Landing page copy · final revision
- Content hash
wp_3f9c4a…d2e1- Checked by
- Outcome verifier
Product tour
From one sentence to evidenced work, inside a budget
Ulpi turns a sentence into an editable company, runs work in an isolated sandbox with models handled for you, closes each task only on real evidence, and gives you one Home view to steer it — without spending past your cap.
How it works
Four stages, end to end
This is the whole loop — describe, land, prove, steer. Nothing closes without evidence, and nothing spends past your cap.
- 01Describe
Describe the company in one sentence
Write a single line. ulpi proposes an editable org chart, a goal with a measurable target, 30/60/90 milestones, and the Day-1 work. Adjust the roles, goals, and budget envelope, then hire the team in a click — nothing runs until you approve the plan.
You shape the company before any spend: edit the org chart, set the goal target, and fix the budget cap that will bound every run.
- 02Home
Land on Home and watch your team get to work
After you hire, Home becomes the daily view of your company. Your teammates pick up Day-1 work and run it in an isolated sandbox, with models handled for you and no keys to manage. Home shows verified work, current spend, budget health, decisions waiting for you, and what each teammate just made.
Every run is metered and budget-capped: cost accrues as quantity times versioned pricing as a run proceeds, secrets and cost references never leak into logs or outputs, and a run that would cross your cap pauses mid-flight and surfaces for approval.
- 03Evidence
Work closes only when it is proven
A task is done only when it produces a content-addressed WorkProduct you can open and passes a verification on every required outcome, under separation of duties. A teammate saying it finished is never enough.
Open the WorkProduct, see the passing verification on each outcome, and trust the closure — done is evidenced, not declared.
- 04Chat
Steer your company in plain language
Open Chat and tell your company what to do next. Each turn resolves to a typed, reviewable change — or a clear refusal that tells you why — never vague prose, and every change is undoable. When you want the numbers, the Cockpit sub-view shows burn against the cap, cost per verified outcome, and read-only revenue from connected Stripe and analytics.
Every Goal to Work to Run to cost to log is threaded by one correlation ID, on an append-only, hash-chained activity ledger you can open from the Cockpit.
Evidenced, never declared
This is what a closed task looks like
Every task produces a content-addressed WorkProduct and a passing check on every required outcome before it closes. Done is shown — not declared.
Three honest states
VerifiedReviewedRecorded
Only the actual closure tier is shown. Absence of proof can never read as proof.
Inside the product
The screens you actually run your company from
No abstractions. This is what you sign in to every day — four tabs (Home, Team, Work, Chat) plus the one-sentence company-builder hero — from the first ask to evidenced, budget-bounded work.
VerifiedReviewedRecordedEvidenced, never declared
01
Build your company
Type one sentence — or tap Ask your company — and ulpi proposes an editable org chart, a goal with a measurable 30/60/90 target, and the Day-1 work. Adjust the roles, goals, and budget envelope before anyone is hired.
02
Home
Where you land every day. See verified outcomes, current spend, budget health, decisions waiting for you, and what your teammates just shipped — with Ask your company at the top.
03
Team
Your teammates — the team you hired, shown as people. Each row shows who they are, what they are working on, what they have spent today, and whether they are active. Open one to see verified, reviewed, and recorded results, plus cost per verified result.
04
Work
Every task closes only when it is evidenced: a content-addressed WorkProduct you can open plus a passing check on each required outcome. Tap any shipped item to see exactly what your teammate made. Done is shown, never just declared.
05
Chat
Steer your company in plain language. A turn resolves to a typed change you can review, or a clear refusal that tells you why — never vague prose, and every change is undoable.
06
Cockpit
Want the numbers? The Cockpit is the deeper money view behind Home: live burn against the cap, a budget gauge that auto-pauses a run before it crosses the line, cost per verified outcome, and read-only Stripe and analytics revenue beside the spend.
What the platform does
Concrete capabilities, not promises
Each module is something you can point at in the product today.
01
Sentence-to-company builder
ulpi turns one sentence into a proposed org chart, a measurable goal, 30/60/90 milestones, and a Day-1 work set — all editable before you hire.
02
Evidence-gated closure
Work cannot be marked done by a teammate's say-so. It needs a content-addressed WorkProduct and a passing verification on every required outcome, with separation of duties enforced.
03
Budget envelope with auto-pause
Set a hard cap. A run that would cross it pauses mid-flight and surfaces for approval. Cost is metered as quantity times versioned pricing, down to the cent.
04
Sandboxed runs
Your teammates execute in an isolated sandbox — the models are handled for you, with no keys to bring or manage. Every run is metered and budget-capped, and secrets and cost references are never written into logs or work products.
05
Cost per verified outcome
The Cockpit divides real spend by evidenced outcomes, so you see the unit economics of the work — not just a token bill.
