Introducing Code Scans | DevinProductSolutionsCustomersResourcesPricingGet a DemoLog inGet StartedIntroducing Code ScansCognition|September 16, 2026|5 min read|Copy linkToday we’re introducing Code Scans: a new way to turn broad engineering goals into concrete improvements across your codebase. Tell Devin what you want to achieve, and it helps you investigate what needs to change, evaluate the findings, and turn them into pull requests.
Many engineering tasks start with a specific change. Others start with an outcome:

Improve SEO
Reduce maintenance overhead
Make your application compile faster

These goals often stay on the backlog because the first step alone is a substantial project: investigating the codebase to figure out where to start. Additionally, identifying the opportunities is only half the work — someone still has to implement the changes, and many of them.
Code Scans helps with both.
Powered by Agentic MapReduce, the architecture we built for Devin Security Swarm, Code Scans breaks large investigations into focused batches, distributes them across parallel agents, and synthesizes their findings into one report. Devin then turns its findings into PRs ready to review.
Teams testing Code Scans ahead of launch are already seeing results:
Code Scans had a significant impact on the things we care most about: software quality, bug fixes, stability, performance, and compliance, including security and privacy. With an estimated 96% PR merge rate across several repos, we estimate we've saved over 700 engineering hours in our short testing timeframe.Digital Computational Pathology, Enterprise Informatics at PhilipsPR merge rate96%Engineering hours saved700+
To get started, type /scan in the Devin webapp, or read the docs.
Start with a goal
You don’t need to know which files to look at before starting a scan. Instead, you define what you’re looking for, and Devin works with you to turn that goal into a concrete codebase investigation.
For example:

Find unused code in our web app. Exclude generated files and test fixtures, and check for indirect references before recommending a removal.

You can also bring your own criteria: a team’s coding standards, an accessibility checklist, or requirements for an upcoming migration. Devin helps establish what to inspect, what to skip, and what should count as a finding.
Once you confirm the scope and settings, Devin runs the investigation and brings back a list of findings ordered by priority. From there, you can inspect the evidence, discuss the results with Devin, and ask it to open PRs for the issues you want to address.
Improve Rust compilation time
We asked Code Scans to speed up compilation in the Dioxus repository. Devin identified opportunities to streamline dependencies and build configuration, including making heavyweight CLI features opt-in rather than compiling them by default. After applying the changes locally, clean debug build time dropped from 58.6 seconds to 21.0 seconds—a 64% reduction across the 22 workspace crates tested.
Scan findingsdioxus · compile-time scanDefault mounted feature forces web-sys/js-sys/wasm-bindgen (and serialize forces serde) onto every non-web rendererThe default feature set enables mounted, which activates the heavyweight optional web-sys dependency (and transitively js-sys + wasm-bindgen) — yet those bindings are…Oversized foundational crate: stable generated element/attribute tables bundled with volatile logic causes full re-expansion and downstream recompilesdioxus-html is a foundational crate that every renderer depends on, and it bundles its enormous, near-static generated element/attribute API (elements.rs, global_attributes.rs)…builder_constructors! element table is the html crate's dominant compile cost (~112 elements, ~112 per-element proc-macro invocations, duplicated hot-reload traversal)The single builder_constructors! invocation is the html crate's dominant compile-time cost. It expands 112 HTML/SVG elements, each into a unit struct, TAG_NAME/NAME_SPACE…cargo-generate compiled unconditionally in dioxus-cli though used only by dx createcargo-generate is a non-optional dependency used only by the dx create/dx init scaffolding path, but it drags in git2/libgit2-sys (a native C library build), liquid templating…dioxus-ssr pulls tokio "full" (default-on) but only uses fs + io-utildioxus-ssr declares tokio = { version = "1.28", features = ["full"], optional = true }, but the crate uses tokio in exactly one module (incremental.rs) and only touches tokio::fs and…Example findings · ordered by priorityHighMedium
SEO Optimization
We ran a scan for SEO issues across devin.ai and cognition.com. It surfaced 44 findings across the two repositories, and we shipped fixes over the following days. Comparing Ahrefs crawls before and after:

Ahrefs health score increased from 87 to 92 on devin.ai.
Slow pages decreased by 73% on devin.ai.
Missing image alt text was eliminated on cognition.com.

