Learn Devin the practical way
Clear guides for the Devin community and for people coming from Cursor, Claude Desktop, Copilot, or Windsurf.
Tutorial & demo videos
TubeOnAI-assessed learning resources from official and community YouTube videos.
-
demo · Video
Solving Open Math Problems with 100+ Parallel Devins
Here's a summary of the concrete claims, demos, limitations, and source-worthy details about Devin and Cognition from the video: Devin Product Claims & Demos: Automated Problem Solving:* Devin can be prompted to find and solve open math problems. Parallel Processing:* Devin can spin up and manage over 100 "child sessions" (agents) that work in parallel on different approaches to a problem. "Ultra Mode":* This mode utilizes the best available models (Fable, Soul) for problem-solving. Prompt Variation:* Devin can run the same problem multiple times with slightly different prompts (e.g., "solve X way," "investigate Y") to harness entropy and increase the chance of success. Self-Correction/Iteration:* Devin can re-evaluate, redo tasks, and provide encouraging words to its sub-agents. Environment Improvement:* Devin can optimize its operating environment to increase speed. Content Generation:* Devin can generate follow-up tweets, explanations of solved problems, and graphics for solutions. Formalization & Verification:* Devin can assist in formalizing solutions (e.g., using Lean) and running verification tests. Multi-Agent Communication:* Devin's architecture facilitates communication between agents, with examples of the master agent encouraging child sessions. Sandboxed Environment:* Devin's architecture is described as sandboxed, making it easier to manage multiple agents as "teammates." Public GitHub Repo:* The speaker has made a public GitHub repository containing the formalizations and the process. Cognition Product Claims & Demos: Cloud Agent Product:* Devin is presented as a cloud agent product, which is crucial for enabling long-running, parallel tasks without requiring the user's local machine. "Nerd Sniping" Capability:* The platform can be used to tackle complex, engaging problems. Team of Math Professors:* Cognition has math professors on staff who provided advice on the math problems. Limitations & Nuances: Prompt Engineering is Key:* While Devin automates much of the process, the initial prompt is crucial for directing Devin to find relevant problems. Model Dependence:* The success of problem-solving relies on the underlying AI models (Fable, Soul, GPT-4). "Earth-Shattering" Scale:* The initial problems solved, while novel and previously unsolved, were ranked lower on an "earth-shattering" scale (Richter scale analogy). Potential for Pre-existing Solutions:* One of the solved problems was later found to have a solution in a Git repo from a month prior. Token Limits:* The speaker encountered and had to manage token limits. Verification Importance:* Human verification and collaboration with math experts were necessary to ensure the correctness and avoid embarrassment. AI-Generated Tweets:* Using AI for writing tweets directly can result in boring content; the speaker used it for explanations instead. Not a Replacement for Expertise:* While Devin automates the process, human mathematicians are still needed for deeper understanding and solving truly groundbreaking problems. Exact Source-Worthy Details: Inspiration:* A tweet by "Dimitri" about ChatGPT solving a 30-year-old problem with "gigachad prompting." Initial Prompt:* "Find open math problems we can solve like this together." Methodology:* * Run in "ultra mode" using best models. * Run many agents in parallel. * Run each problem five times with slightly different prompts to harness entropy. * Select the best 10-15 problems. * Focus on counter-examples as a good first step. * "Don't stop. Try a different attack." (Example of agent communication). Verification:* * "Lean formalization" was used to verify solutions. * Adversarial verifications were run. * Solutions were ranked on an "earth-shattering" scale. Problems Solved (mentioned):* * One 30-year-old problem (inspiration). * Several other conjectures: one proved false, one proved true, one refuted. * Five new theorems settled, including a 35-year-old conjecture. Cognition Collaboration:* The speaker mentioned working with math "geniuses" on their team at Cognition. Public Repository:* The speaker is making the repo public with all formalizations. Call for Collaboration:* Seeking a fellow to help solve more unsolved problems.
