How Devin Covers Every Stage of the Software Lifecycle
• Understand
• Build
• Test
• Verify
• Review
• Secure
• Operate
Everything you need to know in 6 Minutes
• Understand
• Build
• Test
• Verify
• Review
• Secure
• Operate
Everything you need to know in 6 Minutes
7
20
255
From Software Factory to Model Factory
@TheWuster from Cognition uses @DevinAI to train a custom image model on @modal, deploy it, and ship it into a product
@TheWuster from Cognition uses @DevinAI to train a custom image model on @modal, deploy it, and ship it into a product
7
16
225
Devin Fusion. Better and cheaper.
Devin Fusion has claimed a top score of 68 on the @ArtificialAnlys Coding Agent Index with an Opus 5.5 lead and GPT-6 Luna sidekick.
Devin Fusion outperforms Claude Code with Opus 5.5 on both performance and price – earning a score of 68 at a 31% lower cost per task.
7
14
158
Dynamic workflows let Devin split a big job into pieces, hand each one to its own Devin, and bring the results back together.
The plan for a Dynamic Workflow lives in code instead of an agent’s head, so you always know which Devins will run, in what order, and what each one is told.
The plan for a Dynamic Workflow lives in code instead of an agent’s head, so you always know which Devins will run, in what order, and what each one is told.
25
25
239
The hardware you run no longer dictates where or what you can build
macOS, Linux, Windows, and Android cloud environments on-demand with Devin
macOS, Linux, Windows, and Android cloud environments on-demand with Devin
coding is solved. i own a windows pc, but i can build for iOS seamlessly.
thanks @cognition 🎉
14
13
195
Devins can start managed Devins of their own, so one task can branch into a tree of Devins several levels deep.
Work done in sequence takes as long as all its parts added together, while work split this way takes roughly as long as its slowest part.
So size stops being the poned, since a larger task simply produces a larger tree.
Work done in sequence takes as long as all its parts added together, while work split this way takes roughly as long as its slowest part.
So size stops being the poned, since a larger task simply produces a larger tree.
22
27
231
Security Swarm sends a swarm of parallel Devins through your codebase to build a threat model, hunt down real, exploitable vulnerabilities (even ones chained across files), prove them in a sandbox, and hand you the fix as a pull request.
Here's how it works:
Here's how it works:
22
21
228
Cloud agents get much more useful when they can run the real toolchain: xcodebuild, the iOS Simulator, Computer Use tapping through the UI.
Every Devin session gets its own cloud Mac so mobile work can be delegated like any other ticket. Here's how it works:
Every Devin session gets its own cloud Mac so mobile work can be delegated like any other ticket. Here's how it works:
11
20
183
Fusion in Devin Desktop & CLI
Fusion achieves frontier intelligence while being up to 39% cheaper.
Use your favorite frontier model for planning and a cost-effective model for execution.
Fable/Astra + SWE-2 is very cost-effective during SWE-2’s free promo.
Fusion achieves frontier intelligence while being up to 39% cheaper.
Use your favorite frontier model for planning and a cost-effective model for execution.
Fable/Astra + SWE-2 is very cost-effective during SWE-2’s free promo.
Introducing Fusion in Devin CLI
The most efficient frontier harness for Fable & Astra; 39% cheaper across coding benchmarks.
Pick your favorite model for planning and a cost-effective model for execution.
19
16
257
The Devin CLI has a brand new model picker! You can now set your model, tune its reasoning effort, and compare costs - all in one view
Try it today with `/model`
Try it today with `/model`
24
26
339
GPT-5.6 Sol is now 70% off in Devin Desktop and Devin CLI, through October 3.
On FrontierCode 1.1, Sol achieves top-tier results. With this promo, it's one of the most cost-effective frontier models you can run in Devin.
On FrontierCode 1.1, Sol achieves top-tier results. With this promo, it's one of the most cost-effective frontier models you can run in Devin.
52
81
1,086
We're making SWE-1.7 and GLM-5.2 free for the next month!