Scan findingsdevin.ai + cognition.com · SEO scanCustomer case-study pages emit relative og:image / twitter:image / JSON-LD i…Every customer case-study page (/customers/<slug>) sets its Open Graph image, Twitter image, and Article JSON-LD image to the raw frontmatter.ogimagePath value, which is a root-relative path with no domain and no leading slash. Open Graph / Twitter Card spec and schema.org require absolute URLs, so previews and the Article rich-result image break.devin-websiteRedirect chain /resources/university → /university → external drops a hop on a…vercel.json defines /resources/university -> /university and, separately, /university -> https://learn.devinenterprise.com. Because the first redirect targets another redirect source, requests to /resources/university traverse a two-hop 301 chain instead of going straight to the final destination. Ahrefs confirms /resources/university has 157 live backlinks (22 referring domains).devin-websiteHomepage og:url resolves to non-canonical /index (mismatches canonical https:…The root layout sets openGraph.url: './' on every page. This holds for sub-routes but is false for the homepage: Next resolves ./ for the root route against pathname /index, so the served homepage emits og:url = https://cognition.com/index while its canonical link tag is https://cognition.com.cognition-marketing-websiteTerminal layout omits the JSON-LD structured data every base/desktop page emitsThe _terminalLayout head assembles title/description/canonical/OG/hreflang but emits no JSON-LD, unlike _baseLayout and _desktopLayout which both ship a default SoftwareApplication block. Its consumers /cli (the Devin CLI product page) and /auto-triage are both indexable central product surfaces.devin-websiteEnded event stays indexable with meta description advertising a live webinarThe whats-new-in-devin-06-24-26 event page announces on-page that the event is over ('This event has ended', 'Event ended', 'Registration closed'), yet its metadata contains no robots: {index:false} and its meta/OG descriptions still advertise the webinar as live and upcoming. So an expired page remains indexable while its search snippet promotes a past event as though registration were open.cognition-marketing-websiteExample findings · ordered by priorityHighMedium
Agentic MapReduce
Code Scans is built on top of Agentic MapReduce, the architecture we built for Devin Security Swarm, to make codebase-wide investigations practical. It works in 4 phases:

Plan. Devin studies your repository and defines rules for identifying code relevant to your goal.
Shard. Those rules run across the codebase, and the matching code is divided into focused batches.
Map. Parallel Devin agents investigate each batch, reading surrounding code as needed and reporting their findings.
Reduce. A final agent combines the findings, removes duplicates, and prioritizes the results into one report.

Agentic MapReduce Pipelinedead-code scan example1Plan2Shard3Map4Reduce1. PlanAgenticDevin studies the repository and defines rules for the code relevant to your goal — here, symbols, modules, and dependencies that may no longer be used.repoagentselectorsexports with no importersunreferenced modulesunused dependenciesstale feature flags
This keeps each agent’s context focused and directs the reasoning budget toward relevant code rather than repeated searching. This architecture also ensures completeness: every selected batch must be processed. Code Scans brings that same approach beyond security to the engineering goals you define.
What would you scan for?
Code Scans can investigate a wide range of engineering questions, using your codebase’s conventions and the criteria you provide. Here are some examples:
ScanGoalPerformanceFind slow paths, redundant computation, and missed caching opportunities that could make your application faster.Database queriesLook for N+1 queries, unnecessary round trips, unbounded reads, and other inefficient or unreliable data-access patterns.Test coverageIdentify important flows, edge cases, and failure paths that aren’t covered by tests.Dead codeFind unused functions, modules, dependencies, and obsolete feature flags, with evidence for what can safely be removed.Code qualityLook for duplicated logic, unnecessary complexity, better abstraction opportunities, and patterns that violate your team’s coding standards.CleanupIdentify redundant abstractions, excessive boilerplate, and code that can be simplified without changing behavior.TelemetryFind gaps in logging, metrics, and tracing that make failures difficult to diagnose or important behavior difficult to measure.AccessibilityLook for missing labels, broken keyboard interactions, and other gaps against the WCAG criteria you specify.ComplianceInvestigate sensitive-data handling, audit trails, and retention logic against your organization’s regulatory requirements and policies.Migration planningTrace existing dependencies, end-to-end flows, and business logic to produce a plan for an upcoming migration.SEO OptimizationFind code-level issues affecting search visibility, including missing or duplicated metadata, incorrect canonical URLs, indexing directives, and gaps in sitemaps or structured data.Your ownDefine a pattern you want Devin to look for throughout the codebase.
The most useful scan might come from a question your team has been putting off because answering it meant looking everywhere.
Type /scan in your Devin session, specify what you want to investigate, build the scope together, and start optimizing your codebase today.
Try Code Scans at devin.ai and learn more in the Code Scans docs.Table of contentsStart with a goalImprove Rust compilation timeSEO OptimizationAgentic MapReduceWhat would you scan for?Privacy PolicyTerms of ServiceYour Privacy ChoicesLinkedInX (Twitter)

