog/devin-generally-available#).\n\nFor more information about [Devin Enterprise](https://devin.ai/enterprise), reach out to our Sales team [here](https://cognition.ai/get-started#company).\n",
  "authors": [],
  "captured_at": "2026-10-19T01:26:53.998049939+00:00",
  "category": "ai",
  "content_html": "<p>Today we’re making Devin generally available starting at $500 a month for engineering teams, which includes:</p>\n<ul>\n<li>No seat limits</li>\n<li>Access to Devin’s Slack integration, IDE extension, and <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://www.cognition.ai/blog/dec-24-product-update#for-repetitive-engineering-tasks-try-the-devin-api-with-structured-inputoutput\">API</a></li>\n<li>Onboarding session &amp; support from the Cognition engineering team</li>\n</ul>\n<p>All engineering teams can now start working with Devin at <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"http://app.devin.ai\">app.devin.ai</a>.</p>\n<h2><strong>Where Devin Shines</strong></h2>\n<p>While Devin can be an all-purpose tool, we recommend starting with:</p>\n<ul>\n<li><strong>Small frontend bugs and edge cases</strong> - tag Devin in Slack threads</li>\n<li><strong>Creating first-draft PRs for backlog tasks</strong> - assign Devin tasks from your todo list at the start of your day</li>\n<li><strong>Making targeted code refactors</strong> - use the Devin IDE extension (for VSCode and forks) to point Devin to parts of the code you want edited or upgraded</li>\n</ul>\n<p>Devin has helped teams with everything from building integrations to migrating and maintaining documentation. Devin is versatile, but works best when you:</p>\n<ul>\n<li>Give Devin tasks that you know how to do yourself</li>\n<li>Tell Devin how to test or check its own work</li>\n<li>Keep sessions under ~3 hours and break down large tasks</li>\n<li>Share detailed requirements upfront</li>\n<li>Invest in coaching Devin by providing feedback in chat and accepting suggested <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://docs.devin.ai/Onboard_Devin/knowledge\">Knowledge</a>, or adding your own Knowledge manually</li>\n</ul>\n<h2><strong>Working with Devin</strong></h2>\n<p>Slack is the primary interface for spinning up Devin sessions, so you can quickly tag @devin to offload smaller tasks and fix bugs when they’re reported.</p>\n<p>Try asking Devin to do the first pass on the next 3rd party integration, refactor, or codebase question you have. Devin messages you when it’s done, so you can review Devin’s PR whenever convenient. Devin responds automatically to your Github PR comments.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://www.youtube.com/watch?v=xTbpGq09g88\">YouTube video</a></p>\n<p>Hand off async work to Devin directly from your IDE with ⌘ G. The Devin extension (Beta Feature available for VScode and forks) allows you to checkout Devin’s PRs and review and accept Devin’s code directly in your IDE.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://www.youtube.com/watch?v=0e6Vx4rngm8\">YouTube video</a></p>\n<h2><strong>Contributing to Open Source Repositories</strong></h2>\n<p>To showcase Devin in action, we’re sharing sessions where Devin resolves issues on a few of our favorite open-source repositories. Devin often needs guidance but we share these examples to show how we use Devin to speed our own workflows.</p>\n<p><strong>Anthropic MCP</strong><br />\nIn this session, Devin identifies the cause of a user-reported issue. We liked how it read the MCP spec in the browser to understand “capability negotiation” and tested its changes end-to-end in the browser. The changes weren’t perfect, so the maintainers gave some feedback on the PR which we addressed with a second Devin session.</p>\n<p>First session: <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://app.devin.ai/sessions/266955553baf40cfa7fdd32d42ab219d\">https://app.devin.ai/sessions/266955553baf40cfa7fdd32d42ab219d</a></p>\n<p>Second session: <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://app.devin.ai/sessions/807168f5f9874d47a4c1965bf7afc9df\">https://app.devin.ai/sessions/807168f5f9874d47a4c1965bf7afc9df</a></p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/modelcontextprotocol/inspector/pull/105\">https://github.com/modelcontextprotocol/inspector/pull/105</a></p>\n<p><picture class=\"article-picture article-picture-fallback\" style=\"--image-ratio:16 / 9\"><img src=\"https://cdn.sanity.io/images/2mc9cv2v/production/c7c887019189c18355d40cf904fba5448f21d5f5-2014x168.png?w=1600&amp;fit=max\" alt=\"Devin is now generally available\" loading=\"eager\" decoding=\"async\" fetchpriority=\"high\" referrerpolicy=\"no-referrer\" class=\"progressive-image\"></picture></p>\n<p><strong>Zod</strong><br />\nThis PR adds a new feature to the popular library Zod. Devin planned collaboratively with the user, implemented the feature across multiple files and wrote tests – we were very impressed! There was a merge conflict which we manually resolved because Devin tends to struggle with that.