--- title: Arcus url: https://tryarcus.ai/ --- ## The verification harness for AI-native software teams Catch drift while the coding session is on. Arcus checks the code against what the ticket asked for while developers and agents are still coding, so drift gets fixed before you move on to the next ticket. arcus · feat/login Find what your coding agent didn’t catch. Independent agents check every PR against the sprint — gaps flagged before they ship. SP-44 #### Sprint 43 · Payments v2 **148** Gaps IdentifiedIn Progress **75%** Readiness**68%** Coverage**29** Gaps See the blast radius before you merge. Correlates the diff against coverage, tickets, and history to show what a change could actually break — not just which tests ran. By: StoryModules impacted Gap type: **All** 300 FiltersSimpleDetailedSearch tests Account Summary Cards 73%4 open gaps|15 testsAccept all 4 Booking Management 0%15 open gaps|15 testsAccept all 15 Dashboard 50%1 open gap|2 testsAccept all 1 Dashboard Account Summary Cards 30%7 open gaps|11 testsAccept all 7 Every merge traced back to intent. PR, ticket, design, and test history linked in one chain — so when something fails, you know exactly what it was supposed to do. Jira Test Management by Testsigma_/_**SCRUM-7** #### Success Criteria - Complete family quote process in under 15 minutes - Quote completion rate > 65% for family plans - Clear family pricing differentiation displayed - Professional proposal with all family members listed **Linked Test Cases**Link JT-8Attempt to add family member with missing required fields66.67%Passed JT-9Remove a family member from the list66.67%Passed JT-12Quote completion rate above 65% - Multiple users0%Failed JT-14Monitor Quote Completion Rate During Peak Hours66.67%Passed ## Follow a task from ticket to release. Plan ### The ticket becomes the baseline intent everything is verified against. Jira Test Management by Testsigma_/_**SCRUM-7** #### Success Criteria - Complete family quote process in under 15 minutes - Quote completion rate > 65% for family plans - Clear family pricing differentiation displayed - Professional proposal with all family members listed **Linked Test Cases**Link JT-8Attempt to add family member with missing required fields66.67%Passed JT-9Remove a family member from the list66.67%Passed JT-12Quote completion rate above 65% - Multiple users0%Failed JT-14Monitor Quote Completion Rate During Peak Hours66.67%Passed Arcus reads the ticket, its acceptance criteria and the designs, so every later check knows what the task was supposed to do. Code ### Drift gets caught in the developer session, right inside the preferred IDE. arcus · feat/login While the developer and their agent are still working, Arcus checks the code against intent, shows the blast radius and writes the tests the behaviour calls for. Test ### The paths nobody tested get found. EX-12 #### Exploratory run · Checkout Account summary**73%** Booking**0%** Dashboard**92%** **37** Paths explored**12** Untested**9** Scripts The exploratory agent crawls the live app, runs against what no test covers, and turns good runs into scripts that run the same every time. QA starts from verified, not from zero. Release ### Ship it, or know exactly why not. SP-44 #### Sprint 43 · Payments v2 **148** Gaps IdentifiedIn Progress **75%** Readiness**68%** Coverage**29** Gaps The release score is built from everything verified upstream, so the call on whether to ship comes with its reasons, not a guess made at the end. ## How Arcus sits across the lifecycle Plan sets the scope. Code, test and release are where the agents act. The knowledge graph runs underneath all of it, and feeds forward into the release gate. Plan Plan**Tickets, acceptance criteria, specs** — set the baseline intent that everything coded and tested downstream is verified against. Code Code ### Where the diff happens - Unit tests - Blast radius - Developer-authored functional tests Agent-native ![Claude Code](/images/arcus/resoning-section/icons/claude.webp)Claude Code![Codex](/images/arcus/icons/codex.png)Codex![Cursor](/images/arcus/icons/cursor.png)Cursor Test Test ### Where coverage gets proven - Agentic test runs - Explorer agent - Coverage gap detection - Traceability Release Release ### Where the call gets made - Release confidence - Release readiness - Release gate Integrations: where Arcus reads context and shows what it finds [Jira](/integrations)[Linear](/integrations)[Figma](/integrations)[Claude Code](/integrations)[Codex](/integrations)[GitHub