AI runtime infrastructure for X-system work

Your AI can think. UniversalBench does the work: one runtime that carries X-system work, the tasks that cross several apps, accounts and sites, from request to finished result. You ask once.

Start free See it work 1,000 free actions a month. No card. What’s X-system work?
Works across your stack
EmailFiles and docsSpreadsheetsAccountingHelp deskCodeDatabasesany websiteAll integrations →
See how UniversalBench compares with Composio, Zapier and others →
WORKINGFINISHED
The request

The result
Supplier chased and delivery confirmed
Invoice adjusted in accounting
Customer emailed the new date
Everything logged for next time
6 systems · 1 orchestrator · 0 handovers Illustrative

Code that runs

A sandbox where the AI calculates, cleans data and builds, instead of only describing.

A browser of its own

Reaches the systems that have no connection option, like supplier portals and older tools.

Your apps, connected once

Sign in with OAuth. No passwords passed around and no integration code to write.

Memory that carries over

Context follows the work from one step, and one session, to the next.

Up to 96.5%fewer tokens on data tasks
1 URLconnects any AI to your stack
1,000free actions a month
Driven by

Behind UniversalBench is Intralace™, our runtime infrastructure. Think of an intranet, an internal system, laced together: it takes the tangle of systems an AI has to work across, handles the complexity inside one controlled place, and hands back one clean result.

How the runtime works

What’s X-system work?

Real work doesn’t live in one app.

A single task usually crosses several systems, each with its own login, its own rules and its own gaps. That’s X-system work, and it’s where most AI tools stop.

One task, six systems

“A customer emails to say their order is late. Chase the supplier, fix the invoice, tell the customer and log it.”

  1. 01Read the emailEmail
  2. 02Look up the customer and their orderAccounting
  3. 03Check the supplier’s site for the deliveryA website with no connection option
  4. 04Correct the invoiceAccounting
  5. 05Reply to the customerEmail
  6. 06Log what happenedA notes app or a spreadsheet

Where it goes wrong

Here’s where a task usually falls apart.

Six systems means six places for the work to stall. Most AI tools stop at the first one and hand the job back to you. This is what the runtime does at each.

01

Every app wants its own login.

So you paste passwords into a chat, or you end up doing that step yourself.

Sign in to each app once. Your passwords stay locked in an encrypted vault, and the AI never sees them.

02

Some systems have no way in.

A supplier portal, an older tool, a website with a login and nothing else.

A built-in browser opens the website, signs in like a person would, and reads what it needs.

03

The steps don’t stay in order.

Real work changes halfway through. The supplier says Friday, not Tuesday.

Each step is checked as it finishes. When the answer changes, the plan changes with it, and the job keeps going.

04

Context gets lost between steps.

By step five you’re explaining the order all over again.

The details travel with the job, from the first step to the last and into next time, so you never repeat yourself.

Inside the runtime

Your AI decides. The runtime does the in‑between.

Signing in, running the code, opening the website, remembering what happened, checking the result. That is the work between a request and a finished job, and it is what UniversalBench carries, so your AI only gets the answer.

you askYour AIClaude, ChatGPT, Gemini, Cursor or any MCP client
the runtimeUniversalBenchDriven by Intralace™. Plans, runs, checks and remembers.
it acts onYour systemsApps, accounts, websites and data you already use
Watch one real task, start to finish“A customer’s order is late. Chase it and sort it out.”
Step 1 of 8Reads your request and plans the steps.
routerRouterReads the request and sends each step to the right part.
connectConnectYour apps, signed in once through their own sign‑in.
workersWorkersIndependent parts of a task run at the same time.
securitySecurityEvery action is checked before it runs, not after.
memoryMemoryContext follows the work from step to step and session to session.
databaseDatabaseReads, writes and searches your data where it lives.
sandboxSandboxCode actually runs, so numbers are calculated, not described.
browserBrowserReaches websites and portals with no other way in.

Worked out, not guessed

Let your AI think. Let the runtime do the maths.

When a model reads raw data row by row, it guesses, and it burns tokens doing it. UniversalBench runs the calculation inside the runtime and hands your AI only the result. Three tests, run against the live Anthropic API, show the difference.

test 01

Messy CSV revenue

80 sales rows, three date formats, missing and placeholder amounts. Total Q3 2025 revenue from EU customers?