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://app.devin.ai/sessions/51826709fcd3457abc4be25e587c790c\">https://app.devin.ai/sessions/51826709fcd3457abc4be25e587c790c</a></p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/colinhacks/zod/pull/3893\">https://github.com/colinhacks/zod/pull/3893</a></p>\n<p><picture class=\"article-picture article-picture-fallback\" style=\"--image-ratio:16 / 9\"><img src=\"https://cdn.sanity.io/images/2mc9cv2v/production/3411a1a87aa611878f7658e15649177b428bf706-1736x168.png?w=1600&amp;fit=max\" alt=\"Devin is now generally available\" loading=\"lazy\" decoding=\"async\" fetchpriority=\"low\" referrerpolicy=\"no-referrer\" class=\"progressive-image\"></picture></p>\n<p><strong>Google</strong></p>\n<p>A user of the Go Github client wished it propagated response objects even on HTTP errors. These small chores are annoying for human engineers because testing is often more effort than the fix itself. Devin required a few iterations to get it right and we manually cleaned up a few stray edits using the VS Code extension. The biggest timesaver here was Devin writing and running the unit tests.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://app.devin.ai/sessions/1b2f7ce6e3b44942b3ac1f518eac7c22\">https://app.devin.ai/sessions/1b2f7ce6e3b44942b3ac1f518eac7c22</a></p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/google/go-github/pull/3369\">https://github.com/google/go-github/pull/3369</a></p>\n<p><picture class=\"article-picture article-picture-fallback\" style=\"--image-ratio:16 / 9\"><img src=\"https://cdn.sanity.io/images/2mc9cv2v/production/18a73299e1ab51f155303433d963ed6069e18480-1854x168.png?w=1600&amp;fit=max\" alt=\"Devin is now generally available\" loading=\"lazy\" decoding=\"async\" fetchpriority=\"low\" referrerpolicy=\"no-referrer\" class=\"progressive-image\"></picture></p>\n<p><strong>Llama Index</strong></p>\n<p>Devin fixes a bug where the implementation of the Anthropic tokenizer followed the protocol incorrectly. It found the correct fix first try and wrote a unit test too. A PR comment from the maintainer requested a small stylistic change which we fixed manually.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://app.devin.ai/sessions/3d66de6feed946efbadf8a58698caafc\">https://app.devin.ai/sessions/3d66de6feed946efbadf8a58698caafc</a></p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/run-llama/llama_index/pull/17201\">https://github.com/run-llama/llama_index/pull/17201</a></p>\n<p><picture class=\"article-picture article-picture-fallback\" style=\"--image-ratio:16 / 9\"><img src=\"https://cdn.sanity.io/images/2mc9cv2v/production/dc90640bf91bd47cdea29e98fc3b60aaf7cd8107-2042x168.png?w=1600&amp;fit=max\" alt=\"Devin is now generally available\" loading=\"lazy\" decoding=\"async\" fetchpriority=\"low\" referrerpolicy=\"no-referrer\" class=\"progressive-image\"></picture></p>\n<p>**Karpathy’s nanoGPT**This change is just a one-liner. But we wouldn’t trust this change without testing – which Devin did nicely by writing an ad-hoc testing script.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://app.devin.ai/sessions/9e0c3255385c463f838f5b2f4413b92f\">https://app.devin.ai/sessions/9e0c3255385c463f838f5b2f4413b92f</a></p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/karpathy/nanoGPT/pull/578\">https://github.com/karpathy/nanoGPT/pull/578</a></p>\n<p><picture class=\"article-picture article-picture-fallback\" style=\"--image-ratio:16 / 9\"><img src=\"https://cdn.sanity.io/images/2mc9cv2v/production/5a31675b672e516ea4fcb974ecfedb90b78a0c01-1712x168.png?w=1600&amp;fit=max\" alt=\"Devin is now generally available\" loading=\"lazy\" decoding=\"async\" fetchpriority=\"low\" referrerpolicy=\"no-referrer\" class=\"progressive-image\"></picture></p>\n<h2><strong>Hire Devin</strong></h2>\n<p>You can start working with Devin today at <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://cognition.com/blog/devin-generally-available#\">app.devin.ai</a>.</p>\n<p>For more information about <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://devin.ai/enterprise\">Devin Enterprise</a>, reach out to our Sales team <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://cognition.ai/get-started#company\">here</a>.</p>\n",
