SSPART home

Introducing

Hand it the work. Get it back delivered.

100

tasks delivered. Not 100 conversations.

No new AI subscription.

Atlas runs on the plan you already pay for, within its limits.

Available now.

Free to start. $19 per user a month for teams.

Give the requirement. Get it delivered.

We use Atlas to deliver our own work. Write what you need, and it plans, builds, checks and delivers, using the AI subscription you already pay for.

atlas / dashboard
Atlas dashboard: what needs you, live runs, your agents at work and this month's AI spend
  • 24specialist agents
  • 12stages from requirement to approval
  • 6workflow templates, and a visual builder
  • 17-78minutes of run time per delivery, in our internal benchmark on sample repositories
  • $11.75average AI cost per delivered change in that benchmark
  • $0to start, then $19 per user a month for teams

Twelve stages, one map

This is the real Atlas delivery workflow. Every step has a specialist, and work only moves on once it passes. Select a step to see who does it.

The usual way, and the Atlas way

Same request, two routes. One waits at every hand-off. The other splits the work, builds it in parallel, checks everything and delivers.

RequestAdd GST invoices to the merchant app

The usual way

Ready

2 hand-offs, 1 queue, 1 rework loop

BriefHand-offQueueBuildManual testReworkHand-offRelease
Released

With Atlas

Ready

No hand-offs, queues or rework

PlanDesignBuildTestDocsVerifyReview
Delivered
Request inTime
Atlas delivered
  • Work
  • Waiting
  • Rework
  • Atlas, in parallel where it can

Illustrative timeline, not to scale.

Team

A lean senior team steering specialised agents.

Instead of a large team, with every role staffed for the whole project.

Hand-offs

Each step starts the moment the previous one is ready, and independent work runs in parallel.

Instead of work waiting in a queue between every role.

Quality

Every change is checked automatically and reviewed before it is delivered. Anything that fails is fixed and checked again, and anything unclear goes to a person.

Instead of testing near the end, mostly by hand.

AI spend

AI effort matched to each task, with nothing spent where it is not needed.

Instead of the same expensive AI for every task, or no AI at all.

Visibility

Cost, speed and quality of every delivery, tracked live.

Instead of weekly status reports.

Knowledge

Every decision and change is recorded with the work, so nothing lives only in someone's head.

Instead of know-how that leaves when people do.

A full delivery team, on call

Atlas comes with 24 specialists and 6 workflow templates. Pick a kind of work to see who steps in. In delivery workflows, each maker is paired with a reviewer, so nothing passes on its own say-so.

Scope and design

  • PO WriterSplits the work
  • PO ReviewerChecks the scope
  • ArchitectWrites the spec
  • Architect ReviewerChecks the spec

Build

  • CoderBuilds each piece
  • Code ReviewerReviews the code

Test

  • QA WriterPlans the tests
  • QA ReviewerChecks the plan
  • Automation EngineerAutomates the tests
  • Automation ReviewerChecks the tests

Document

  • Doc WriterDocuments the change
  • Doc ReviewerChecks every claim

Fix what fails

  • Hygiene FixerFixes lint failures
  • Coverage FixerCloses test gaps
  • Fix ReviewerChecks the real cause was fixed
  • Performance FixerGets pages back under budget
  • Visual ReviewerReviews what the screenshots show

Final review

  • Release ReviewerReads it as one change

Readiness and research

  • AI Readiness SpecialistPrepares a repository for agents
  • Jira ImporterBrings in your Jira work
  • Knowledge Base CuratorKeeps project reference current
  • AI News ScoutSummarises AI tooling news
  • Market ResearchWatches competitors
  • Regulations ScoutScans regulator news

Put the whole list in. Get finished work back.

Each item runs on the AI you already pay for, and comes back finished for your approval.

  • No new AI subscription. Use Claude Code, GitHub Copilot, or models through Ollama, under each person's own sign-in.
  • Your code goes only to the AI provider you choose. Atlas work counts against that plan's limits.
  • One task at a time per repository, so changes don't collide. Different repositories run side by side.
atlas / tasksIllustrative preview
  1. billingAdd GST to invoicesQueued
  2. storefrontAdd an export buttonQueued
  3. billingShow tax on receiptsQueued
  4. accountsFix the login timeoutQueued
  5. storefrontAdd a size guideQueued
  6. accountsAdd a password reset pageQueued
  7. storefrontFix the cart on phonesQueued
  8. billingAdd refund reportsQueued

92 of 100 ready for your approval

Illustration. Real speed depends on your code, your checks and your AI plan.

See it working

Real Atlas screens.

atlas / workflows
Atlas workflows: delivery, build, docs and test pipelines, each with its trigger and last run
atlas / agents / marketplace
Atlas agent marketplace: specialist agents such as PO Writer, Architect and Coder, ready to install
atlas / agents
Atlas agents: 22 software agents such as Architect, Coder and Code Reviewer, each with its CLI, model and effort
atlas / agents / coder
Atlas Coder agent: what it does, its role and the quality checklist it reports on

Ready for the way companies work

Atlas runs on your own server, with the controls a company expects.