All Pro, Max, and Teams users can keep using both models in Devin Desktop and Devin CLI.
All Pro, Max, and Teams users can keep using both models in Devin Desktop and Devin CLI.
95
70
1,099
Kimi K2.7 Code and GLM 5.2 are available in Devin Desktop and CLI
Both perform strongly on FrontierCode Extended, our benchmark for real-world engineering tasks:
GLM 5.2: 43.0%
Kimi K2.7 Code: 39.5%
Pro/Max/Teams users can try both models for free until July 5
Both perform strongly on FrontierCode Extended, our benchmark for real-world engineering tasks:
GLM 5.2: 43.0%
Kimi K2.7 Code: 39.5%
Pro/Max/Teams users can try both models for free until July 5
31
45
448
At @tryramp, engineers use Devin Desktop to bring their favorite agents into one place.
With Devin Desktop they can dispatch, monitor, and jump between agents from a single surface with shared context across every task.
With Devin Desktop they can dispatch, monitor, and jump between agents from a single surface with shared context across every task.
1
5
75
Claude Agent now runs inside Devin Desktop.
Start Claude Agent sessions in Devin Desktop, coordinate them with your other agents, and keep context shared from a single command center.
Learn more about using your favorite agents in Devin Desktop:
docs.devin.ai/desktop/acp
Start Claude Agent sessions in Devin Desktop, coordinate them with your other agents, and keep context shared from a single command center.
Learn more about using your favorite agents in Devin Desktop:
docs.devin.ai/desktop/acp
2
1
34
Codex CLI now runs inside Devin Desktop.
You can pair your Codex subscription with Devin Desktop to have native multi-agent orchestration.
Learn more about using your favorite agents in Devin Desktop: docs.devin.ai/desktop/acp
You can pair your Codex subscription with Devin Desktop to have native multi-agent orchestration.
Learn more about using your favorite agents in Devin Desktop: docs.devin.ai/desktop/acp
5
1
48
Devin Desktop is built on the Windsurf IDE. Your settings, extensions, keybindings, LSPs, and workflows carry over.
Most agent work should happen in the background. But when you need to review, debug, or make the last-mile edit, the full IDE is exactly where you need it.
Most agent work should happen in the background. But when you need to review, debug, or make the last-mile edit, the full IDE is exactly where you need it.
2
2
51
Devin Desktop supports the Agent Client Protocol (ACP), and is now compatible with Codex, Claude Agent, OpenCode, and any other ACP-compatible agent.
This lets users manage multiple agents from one surface and share context between them.
This lets users manage multiple agents from one surface and share context between them.
8
5
96
Introducing Devin Desktop: the next generation of Windsurf
Manage fleets of local and cloud agents from one surface
Support for any ACP-compatible agent
With a full IDE for when you need to jump into the code
Manage fleets of local and cloud agents from one surface
Support for any ACP-compatible agent
With a full IDE for when you need to jump into the code
105
107
944
Claude Opus 4.7 (fast mode) is now available in Windsurf!
Full Claude Opus 4.7 intelligence
~2.5x higher output speeds
We can't wait to see what you'll build with it!
Full Claude Opus 4.7 intelligence
~2.5x higher output speeds
We can't wait to see what you'll build with it!
22
19
209
Devin Review runs hundreds of thousands of times per day.
Starting today, run it directly from Windsurf: a smart reviewer in your editor, with bugs and context in one place.
Also launching Quick Review: 10x faster bug detection powered by SWE-check, available only in Windsurf.
Starting today, run it directly from Windsurf: a smart reviewer in your editor, with bugs and context in one place.
Also launching Quick Review: 10x faster bug detection powered by SWE-check, available only in Windsurf.
27
41
322
Claude Opus 4.7 is now available in Windsurf 2.0!
Anthropic has clearly optimized Claude Opus 4.7 for sustained reasoning over long runs. Agents stay on track longer without intervention, so engineers can manage multiple agents in parallel instead of working 1:1.