  "content_markdown": "Today we’re making Devin generally available starting at $500 a month for engineering teams, which includes:\n\n- No seat limits\n- Access to Devin’s Slack integration, IDE extension, and [API](https://www.cognition.ai/blog/dec-24-product-update#for-repetitive-engineering-tasks-try-the-devin-api-with-structured-inputoutput)\n- Onboarding session & support from the Cognition engineering team\n\nAll engineering teams can now start working with Devin at [app.devin.ai](http://app.devin.ai).\n\n## **Where Devin Shines**\n\nWhile Devin can be an all-purpose tool, we recommend starting with:\n\n- **Small frontend bugs and edge cases** - tag Devin in Slack threads\n- **Creating first-draft PRs for backlog tasks** - assign Devin tasks from your todo list at the start of your day\n- **Making targeted code refactors** - use the Devin IDE extension (for VSCode and forks) to point Devin to parts of the code you want edited or upgraded\n\nDevin has helped teams with everything from building integrations to migrating and maintaining documentation. Devin is versatile, but works best when you:\n\n- Give Devin tasks that you know how to do yourself\n- Tell Devin how to test or check its own work\n- Keep sessions under ~3 hours and break down large tasks\n- Share detailed requirements upfront\n- Invest in coaching Devin by providing feedback in chat and accepting suggested [Knowledge](https://docs.devin.ai/Onboard_Devin/knowledge), or adding your own Knowledge manually\n\n## **Working with Devin**\n\nSlack is the primary interface for spinning up Devin sessions, so you can quickly tag @devin to offload smaller tasks and fix bugs when they’re reported.\n\nTry asking Devin to do the first pass on the next 3rd party integration, refactor, or codebase question you have. Devin messages you when it’s done, so you can review Devin’s PR whenever convenient. Devin responds automatically to your Github PR comments.\n\n[YouTube video](https://www.youtube.com/watch?v=xTbpGq09g88)\n\nHand off async work to Devin directly from your IDE with ⌘ G. The Devin extension (Beta Feature available for VScode and forks) allows you to checkout Devin’s PRs and review and accept Devin’s code directly in your IDE.\n\n[YouTube video](https://www.youtube.com/watch?v=0e6Vx4rngm8)\n\n## **Contributing to Open Source Repositories**\n\nTo showcase Devin in action, we’re sharing sessions where Devin resolves issues on a few of our favorite open-source repositories. Devin often needs guidance but we share these examples to show how we use Devin to speed our own workflows.\n\n**Anthropic MCP**\\\nIn this session, Devin identifies the cause of a user-reported issue. We liked how it read the MCP spec in the browser to understand “capability negotiation” and tested its changes end-to-end in the browser. The changes weren’t perfect, so the maintainers gave some feedback on the PR which we addressed with a second Devin session.\n\nFirst session: https://app.devin.ai/sessions/266955553baf40cfa7fdd32d42ab219d\n\nSecond session: https://app.devin.ai/sessions/807168f5f9874d47a4c1965bf7afc9df\n\nhttps://github.com/modelcontextprotocol/inspector/pull/105\n\n![Devin is now generally available](https://cdn.sanity.io/images/2mc9cv2v/production/c7c887019189c18355d40cf904fba5448f21d5f5-2014x168.png?w=1600&fit=max)\n\n**Zod**\\\nThis PR adds a new feature to the popular library Zod. Devin planned collaboratively with the user, implemented the feature across multiple files and wrote tests – we were very impressed! There was a merge conflict which we manually resolved because Devin tends to struggle with that.\n\nhttps://app.devin.ai/sessions/51826709fcd3457abc4be25e587c790c\n\nhttps://github.com/colinhacks/zod/pull/3893\n\n![Devin is now generally available](https://cdn.sanity.io/images/2mc9cv2v/production/3411a1a87aa611878f7658e15649177b428bf706-1736x168.png?w=1600&fit=max)\n\n**Google**\n\nA user of the Go Github client wished it propagated response objects even on HTTP errors. These small chores are annoying for human engineers because testing is often more effort than the fix itself. Devin required a few iterations to get it right and we manually cleaned up a few stray edits using the VS Code extension. The biggest timesaver here was Devin writing and running the unit tests.