06
Hash-chained activity ledger
Goal to Work to Run to cost to log is threaded by one correlation ID, and the activity log is append-only and hash-chained so the trail cannot be quietly rewritten.
07
Morning Briefing and one-tap approvals
A daily Shipped / Blocked / Needs-you / Money / Mentions digest with one-tap approve or deny — resolving cleanly to granted, denied, expired, or conflict.
08
CEO Chat that returns typed operations
Steering turns compile to a typed operation or a 422 refusal with a reason. No free-text actions, no silent edits — every operation is reviewable and undoable.
In depth
What each part does
Build your company
Turns one sentence into a proposed, editable org chart with a measurable goal, 30/60/90 milestones, and a Day-1 work set. You edit everything and set the budget cap before hiring.
Sandboxed runs
Your teammates execute in an isolated sandbox — the models are handled for you, with no keys to bring or manage. Every run is metered and budget-capped, and secrets and cost references never leak into logs or outputs — references, never raw values, appear in envelopes and logs.
Evidence-gated closure
Each required outcome needs a passing verification and a content-addressed, immutable WorkProduct before the task closes. Separation of duties keeps the doer and the verifier apart.
Budget envelope
A hard cap with a visible auto-pause. Spend is metered as quantity times versioned pricing across every matching scope, and a breach pauses the run until you resume it.
Cockpit
The deeper money view behind Home: cost per verified outcome, live burn, and read-only Stripe and analytics revenue, with a trust ledger and a correlation-ID drilldown into the underlying activity.
Morning Briefing
A daily Shipped / Blocked / Needs-you / Money / Mentions digest. Approve or deny what needs you in one tap, resolving to granted, denied, expired, or conflict.
CEO Chat
Plain-language steering that compiles to a typed operation or a 422 refusal with a reason — never free prose. Every operation is reviewable and undoable.
Honest bounds
Ulpi is in its founding-customer phase, with every run metered, budget-capped, and evidence-gated, and no claim of unlimited autonomy. The platform makes its limits explicit rather than hiding them.
What people build
A few companies owners have described
Illustrative examples of the work an evidenced, budget-capped team takes on. ulpi shapes the plan; you approve before anyone is hired.
“Build and launch a landing page and waitlist for my developer tool.”
Your teammates draft the page copy, ship a clickable landing page as a WorkProduct, wire a waitlist capture, and verify each against the brief before it closes — inside a fixed launch budget.
“Run a weekly technical blog and keep the docs in sync.”
Your teammates propose a calendar, produce drafts as reviewable WorkProducts, run a verification pass on accuracy and links, and surface anything that needs your sign-off in the Morning Briefing.
“Keep product listings accurate and answer common support questions.”
Your teammates reconcile listing data, prepare update WorkProducts for review, and draft support replies — escalating edge cases to you rather than guessing, all under a monthly cap.
“Build small internal utilities and keep them maintained.”
Your teammates scope each utility when you describe it, build it in an isolated sandbox with the models handled for you, and close the work only when a passing verification confirms it does what the goal said — every run metered and budget-capped.
Questions
Straight answers
- Do teammates have unlimited autonomy?
- No. Every run is bounded by a hard budget cap that auto-pauses before it is crossed, work closes only on verified evidence, and steering operations are typed and undoable. You stay the decision-maker.
- Do I have to bring or manage AI keys?
- No. ulpi runs the models for you — there are no keys to bring or manage. Every run executes in an isolated sandbox, is metered once as quantity times versioned pricing, and is held to the budget caps you set, with usage shared by billing and your caps.
- What does "evidenced" mean?
- A task closes only when it produces a content-addressed WorkProduct and passes a check on every required outcome, under separation of duties. In the app you see exactly how each result is evidenced — Verified (a deterministic check we re-ran), Reviewed (a separate judge graded it), or Recorded (an external receipt). A teammate claiming it is done is never enough.
- How do I control spend?
- You set a budget envelope. Costs accrue as quantity times versioned pricing across every matching scope, and any run that would cross a cap pauses and surfaces for your approval before continuing.
- Is my data safe?
- Every run executes in an isolated sandbox, and secrets and cost references are never written to logs or WorkProducts. Companies are tenant-isolated and the activity log is append-only and hash-chained.
- Can I steer the work day to day?
- Yes. Home surfaces what shipped, what is blocked, and what needs you with one-tap approvals, and Chat turns plain-language direction into typed, reviewable changes.
- Is Ulpi generally available?
- Not yet. Ulpi is in its founding-customer phase — we are onboarding a small set of teams to build companies alongside us. Request access and we will be in touch.
Build a company the way you would actually run one
Describe it in a sentence, set a budget, and let an evidenced team of teammates get to work — with you steering from Home.