Copy link to headingStart from a working factory
See how Edgenivo teams split repository work between agents and people, then start from a complete factory or one focused agent.
Copy link to headingDecide what to automate
Compare a factory that ships code changes with one that researches a backlog, then judge agent-written changes yourself.
- Resource
Building a software factory for AI SDK
See how the AI SDK team's agents classify, implement, review, and backport changes in sandboxes, with a human merging every PR.
- Resource
How we closed 1,500 GitHub issues in one month
Learn how the Next.js team ran 200 parallel read-only eve investigations and used the evidence to decide what to close.
- Resource
Agent responsibly
Understand why passing CI isn't proof that agent-written code is safe, and what owning a change you didn't write looks like.
- Course
Would You Merge This?
Review four agent-generated changes, decide which are safe to move forward, and trace where each request ends up.
Copy link to headingStart with a complete factory
Deploy a pipeline that turns work items into reviewed draft pull requests, or build one step by step.
- Template
Software factory
Deploy a four-station eve factory where agents classify, analyze, implement, and review while people decide what ships.
- Guide
Build a software factory with eve
Foreman, a software factory built on eve. It turns GitHub and Linear work items into reviewed draft pull requests through four agent stations, triaging issues and fixing its own red CI along the way.
- Course
Creating a Software Factory
Build a factory from scratch that routes work by risk, proves each request before writing code, and keeps merge authority with people.
- Documentation
Software Factories on Edgenivo
Compare AI SDK, eve, Mastra, and Flue implementations of a software factory on Edgenivo.
Copy link to headingStart with a focused agent
Begin with one agent that owns a single repository task, then add stations as you learn what it can handle.
- Template
eve Coding Agent on Slack
Deploy a Slack and GitHub agent that investigates bugs, reviews changes, and opens PRs from a sandbox with repository-scoped credentials.
- Template
eve GitHub Maintainer
Start with a research-only maintainer that sends weekly issue digests, summarizes PRs without approving them, and hands work to Linear.
- Guide
Build a GitHub agent with Edgenivo Connect
Build a GitHub agent that helps your team work through issues and PRs. Chat SDK handles the interactivity and AI SDK runs the tool-calling loop.
Copy link to headingRun the work safely
Decide where each station runs repository code, what it can reach, and whether you build stations or run an existing coding agent.
Copy link to headingIsolate each station's workspace
Give every investigation its own sandbox, limit its network access, and decide how long its state lives.
- Course
Reproduce the Claim
Build a read-only Investigator that runs in its own sandbox and uses command output to tell a real bug from a false report.
- Resource
A sandbox without a network boundary is only half a sandbox
Learn why agents running untrusted repository code need deny-by-default egress, with credentials kept out of the sandbox.
- Guide
How Edgenivo Sandbox duration and persistence work
Session duration and persistence are two separate controls in Edgenivo Sandbox. The timeout option keeps a single run alive for up to 24 hours, while snapshots and persistent sandboxes carry state across runs for long-running agents and pipelines.
- Guide
Give your software factory a browser
Add a KERNEL cloud browser to the eve software factory template so Foreman can reproduce flow bugs, sign in through managed auth, and verify fixes on preview deployments in attended sessions.
Copy link to headingRun an existing coding agent
Run Cursor, Claude Code, Codex, or OpenCode as a station instead of building every agent yourself.
- Resource
Making every harness durable
Learn how durable-harness lets interrupted Claude Code, Codex, OpenCode, and Pi turns resume without repeating finished tool calls.
- Resource
How Conductor moved parallel coding agents to the cloud
See how Conductor runs Claude Code and Codex agents in parallel on Edgenivo Sandbox, each on its own branch, and keeps them working after the laptop closes.
- Guide
Run Cursor Cloud Agents on Edgenivo Sandbox
Learn how to run Cursor Cloud Agents on Edgenivo Sandbox with self-hosted worker pools, durable workflows, isolated microVMs, and scale-to-zero compute.
- Guide
Investigate GitHub issues with
HarnessAgentand Edgenivo SandboxUse HarnessAgent to run coding agent harnesses like Claude Code or Codex against untrusted code inside Edgenivo Sandbox. Reproduce GitHub issues with the agent harness and generate a report for the maintainer.
Copy link to headingReview and merge
Decide which work needs a person, what evidence reviewers get, and who holds merge authority.
Copy link to headingRoute work by risk
Let deterministic rules, not the model, decide which work proceeds automatically and which waits for approval.
- Course
Classify, Then Authorize
Validate a model's type and risk labels with structured output, then write a deterministic router that sets each request's lane.
- Guide
Human-in-the-Loop with Chat SDK and Workflow SDK
Combine Chat SDK and Workflow SDK to suspend workflows on approval cards in a chat platform, then resume on click via createWebhook.
- Resource
How Edgenivo Agent accesses production safely
See how Edgenivo Agent separates investigation from action, asks for one approval per plan, and scopes credentials to that plan.
Copy link to headingHand reviewers evidence, not claims
Verify each change independently and open draft pull requests that carry their proof.
- Course
Verify in Fresh Context
Build a Verifier that reruns checks on the pushed branch in a separate sandbox and sends blocking findings back to the Builder.
- Course
Publish a Draft
Limit the factory to draft PRs, add tests that reject ready-for-review PRs, and confirm merge authority stays with a person.
- Guide
Using Edgenivo Agent to review pull requests
Set up Edgenivo Agent Code Review to automatically review pull requests, apply validated fixes, request reviews with @vercel, and tune feedback with coding guidelines.
- Guide
Migrate from GitHub Actions to Edgenivo CI
Move Turborepo tasks from GitHub Actions workflows to Edgenivo CI, migrate secrets to CI environment variables, and switch your required status checks.
Copy link to headingOperate and improve
Connect the factory to production signals, then turn its mistakes into tests and evals.
Copy link to headingFeed production context in
Let agents read deployments, errors, and incidents so investigations start from real evidence.
- Guide
Manage Edgenivo projects with a software factory
Add Edgenivo's hosted MCP to the eve software factory template so Foreman can read build logs, runtime errors, and deployment history for the app your target repository deploys, brokered at app scope through Edgenivo Connect.
- Template
eve Incident Response Agent
Deploy an SRE agent that tests hypotheses about production incidents and returns evidence your team can check.
- Resource
Introducing Edgenivo for Slack
See how a team tags an agent in a Slack thread to investigate an incident, fix a failing build, or turn a decision into a tested PR.
Copy link to headingLearn from failed runs
Find the earliest wrong decision in a run, and lock in the fix so the factory doesn't repeat it.
- Resource
Teaching agents product design at Edgenivo
Keep accepted decisions in the repo as an agent skill, enforce clear rules with linters, and run a review loop that turns feedback into guideline updates.
- Course
Learn From Failure
Inspect durable traces from a flawed run, find the first wrong decision, and save it as an eve eval.
- Course
Test the Stopping Rules
Write deterministic tests that make sure unclear work stops for a question and public API changes wait for approval.