Without2,971input tokens
With UniversalBench101input tokens

Right answer, 25x cheaper output. 96.6% fewer input tokens.

test 02

Statistics over 200 transactions

How many amounts are above $5,000, what is the median, and what is the standard deviation?

Without5,000output tokens, hit the budget
With UniversalBench84output tokens, all three exact

Never finished, versus done instantly.

test 03

Server log error count

A 500-line server log with a realistic mix of INFO, WARN and ERROR. How many ERROR-level lines?

Without20,226input tokens, answered 96 (true: 80)
With UniversalBench48input tokens, answered 80

20% wrong versus correct. 99.8% fewer input tokens.

How we tested. Run on 20 May 2026 with claude-opus-4-7 via the Anthropic API directly, at $15 per million input tokens and $75 per million output tokens. Each “with UniversalBench” call sends Claude a Python-computed answer instead of the raw data, and token counts come from the API’s usage field. The test data is published, and every correct answer is elementary maths you can check in Excel, R or a calculator. Savings depend on the workflow: small queries save less, while bulk data tasks like these save 95% to 99.8%. The “up to 96.5%” figure is a conservative reference from our original public test.

Free tool: LLM cost calculatorSee the tokens and dollars you’d save in a year.Open the calculator →

Guardrails

Limits the AI can’t talk its way around.

Asking an AI to be careful is a request. These are rules the runtime enforces before anything runs, whatever the model decides.

code safety

It never ships broken code.

Every code push is validated before it lands.

  • Syntax validation
  • Live URL smoke test (optional)
  • Automatic rollback support
  • Production-safe deployments
cost guardrails

It never burns your wallet.

Every model call is budget-checked before it runs.

Default ceiling$0.50 / requestHard platform cap$50.00 / requestOver budgetRejected before runSurprise invoicesImpossible
network isolation

It can’t reach your internal network.

Every outbound request is inspected before it goes.

  • Private IP ranges blocked
  • Loopback addresses blocked
  • Link-local ranges blocked
  • Cloud metadata endpoints blocked
asked in a prompt
enforced by the runtime
“Please don’t break anything.”
Broken deployments are blocked before commit.
“Please don’t overspend.”
Overspending is impossible.
“Please stay out of internal systems.”
Internal systems are unreachable by design.
Secrets vaultCredentials are stored encrypted. Never passed to your AI, never logged.
Network isolationThe runtime cannot reach internal IPs or cloud metadata. Enforced at the network layer, not the prompt.
Execution isolationEvery customer runs in its own sandboxed process. No shared state, no cross-customer access.

None of this depends on prompt instructions, agent behaviour or the model choosing to comply.

Getting started

Three steps, then you just ask.

step 01

Create your account

Thirty seconds, no card. 1,000 free actions every month, enough to try it on real work.

your own account and key
step 02

Connect the AI you already use

Claude, ChatGPT, Gemini, Cursor, Codex, n8n or any MCP client. Connect once; switching AI later doesn’t mean starting again.

about two minutes
step 03

Hand over the task

Ask for the outcome, not the steps. The runtime carries it across your systems and brings back the finished result.

you ask once

works across the systems you already use

  • Email
  • Files and docs
  • Spreadsheets
  • Search and analytics
  • Accounting
  • Rostering and payroll
  • Help desk
  • CRM
  • Calendars
  • Team chat
  • Code
  • Databases
  • Any website
  • All integrations →

Your accounts, your say

It acts on your accounts, only when you ask.

UniversalBench connects your AI assistant to the tools and accounts you already use, so it can read your data and take real actions for you, only on your instruction. It works across many services.

As one example, you connect your own Google Search Console and Google Analytics, and your AI reads your search performance (queries, impressions, clicks, position) and your site traffic to diagnose issues and improve your site. At your instruction it can also submit sitemaps and request indexing.

We act only on accounts you own, only when your AI requests it. We never retain your Google data after returning it to your AI, and we never use it for advertising or to train any AI or ML model.

Full details are in our privacy policy.

Pricing

Start free. Pay only for what runs.

All prices in USD. Pick a monthly plan and hand over the work. Every plan runs on the same runtime, so you only choose how much you need.