  • On your own systemsOne server in your organisation, using Docker and Postgres. Your code doesn't come to us.
  • Single sign-onThrough OpenID Connect, or email and password.
  • RolesAdmin or member across the organisation. Admin, member or viewer on each project.
  • Audit logSign-ins, secret views, role changes, and runs started or stopped.
  • Delivery and spendAnalytics for delivery and workflows, with spend by reporting line.
  • Connects to your toolsGitHub.com, Jira Cloud, and alerts to Microsoft Teams and Telegram.

How Atlas compares

Most AI work tools bundle the AI into the price. Atlas doesn't, so you pay for the delivery system and keep the subscription you have.

Types of AI work tool, by where the AI comes from and what you get
A person directs the workFinished work comes back
Your own AI subscription Parallel agent toolsFree to about $60 per user a month. Several agents at once, and you still direct each one. AtlasFree to start, then $19 per user a month. Planned, built, checked and delivered, on your own systems.
AI bundled into the price AI coding assistantsAbout $20 to $40 per user a month. Help for a developer, one conversation at a time. Autonomous coding agentsAbout $40 per seat, plus a team fee and usage. Finished changes, on the vendor's cloud.
Type of toolTypical costWhere the AI comes fromWhat you get
AI coding assistantsAbout $20 to $40 per user a monthBundled, and heavy use can cost extraHelp for a developer, one conversation at a time
Autonomous coding agentsAbout $40 per seat, plus a team fee and usageBundled and meteredFinished changes, on the vendor's cloud
Parallel agent toolsFree to about $60 per user a monthYour own subscriptionSeveral agents at once, and you still direct each one
Enterprise agent buildersAbout $500 to $6,000 or more a month, or usage creditsBundledBusiness process automation, not software delivery
AtlasFree to start, then $19 per user a monthYour own subscriptionPlanned, built, checked and delivered, on your own systems

Typical public list prices by type of tool, October 2026. Prices change, and each vendor's own page has the current figure.

Pricing

Free

$0

For one person trying Atlas on their own work.

  • Open source under AGPL-3.0
  • One agent per task
  • 7 ready-made agents
  • Runs on your machine
Get Atlas free

Team

$19per user a month

For teams. $15 per user a month when billed annually.

  • One shared server for your organisation
  • Multi-agent delivery workflows
  • Single sign-on, roles and an audit log
  • Delivery and spend analytics
  • Support from SSPART
Talk to us

Enterprise and cloud

Let's talk

For organisations with their own security, hosting or integration needs.

  • We set Atlas up on your servers or in your cloud
  • Integrations scoped and built with you
  • Support terms agreed in writing
Contact us

Prices are in US dollars and exclude taxes. Your AI subscription is separate: each person uses their own Claude or GitHub Copilot plan, and Atlas work counts against that plan's limits.

Questions

Do we need to buy AI from you?

No. Atlas runs Claude Code or GitHub Copilot under each person's own sign-in, or models through Ollama, and you choose which one each agent uses. You keep paying your AI provider directly, and Atlas work counts against that plan's limits.

How does Atlas make delivery faster and cheaper?

Atlas breaks each request into small pieces of work, runs specialised agents on them in parallel and matches the AI effort to each task, so nothing is overspent. Every result is checked and reviewed before an engineer signs off the delivery, and the cost of each delivery is tracked so you see what the spend achieved.

Does Atlas need access to our cloud?

No. Atlas delivers into your repositories, where your team reviews every change. When we build for you, Atlas runs on our systems and the result is deployed to your own AWS or Azure account. If you license Atlas, it runs on your own systems.

Who approves the work?

Your team does. Atlas raises each finished change as a pull request and a person approves it. Atlas doesn't merge changes by itself.

Can 100 tasks run at the same moment?

Not in one repository. Atlas works on one task at a time per repository and queues the rest, so changes don't collide. Tasks in different repositories can run side by side, up to the limit you set for each workflow.

What do we install?

Atlas runs on one server in your organisation, using Docker and Postgres. Each person also runs a small Atlas runner on their own computer, where their agents work. A task needs its owner's runner to be online. You also add your own lint, build and test commands to the workflow, so Atlas can run them.

Does our code go to SSPART?

No. Atlas runs on your systems, and your code goes only to the AI provider you choose. There's no third-party analytics in the app. Online licences send us a daily usage count, such as active users and version, and offline licences are available.

What does Atlas connect to today?

GitHub.com, Jira Cloud, and alerts to Microsoft Teams and Telegram. If you use something else, tell us and we'll scope it with you.

Is the Free plan really free?

Yes. It's open source under the AGPL-3.0 licence, and you only need your own AI subscription, or local models through Ollama, to run it.

Do you host Atlas for us?

Atlas isn't a shared hosted service. We can set it up in your own cloud account as an Enterprise project.

Have a list of work waiting?

Talk to us