-
tutorial · From Videos
Cloud Stacked Diffs: Turn One Prompt Into a Stack of Reviewable PRs (with Linear + Devin)
Cloud Stacked Diffs: Turn One Prompt Into a Stack of Reviewable PRs (with Linear + Devin)
-
tutorial · Video
How to Install and Set Up Devin Desktop on Windows 11
How to Install and Set Up Devin Desktop on Windows 11
-
tutorial · Video
How to Build AI Agents That Check Their Own Work | Jared Zoneraich
🔥 Build agents by "letting the model cook": give simple high-level instructions and useful tools, not brittle, ultra-specific prompt hacks. – Tool engineering (choosing which tools the model can use) is the primary lever for capability and longevity. 💡 Align your roadmap with model progress: expect hacks like chain-of-thought prompting to become less important over time. – Do not treat prompt-engineering tricks as long-term defensibility. ⚙️ Rollout strategy: prioritize done over perfect; aim for an 80% working product quickly and invest long tail effort on the final 20%. – Users are often forgiving of probabilistic AI behavior during novel workflows. 🔎 Eval approach: avoid getting stuck on exhaustive deterministic tests before shipping; use smoke tests and iterative production feedback instead. – Agents can be given programmatic sanity checks to validate and iterate on their own outputs. 🤖 Agents should verify and iterate on their own work where possible, using tests, screenshots, or programmatic endpoints as evidence. – Self-evaluation reduces human bottlenecks and accelerates autonomous improvement. ☁️ Cloud agent paradigm: run agents as asynchronous cloud VMs that persist and work independently of a human session. – This enables background work, mobile-triggered jobs, and continuous automation. 🔗 Master–child orchestration: a master agent can spin up multiple child agents (each with its own VM) to parallelize tasks and keep contexts small. – Parallelization speeds large projects and reduces per-agent context-window pressure. 🧩 Use cases for fan-out agents: large code migrations, parallelized testing, focused single-responsibility tasks, and breaking monolithic jobs into verifiable chunks. – Each child agent can write, run, test, take screenshots, and produce PRs independently. 👥 Multiplayer workflow: support human + agent collaboration and team-shared skills, macros, playbooks, and indexed docs to capture knowledge and speed onboarding. – Indexing repos and auto-generating docs provides immediate ROI on large or poorly-documented codebases. 🏢 Product fit: agent harnesses that prioritize verifiable code, testing, and brownfield engineering are attractive to enterprises where correctness matters. – These tools are especially useful for migrations, test coverage, and legacy modernization. 💸 Cost model: evaluate spending by ROI, not token count; route simple tasks to cheaper models and complex tasks to stronger models to balance cost and value. – A harness should optimize model selection for task-fit rather than incentivize token maximization. 🌐 Market view: building a great coding agent is a core, high-leverage problem with many downstream applications, and the market may bifurcate into hardcore engineering tools and short-form "play" tools. – Non-technical agent use cases will continue to grow alongside coding-focused products. 🧭 Long-term thesis: many artifacts (raw code, slides, simple UIs) may become second-order outputs produced by higher-level agent interactions or APIs. – Design products for agent-first access patterns and discoverability rather than only human-first UI.
The guide path
Written in order — each step assumes the one before it.
- 1 What is Devin? A practical explainer A clear overview of Devin — Cognition's AI software engineer — and when agentic coding actually helps you ship.
- 2 Devin's four surfaces: Cloud, Desktop, CLI, and Plugins Devin is not one product. Cloud, Desktop, the CLI, and the Windsurf Plugins line each do different work — and the local agent story changed in 2026.
- 3 Your first Devin Cloud session, end to end Connect a repo, build the snapshot Devin boots from, and run a first task in Ask mode before letting Agent mode loose.
- 4 Writing tasks Devin can actually finish Scope decides whether an agent session succeeds. Cognition's own guidance: clear success criteria, wide and shallow over tall and deep, and roughly three hours of work.
- 5 Knowledge, Playbooks, and Skills: teaching Devin your codebase Three features that look interchangeable and are not. Knowledge is context, Playbooks are reusable prompts, Skills are procedures committed to the repo.
- 6 Devin Review and the pull request workflow How Devin reviews pull requests, the three ways to open a review, and where a human still has to make the call.
- 7 Plans, usage, and what an ACU actually is Devin's plan tiers, how usage is metered, and an honest account of what Cognition does and does not publish about Agent Compute Units.
Want the releases instead of the fundamentals? Read the news desk or get it by email.