Personal

$85/ month

Your whole AI business system, for one person

  • Business DNA™ liveUB’s own intelligence engine. It distils the essence of your business (rules, decisions, preferences, people, how work gets done) into a structure we designed, not chat logs.Every AI you connect starts already knowing your business, and gets sharper every day you use UB.Without it: every chat starts from zero and you explain your business again.Yours and ours: Your intelligence is yours. The engine that captures and recalls it is UB’s. We built it for ourselves first, and it is why our small team ships so fast.
  • UB Remote: your AI runs your computerA small app that lets your AI run your computer for you, like having IT support on call.Your AI can use almost any software on your computer: open programs and websites, fill in forms, sort files, print, and even fix problems like a stuck printer by running admin commands. You no longer need to know how every app works.Without it: your AI tells you what to click and you do the work, or you wait for IT.Good to know: it works only on computers you pair, only while they are on, and you can stop it at any time. Approvals before risky clicks are coming soon.
  • Unlimited connected appsConnect your accounting, rostering, email, help desk and more with one click each.Your AI works across all your systems at once.Without it: you copy and paste between tabs all day.
  • Build your own tools previewAsk your AI to build a tool for any job you repeat. UB saves it and runs it the same way every time.UB grows into the shape of your business. Tools run like machines: fast, consistent and cheap.Without it: you explain the same job every week and hope it is done the same way.For example: list unpaid invoices over 30 days every Friday; check next week’s roster for empty shifts; match supplier bills to orders.
  • UB Vault: your password safeThe next step for password managers. People and their AI share one vault, and the AI uses a login without ever seeing it.Your AI can sign in and get work done safely. Passwords never sit in a chat, a document or an email.Without it: you paste passwords into chats, or your AI simply cannot act.Coming soon: the Vault app with a browser extension, and a yes on your phone for every share your AI starts.
  • TypeFree Pro, includedBest in class speech to text on any page.Speak at full speed, press space twice, and your words appear wherever your cursor is.Without it: you type everything, or live with dictation that works in one app only.
  • Nothing moves without your sayAn approval card before any action that moves money.Your AI does the work and you keep the final word. It asks every time, with no “always allow” shortcut.Without it: one wrong AI action can pay the wrong person.Status: live for payments in your accounting app; more apps and UB Remote coming soon.
  • 5,000 actions a month
  • Email support

Or start on Free: 2 apps, 1,000 actions a month.

Add to this plan

Extra actions5,000 for $60
Extra Business DNA storageas you grow
Phone support$29 / month
Choose Personal →

Teams Most popular

$150per person / month

Your company, thinking as one. For 2 or more people

People5= $750 a month

Everything in Personal for each person, plus:

  • Shared company brain liveOne Business DNA for the whole company.A new staff member’s AI is trained on day one, and everyone’s AI follows the same rules.Without it: each person’s AI knows only what that person told it.
  • Live team board coming soonA live board where each person’s AI posts what it is working on, and any AI can raise a ticket mid task.AIs that see each other do not double up, and problems are logged the moment they are found.Without it: two people’s AIs do the same job and issues get lost in chat.We run our own team on it.
  • Share without showingShare a login with a teammate. Their AI can use it, but nobody sees it.Staff get access without ever knowing the password, and you take it back with one click.
  • Owner’s eye coming soonOne view of what every team member’s AI did, when, and in which system.You can trust staff with AI because you can see it.Without it: AI work stays invisible until something goes wrong.
  • Right access, right peopleDecide which systems and actions each person’s AI can reach.Staff get what they need, and nothing more.
  • Staff approvalsMoney actions by your staff’s AI wait for the owner.Your team moves fast and you keep control of the money.Status: live for payments in your accounting app.
  • Tools built once, used by everyoneA tool one person builds can be used by the whole team.Your best way of doing a job becomes everyone’s way.
  • Team dashboard: the team’s work in one place
  • 5,000 actions per person, shared across the team
  • Phone support
  • People who only view or approve are free

Add to this plan

Extra actions5,000 for $60
Setup done for youfrom $500 once
On-site visitfrom $400
Choose Teams →

Enterprise

Talk to us

Proof and control at company scale

Everything in Teams, plus the full control layer:

  • Company single sign-on coming soonStaff sign in with your company’s Microsoft or Google account.Access starts and ends with their work account.
  • Always-on watch coming soonWatches AI activity around the clock.Flags anything unusual before it becomes a problem.
  • Role continuity coming soonWhen someone leaves, their access ends but their work, history and tools pass to whoever takes over the role.Nothing walks out the door.
  • Vault-locked activity records coming soonA full record of staff AI activity, sealed so even UB cannot read it. Switched on only by you.Proof for auditors without giving anyone your data.
  • Your rules, enforced coming soonWrite company rules once, and UB stops any AI action that breaks them before it happens.Prevention, not clean-up.
  • Audit-ready security coming soonSecurity reports for your auditors and insurers.Available once our security certification is complete.
  • Guided onboarding and dedicated helpWe set you up module by module and train your staff as each part goes live.A capable tool is only as good as how it is used.
  • Actions sized to your company
  • Monthly invoice
  • Named contact and on-site visits

Add to this plan

Done-for-you automationsfrom $750 once
A connection to any app, built for youfrom $1,500 once
Extra actions5,000 for $60
Book a call →

Pay yearly and get 2 months free. Actions reset each month and don’t roll over. AI models are billed at a small margin, or free with your own key. Scheduled automations are coming soon.

The control layer: what keeps your company safe while the AI works

What the AI can do grows every month. This part stays the same: a record of everything, rules it must follow, and proof of every job. It’s the same layer we run UniversalBench on ourselves. All included in Enterprise. Teams include Owner’s eye and staff approvals.

Audit log coming soonWho did what, when, from where, with which password, and who approved it. Every person, every action, exportable for your auditor.
Activity monitoring coming soonWatch what every person’s AI is doing as it happens, with alerts for odd hours, new locations or big data exports.
Leash coming soonYour company rules are checked at the moment the AI acts, so it can’t do what you’ve ruled out.
Playbooks coming soonWrite how your company does a job once. The AI follows that playbook every time, so no step gets missed.
Second check coming soonBefore a risky change runs, a second, independent AI reviews it.
Proof of done coming soonEvery finished job comes with a receipt that shows it really happened, not just a “done”.
Staff handover coming soonWhen someone leaves, their access is cut at once and their history passes to whoever takes over the role.
Approvals livePayments in your accounting app wait for the owner’s yes. Payroll, more apps and UB Remote coming soon.
Spend guard liveEvery AI call has a cost ceiling checked before it runs. No surprise bills.
Locked-down by design livePasswords are never shown to the AI, and the AI can’t reach your internal network.

What’s an action?

One thing the runtime does for your AI. Planning and safety checks are free.

1 Send an email1 Read your invoices from your accounting app1 Run a calculation1 One page step in a browser1 Save a row to your database

A busy small business uses about 1,700 actions a month. Most people never reach their plan’s limit.

Common questions

The things people ask us first.

Which AIs work with UniversalBench?

Claude, ChatGPT, Gemini, Cursor, and any MCP-compatible client. Switching AI providers does not require re-integrating UniversalBench.

What counts as an action?

One thing the runtime does for your AI: running code, reading or writing a connected app, a database query, a browser step. Planning and safety checks are free.

Can people from another UB account join my team?

Yes, free. Anyone with their own UB account can join your team, and what they use is billed to their own plan, not yours.

Is the 96.5% token reduction real?

Yes, on bulk data tasks. We have measured reductions of 95% to 99.8% across the three live tests above, all run against the current Anthropic flagship and reproducible from published data. Tasks that send small inputs to your AI will not see savings on this scale.

What happens when I use up my plan?

Extra actions are $0.016 each, or 5,000 for $60, or you move up a plan. Actions reset at the start of each month and don’t roll over. Most people use far less than their plan.

Is my data sent to other AI providers?

Only what your AI explicitly asks UniversalBench to send. Credentials you save go into an encrypted vault scoped to your account. Your data is not used for training. Your AI cannot reach your internal network by default.

What if a validation blocks something I want to push?

You see the exact reason. You fix it and try again. The validation is mandatory because that is what makes the safety claim real, but the error is always visible and actionable.

Can I raise the cost ceiling on LLM calls?

Yes. The default ceiling is $0.50 per call, and you can raise it up to $50. The cap stays on, and you control its size.

How do I cancel?

Cancel any time from your account. Your plan stays active until the end of the month you’ve paid for.

Free setup call

Get connected in 30 minutes. I’ll walk you through it.

We connect your AI assistant, run a live task, and make sure everything works. No technical knowledge needed.

30 minutes · video call · 1,000 free actions a month, no card