Claude Opus available at promotional pricing until April 30th across all plans.
Let us know if there's anything else you need from us!
Anthropic has clearly optimized Claude Opus 4.7 for sustained reasoning over long runs. Agents stay on track longer without intervention, so engineers can manage multiple agents in parallel instead of working 1:1.
Claude Opus available at promotional pricing until April 30th across all plans.
Let us know if there's anything else you need from us!
29
34
421
Devin runs in its own VM in the cloud.
You plan locally, delegate to Devin with one click, and keep coding (or close your laptop). Included with every Windsurf plan.
Access to Devin in Windsurf is rolling out gradually over the next 48 hours.
You plan locally, delegate to Devin with one click, and keep coding (or close your laptop). Included with every Windsurf plan.
Access to Devin in Windsurf is rolling out gradually over the next 48 hours.
1
1
66
Every time you switch tasks, you lose context.
Spaces help you stay in the flow by grouping agent sessions, PRs, files, and context for a project. When you return to a Space, you can pick up where you left off.
Spaces help you stay in the flow by grouping agent sessions, PRs, files, and context for a project. When you return to a Space, you can pick up where you left off.
2
1
74
The more agents you run, the harder it gets to track what's running, what's blocked, and what needs review.
The Agent Command Center puts all your agents - local and cloud - in a single Kanban view.
The Agent Command Center puts all your agents - local and cloud - in a single Kanban view.
5
9
138
Introducing Windsurf 2.0.
Manage all your agents from one place and delegate work to the cloud with Devin - so your agents keep shipping even after you close your laptop.
Manage all your agents from one place and delegate work to the cloud with Devin - so your agents keep shipping even after you close your laptop.
128
180
1,973
When we launched our new quota system, we should have been clearer: your quota and extra usage are billed based on tokens consumed.
To address that, we’re introducing a redesigned model picker that shows exact token pricing upfront, so you can plan your model usage based on the model.
To help you manage token costs better, we also added a prompt cache timer directly in the context window and now show precise token counts on every response card.
To address that, we’re introducing a redesigned model picker that shows exact token pricing upfront, so you can plan your model usage based on the model.
To help you manage token costs better, we also added a prompt cache timer directly in the context window and now show precise token counts on every response card.
2
2
28
Adaptive is now live - our new intelligent model router.
It automatically picks the best model for every task while avoiding overuse of premium models, so your quota lasts significantly longer.
For the next 2 weeks, we’re offering promotional rates for adaptive to give you a $0.50 per 1M input, $2 per 1M output, $0.10 per 1M cache read tokens.
We’re rolling out the Adaptive model to all self-serve users today, including Pro, Max, and Teams.
We expect this to be the best default option for most users who want to stay within the quota limits throughout the month, and we’ll continue deploying new updates to improve routing performance.
It automatically picks the best model for every task while avoiding overuse of premium models, so your quota lasts significantly longer.
For the next 2 weeks, we’re offering promotional rates for adaptive to give you a $0.50 per 1M input, $2 per 1M output, $0.10 per 1M cache read tokens.
We’re rolling out the Adaptive model to all self-serve users today, including Pro, Max, and Teams.
We expect this to be the best default option for most users who want to stay within the quota limits throughout the month, and we’ll continue deploying new updates to improve routing performance.
3
8
62
GPT-5.4 is live in Windsurf with multiple reasoning efforts!
GPT-5.4 Low is also available in Arena Mode's Frontier and Hybrid Battle Groups.
Let us know what you think!
GPT-5.4 Low is also available in Arena Mode's Frontier and Hybrid Battle Groups.
Let us know what you think!
21
15
349
Gemini 3.1 Pro is live in Windsurf!
It's also available in Arena Mode's Frontier and Hybrid Battle Groups.
Let us know what you think!
It's also available in Arena Mode's Frontier and Hybrid Battle Groups.
Let us know what you think!
23
20
333
Claude Sonnet 4.6 is live in Windsurf, with support for 1M token context!
