Skip to content
Helix
How it worksCrewScreensPricing
Log inStart free
Menu
How it worksCrewScreensPricingDocsDevelopers

Documentation

How Helix works

The loop end to end, then the parts you configure. Each section says what actually happens.

The loop, in six steps

Every run follows the same shape. Nothing here is a mode you turn on.

01

You state an outcome

Plain words. That is the whole input — no schema, no prompt syntax, no tool selection.

Add a rate limit to the public API and prove it works.
02

Helix drafts a plan

The goal is broken into steps, and each step is routed to the specialist whose tools fit it. You can read the plan before the work starts.

03

A sandbox is provisioned

The run gets its own machine with its own filesystem and network namespace. Commands and files happen there, not on your machine.

04

The crew works

Specialists execute steps and hand work between each other. Every handoff is written into the transcript in that specialist's own voice.

05

It verifies

A change with no check is reported as unverified, not as done. The summary is built from tool outcomes, not from the model's account of them.

06

You keep the record

The transcript, the artifacts and the workspace all persist. The machine is parked between messages, so tomorrow's follow-up finds its files.

The crew

Five specialists ship with every workspace. Each has its own tools, so work is routed rather than piled onto one generalist.

Marcus Chen

Senior Software Engineer. Edits, tests, builds, refactors.

Priya Nair

Cloud Engineer. Services, deploys, logs, capacity.

Diego Ramos

Data Analyst. Queries, CSV and spreadsheet work, charts.

Sofia Lindqvist

Research Analyst. Web search, reading, citations.

Amara Okafor

Virtual Assistant. Writing, summaries, scheduling.

Your own

Describe a specialist in a sentence and it joins the roster.

Every run gets its own machine

Isolation is the reason a run can be trusted with a real shell.

A real machine, not a simulation

The sandbox is a real Linux environment. A run installs a dependency, builds the project and runs the tests exactly as you would — because it is doing exactly that.

It cannot read another workspace's files. Loopback inside it is the sandbox, not your host, which is what makes a server started there safe to expose through a signed preview URL.

Between messages, the machine is parked — not destroyed

That is why a thread you return to tomorrow still has its files. Parking releases the compute but keeps the disk, so the workspace survives without costing a running machine.

A run's sandbox, reported back to the transcript
$ pwd /workspace $ node --version v22.14.0 $ npm test 42 passing (1.2s) $ echo $DISPLAY :1        # a real X server, so a GUI tool works too

It checks before it says done

The claim being made is not “the model said so”. It is that a check ran.

verified

A check ran after the change and passed. The evidence names which check.

unverified

The change landed and nothing proved it. Reported as exactly that, with the gap written down.

awaiting_acceptance

Finished, and a person should decide. The reason completion was withheld is on the row.

A summary is built from outcomes, not from prose

Which files changed, which checks ran and what could not be established all come from the tool results themselves. A run that says it is done without running anything is recorded as unverified, and the record is what you read.

What a run can call

Seventy tools, grouped. A run is given the ones its goal needs rather than all of them, so the manifest stays small and the model is not invited to reach for something irrelevant.

Files

read_file, write_file, edit_file, apply_patch — every write read back to confirm it landed.

Shell

run_command, start_service, sandbox_jobs — with the process's own log tail on a crash.

Code intelligence

find_symbol, find_references, call_graph, repo_map.

Git and GitHub

git_show, open_pull_request, github_actions, check_merge_conflicts.

Browser and desktop

browser_use, computer_screenshot, computer_click, computer_type.

Data

create_document, export_artifact, read_document — PDF, XLSX and DOCX with no extra install.

Research

search_codebase, search_platform_docs, npm_registry_lookup.

Delivery

publish_artifact, get_preview_url, request_env_values.

The controls you keep

Autonomy is a level, not a switch. It says how much your crew may do without asking.

approval_required

Nothing runs without asking. Every action is proposed first.

supervised

Reads and reversible work run. Writes and external effects ask first.

autonomous

Everything runs except actions above your risk tolerance.

Two guards sit above the level and cannot be raised by it

A destructive action always asks, whatever your setting. And once a run's context contains untrusted text — a fetched page, a web result — any external send escalates to approval, because fetched content can carry instructions that look like yours.

Stopping is always available and never destructive

Stop a run at any time. The transcript and the workspace are kept; nothing is thrown away, and the next message continues from where it stopped.

Questions people ask

Do I need to know how to code?

No. The input is a sentence describing an outcome. The plan, the tools and the checks are the platform's job.

What happens if a run gets something wrong?

You see it in the transcript while it happens, and you can stop it. Every finished task carries its evidence, so you can tell what was actually verified from what was merely claimed.

Can it touch my production systems?

Only through credentials you connect, and only within the autonomy level you set. A destructive action asks regardless of the level.

Is my code used for training?

No. Your workspace, your transcripts and your artifacts are yours; they are not training data.

What happens when a usage window runs out?

The run pauses and the message names the reset time. Nothing is lost — send another message once the window rolls.

See it work on your own problem

Describe an outcome and watch the plan, the work and the proof arrive in one transcript.

Start free

Product

How it worksCrewIntegrationsScreens

Plans

PricingCompare plansUse cases

Company

AboutCareersChangelogContact

Developers

DevelopersDocsSecuritySupportStatus

Legal

PrivacyTermshello@launchverse.app

Elsewhere

Helix

Your workspace for agents.

© 2026 Helix by LaunchVersehello@launchverse.app