\n\nhttps://app.devin.ai/sessions/1b2f7ce6e3b44942b3ac1f518eac7c22\n\nhttps://github.com/google/go-github/pull/3369\n\n![Devin is now generally available](https://cdn.sanity.io/images/2mc9cv2v/production/18a73299e1ab51f155303433d963ed6069e18480-1854x168.png?w=1600&fit=max)\n\n**Llama Index**\n\nDevin fixes a bug where the implementation of the Anthropic tokenizer followed the protocol incorrectly. It found the correct fix first try and wrote a unit test too. A PR comment from the maintainer requested a small stylistic change which we fixed manually.\n\nhttps://app.devin.ai/sessions/3d66de6feed946efbadf8a58698caafc\n\nhttps://github.com/run-llama/llama_index/pull/17201\n\n![Devin is now generally available](https://cdn.sanity.io/images/2mc9cv2v/production/dc90640bf91bd47cdea29e98fc3b60aaf7cd8107-2042x168.png?w=1600&fit=max)\n\n**Karpathy’s nanoGPT\\**This change is just a one-liner. But we wouldn’t trust this change without testing – which Devin did nicely by writing an ad-hoc testing script.\n\nhttps://app.devin.ai/sessions/9e0c3255385c463f838f5b2f4413b92f\n\nhttps://github.com/karpathy/nanoGPT/pull/578\n\n![Devin is now generally available](https://cdn.sanity.io/images/2mc9cv2v/production/5a31675b672e516ea4fcb974ecfedb90b78a0c01-1712x168.png?w=1600&fit=max)\n\n## **Hire Devin**\n\nYou can start working with Devin today at [app.devin.ai](https://cognition.com/blog/devin-generally-available#).\n\nFor more information about [Devin Enterprise](https://devin.ai/enterprise), reach out to our Sales team [here](https://cognition.ai/get-started#company).\n",
  "dateCreated": "2026-10-19T01:26:53.998049939+00:00",
  "date_created": "2024-12-10T00:00:00+00:00",
  "date_modified": null,
  "date_published": "2024-12-10T00:00:00+00:00",
  "description": "Today we’re making Devin generally available starting at $500 a month for engineering teams, which includes: No seat limits Access to Devin’s Slack integration, IDE extension, and API Onboarding session & support from the Cognition…",
  "external_url": "https://cognition.com/blog/devin-generally-available",
  "git": {
    "commit": "ebb0941c5c06a2ab2377342d607535262a3e969e",
    "path": "items/cognition-com/2024/12/2024-12-10-devin-is-now-generally-available.md",
    "permalink": "https://github.com/aymericbeaumet/aggr-instance/blob/ebb0941c5c06a2ab2377342d607535262a3e969e/items/cognition-com/2024/12/2024-12-10-devin-is-now-generally-available.md"
  },
  "id": "urn:aggr:item:d6842b465c98711544441918a3e5b3c31f440e6d",
  "isBasedOn": {
    "@id": "https://cognition.com/blog/devin-generally-available"
  },
  "mainEntity": {
    "@id": "https://cognition.com/blog/devin-generally-available",
    "@type": "CreativeWork",
    "archivedAt": {
      "@id": "https://aggr.aymericbeaumet.com/items/cognition-com/2024-12-10-devin-is-now-generally-available/#webpage"
    },
    "datePublished": "2024-12-10T00:00:00+00:00",
    "headline": "Devin is now generally available",
    "image": {
      "@type": "ImageObject",
      "caption": null,
      "height": 90,
      "url": "https://cdn.sanity.io/images/2mc9cv2v/production/8f45a05478a85e9ac7bfb991b5b85a0faa4da2bc-7680x4320.png?rect=0,154,7680,4013&w=1200&h=627&fit=crop",
      "width": 160
    },
    "timeRequired": "PT4M",
    "url": "https://cognition.com/blog/devin-generally-available",
    "wordCount": 687
  },
  "name": "Archived snapshot: Devin is now generally available",
  "preview": {
    "alt": null,
    "color": null,
    "height": 90,
    "placeholder": {
      "data_url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNk+A8AAQUBAScY42YAAAAASUVORK5CYII=",
      "hash": ""
    },
    "url": "https://cdn.sanity.io/images/2mc9cv2v/production/8f45a05478a85e9ac7bfb991b5b85a0faa4da2bc-7680x4320.png?rect=0,154,7680,4013&w=1200&h=627&fit=crop",
    "width": 160
  },
  "reading_minutes": 4,
  "replicated_at": null,
  "source": "cognition-com",
  "source_name": "Blog | Cognition",
  "summary": null,
  "tags": [],
  "temporalCoverage": "2026-10-19T01:26:53.998049939+00:00",
  "title": "Devin is now generally available",
  "url": "https://aggr.aymericbeaumet.com/items/cognition-com/2024-12-10-devin-is-now-generally-available/",
  "word_count": 687
}