Copilot](/integrations)[Cursor](/integrations)[GitHub](/integrations)[GitLab](/integrations)[Jenkins](/integrations)[CircleCI](/integrations)[Azure DevOps](/integrations)[Slack](/integrations)[Microsoft Teams](/integrations)[All integrations →](/integrations) Compliance SOC 2 Type IIHIPAAGDPRISO 27001ISO/IEC 42001 **Knowledge graph**0 nodes · 0 edges built from every agent run across plan, code and test — connective tissue, not a fourth stage Hover a hub Feeds forward into **release confidence** — the gate verdict is only possible because of what the graph accumulated upstream. ## Works with the agents you use Arcus plugs natively into whichever agent wrote the code, reading exactly what it shipped, and checks it independently of the agent that wrote it. ![](/images/arcus/resoning-section/icons/claude.webp)![](/images/arcus/icons/codex.png)![](/images/arcus/icons/copilot.png)![](/images/arcus/icons/cursor.png)![](/images/arcus/resoning-section/icons/claude.webp)![](/images/arcus/icons/codex.png)![](/images/arcus/icons/copilot.png)![](/images/arcus/icons/cursor.png)![](/images/arcus/resoning-section/icons/claude.webp)![](/images/arcus/icons/codex.png)![](/images/arcus/icons/copilot.png)![](/images/arcus/icons/cursor.png)![](/images/arcus/resoning-section/icons/claude.webp)![](/images/arcus/icons/codex.png)![](/images/arcus/icons/copilot.png)![](/images/arcus/icons/cursor.png) a ## Works with your SDLC stack natively No separate portal to check. Gaps, blast radius, and traceability show up in whichever tool the team already runs, via native 2-way sync, not a dashboard you have to remember to open. ![](/images/arcus/resoning-section/icons/github.png)**GitHub**PR checks ![](/images/arcus/resoning-section/icons/jira.webp)**Jira**Tickets ![](/images/arcus/icons/linear.svg)**Linear**Issues ![](/images/arcus/resoning-section/icons/claude.webp)**Claude Code**In-session checks ![](/images/arcus/resoning-section/icons/jenkins.webp)**Jenkins**Build gates ![](/images/arcus/icons/slack.png)**Slack**Alerts and threads ## Quality starts at the source. The Arcus CLI is a true harness, sitting deeply embedded in the developer’s workflow — the same terminal, the same hooks, the same CI, not a dashboard bolted on after the fact. $ npm install -g arcus_⧉_**✓**[See the CLI →](/signup) ## Building your own? Plenty of teams start with Claude and Playwright, and it works. This is what you end up owning once it does. In-house verification harness built using Claude Arcus Who checks the work Built in-houseThe same agents that wrote the code ArcusAn independent system, separate from the agents writing code When behaviour gets checked Built in-houseAfter the code is written, in CI or a review pass ArcusWhile the coding session is still open, against expected user behaviour Finding missing coverage Built in-houseCoverage stops at the tests someone thought to write ArcusAn exploratory agent crawls the live app, finds what’s missing and widens the regression suite Test execution across apps Built in-housePlaywright for web, Appium for mobile, a third-party vendor for Salesforce ArcusWeb, mobile and Salesforce in one platform Test execution infrastructure Built in-houseYour CI runners and local browsers, plus a third-party browser lab, a third-party device lab, or an in-house device lab your engineers have to build and run ArcusA real device and browser cloud lab, built in Keeping tests stable Built in-housePlaywright scripts your team updates every time the UI moves ArcusDeterministic scripts in plain English steps, with self-healing Test management Built in-houseA sheet, or a paid third-party tool ArcusAgent-native test management, built in Fitting into how you work Built in-houseCustom wiring for each coding agent, tracker and CI pipeline ArcusNative integrations with coding agents, project tools and CI/CD, plus a CLI agents can call directly Where issues show up Built in-houseWherever your scripts post them ArcusFiled in Jira and Linear, surfaced in the CLI, Slack and GitHub Ready to ship? Built in-houseA judgement call at the end ArcusRelease confidence built from everything verified upstream Deployment Built in-houseSelf-hosted, and hard to scale across regions ArcusPublic cloud, private cloud or self-hosted Compliance Built in-houseYours to document and audit ArcusSOC 2 Type II, ISO 27001, HIPAA, GDPR, ISO/IEC 42001 Upkeep Built in-houseEngineers pulled off product to maintain it ArcusMaintained by us Keep your agents writing code. Let Arcus check it. [Book a demo](/request-demo)