Sonnet 4.6 is also available in Arena Mode’s Frontier and Hybrid Battle Groups.
Let us know what you think!
Sonnet 4.6 is also available in Arena Mode’s Frontier and Hybrid Battle Groups.
Let us know what you think!
23
19
364
GLM-5 and Minimax M2.5 are live in Windsurf!
Limited-time discounts:
- GLM-5: 0.75x credits
- Minimax M2.5: 0.25x credits.
Both models are also available in Arena Mode's Frontier and Hybrid Battle Groups.
Limited-time discounts:
- GLM-5: 0.75x credits
- Minimax M2.5: 0.25x credits.
Both models are also available in Arena Mode's Frontier and Hybrid Battle Groups.
18
26
544
GPT-5.3-Codex-Spark (preview) is now live in Windsurf Arena Mode.
For now, it's exclusively available through the Fast and Hybrid Arena Battle Groups.
For now, it's exclusively available through the Fast and Hybrid Arena Battle Groups.
25
20
295
The Arena Mode Public Leaderboard is live!
Top Frontier models:
1. Opus 4.6
2. Opus 4.5
3. Sonnet 4.5
Top Fast models:
1. SWE 1.5
2. Haiku 4.5
3. Gemini 3 Flash Low
Live leaderboard link and analysis below.
Top Frontier models:
1. Opus 4.6
2. Opus 4.5
3. Sonnet 4.5
Top Fast models:
1. SWE 1.5
2. Haiku 4.5
3. Gemini 3 Flash Low
Live leaderboard link and analysis below.
25
27
331
Opus 4.6 (fast mode) is now available in Windsurf in research preview! It's just as smart as regular Opus 4.6 but runs up to 2.5x faster.
Users will have access to promo pricing until Feb 16.
Let us know what you think.
Users will have access to promo pricing until Feb 16.
Let us know what you think.
23
21
313
Opus 4.6 is free in Arena Mode!
And, we've extended the free period for Arena Mode Battle Groups (Frontier, Hybrid, and Fast) through Sunday.
How to get started 👇
And, we've extended the free period for Arena Mode Battle Groups (Frontier, Hybrid, and Fast) through Sunday.
How to get started 👇
18
32
494
With Arena Mode, you can select specific models to run (up to 5). Credits will be used based on the selected models.
To use Arena Mode for free for the next week, choose a Battle Group. Models like Opus 4.5, GPT-5.2-Codex, and Kimi K2.5 are included in the Frontier group!
To use Arena Mode for free for the next week, choose a Battle Group. Models like Opus 4.5, GPT-5.2-Codex, and Kimi K2.5 are included in the Frontier group!
Introducing Arena Mode in Windsurf: One prompt. Two models. Your vote.
Benchmarks don't reflect real-world coding quality. The best model for you depends on your codebase and stack. So we made real-world coding the benchmark.
Free for the next week. May the best model win.
17
14
221
We've also added Plan Mode!
It's fully compatible with Arena Mode so you can find your favorite model for planning.
Pro tip: type "megaplan" in the chatbox for an extra-thorough interactive planning experience.
It's fully compatible with Arena Mode so you can find your favorite model for planning.
Pro tip: type "megaplan" in the chatbox for an extra-thorough interactive planning experience.
Introducing Arena Mode in Windsurf: One prompt. Two models. Your vote.
Benchmarks don't reflect real-world coding quality. The best model for you depends on your codebase and stack. So we made real-world coding the benchmark.
Free for the next week. May the best model win.
14
11
263
Kimi K2.5 is live in Windsurf! And, it's one of the models available in Arena Mode's Frontier Arena.
Let's see if it lives up to the hype!
0x credits for paid users (limited time).
Let's see if it lives up to the hype!
0x credits for paid users (limited time).
20
16
301
Arena Mode is part of Wave 14! We've also added Plan Mode to Cascade.
Check out the blog post for more details: windsurf.com/blog/windsurf-…
Check out the blog post for more details: windsurf.com/blog/windsurf-…
3
5
60