Code Scans is introduced as a novel method designed to translate broad engineering objectives into tangible improvements across a codebase. The system assists users in investigating code, evaluating the resulting findings, and automatically generating pull requests to implement necessary changes. This capability addresses the common challenge where engineering tasks, such as improving performance or reducing maintenance overhead, are stalled because the initial step—investigating the codebase to pinpoint starting points—is substantial. Code Scans automates this investigative phase.

The core of Code Scans is powered by Agentic MapReduce, an architecture developed for Devin Security Swarm, which is designed to make large-scale codebase investigations practical. This architecture operates in four sequential phases: Plan, Shard, Map, and Reduce. The Plan phase involves Devin studying the repository to establish rules for identifying code relevant to the user's goal. The Shard phase divides the relevant code into focused batches based on these rules. The Map phase deploys parallel Devin agents to investigate each batch, contextually reading surrounding code as needed and compiling their findings. Finally, the Reduce phase involves a concluding agent that synthesizes the findings, eliminates redundancies, prioritizes the results, and compiles them into a single, coherent report. This methodology ensures that agent reasoning is focused, directs resources efficiently, and guarantees completeness by ensuring every selected batch is processed.

Users initiate a scan by defining a specific goal rather than needing prior knowledge of which files to examine. Devin then collaborates with the user to transform this goal into a concrete codebase investigation. Users can introduce custom criteria, such as team coding standards, accessibility checklists, or migration requirements, allowing Devin to precisely define the scope of inspection, which parts to skip, and what constitutes a valid finding. Following this scoping, Devin executes the investigation, returns a prioritized list of findings, and allows the user to inspect the evidence, discuss the results, and instruct Devin to initiate pull requests for addressing the identified issues.

The utility of Code Scans is demonstrated through various applications. For example, one application involved improving Rust compilation time in the Dioxus repository, where Code Scans identified opportunities to streamline dependency management and build configuration, resulting in a significant reduction in debug build time. In the context of SEO optimization, scans across repositories like devin.ai and cognition.com uncovered issues such as incorrect Open Graph image configurations and suboptimal redirect chains, leading to quantifiable improvements in search engine visibility, including increased Ahrefs health scores and reductions in slow page counts. These examples illustrate the system's ability to deliver measurable, high-impact results.

Code Scans can be applied to a wide spectrum of engineering questions, encompassing areas such as performance analysis, identifying inefficient database query patterns, assessing test coverage for critical flows, locating dead code, ensuring code quality by detecting duplicated logic or complexity, identifying opportunities for cleanup, monitoring telemetry gaps, enforcing accessibility standards, conducting compliance checks against regulatory policies, planning migrations, and diagnosing code-level SEO issues. By allowing users to define a custom patterning Devin should look for throughout the codebase, the tool empowers teams to define the most critical, time-consuming investigations they have been postponing. The system effectively transforms broad, open-ended questions into actionable, self-correcting changes.