The 30-Day Dandori Proof · pay after use

See it work before you pay for it.

Because the preparation is done properly, we can stand behind the result. Pick one workflow. In thirty days we deliver a working agent doing it — and if it doesn't do what we agreed, you owe nothing for the build.

One workflow. One governed agent. Real systems. Real work. Measured result. Yours to keep.

Most AI vendors ask you to pay first and hope it works. We think that's backwards. You should see the thing working on your own business before a single dollar changes hands for the build.

The reason we can make that offer is not confidence for its own sake — it's dandori. The risk in an AI project lives almost entirely in the preparation: the unclear process, the undefined rules, the systems that don't connect the way everyone assumed. We do that preparation up front and in the open, so by the time we're building, the outcome is already largely decided. A vendor who skips preparation can't offer a guarantee like this, because they genuinely don't know if it'll work. We do the part that removes the doubt — so we can stand behind the result.

How the guarantee works

Use it. Test it. Push on it.

Before we start, we write down — in plain language — exactly what the agent must do and the boundaries it must respect. That written agreement is the whole deal. No moving goalposts on either side.

At the end of thirty days you decide: keep it running and pay, or walk away owing nothing for the build. Either way, what we prepared is yours — the setup, the rules, the learning. That's not a sales trick. It's how a craftsman stands behind their work.

30Day Proof
What happens, week by week

A structured proof, built for speed and clarity.

Four weeks, four clear steps — the same craft as our method, on a fixed clock. You always know what week you're in and what comes out of it.

Week 1 · Select

Pick the work

We choose the one workflow, define what success looks like, identify the data and systems it touches, and set the boundaries — what the agent decides, and what it must bring to you.

Week 2 · Prepare

Mark the lines

We map the workflow in full: the context, the approvals, the rules, the connections, and the test scenarios. This is the eight-tenths — the preparation that makes the build fast.

Week 3 · Build

Fit the joint

We connect the agent to real inputs and produce working outputs on a controlled path — reviewed with you as it takes shape, never behind a curtain.

Week 4 · Validate

Prove it

We test accuracy, consistency, escalation, and the audit trail on your real work — until you can see it does the job your way, and decide whether to keep it.

A fair trade, made plain

What you bring. What we hand back.

A proof works when both sides know their part. Here's exactly what each of us brings to the thirty days — no surprises.

You bring

One real workflow

  • A sponsor who knows the work — the business or operations side
  • Example inputs: documents, tickets, quotes, or data
  • The systems to connect to (or ones we can simulate)
  • A clear idea of what a useful result looks like
  • Someone who can look at the output and say "yes, that's right"
We deliver

One working proof

  • The workflow and integration design, written down
  • A working agent with predictable output patterns
  • A human-in-the-loop control path — you stay in charge
  • The validation scenarios and success criteria we measured against
  • A clear-eyed recommendation on whether (and how) to go further
Plain terms

What "does what we agreed" actually means.

A guarantee is only fair if both sides know what it means. So we define it up front, in writing, before any money or work is committed. Your engagement is covered by a short written agreement, provided before the build begins.

In plain terms: if the proof does not meet the written success criteria, you owe no build fee. You keep the prepared workflow documentation, rules, success criteria, and integration design. Production operation of the agent begins only if you choose to continue.

What that draws a clean line around: the discovery artifacts, workflow map, rules, success criteria, and agent configuration are prepared and yours to keep regardless of outcome. The deployed working agent is demonstrated against those criteria on your real work. Ongoing production operation is a separate, opt-in step — it starts only when you decide to proceed, never automatically.

See the full guarantee terms in the FAQ
What thirty days actually produces

Sample deliverables, not just promises.

You shouldn't have to take "it works" on faith. Every 30-Day Dandori Proof hands over the same six artifacts — concrete, documented, and yours to keep. Here's the full set, with detailed samples below.

01

Workflow map

Your real process, documented before anything is automated.

02

Rules matrix

What the agent decides, what it escalates, what it must never do.

03

Approval model

The human-in-the-loop control path — who signs off, and when.

04

Integration design

How the agent connects to your systems of record, cleanly.

05

Audit log

Every action recorded — defensible, reviewable, reversible.

06

Ownership package

The agent, rules, and everything it learned — portable, yours.

Illustrative samples of three of these follow, so you know exactly what to expect before you begin.

Workflow map

Sample

Your real process, documented before anything is automated. Example — a purchase-order intake & production-scheduling workflow, integrated with SAP:

1 · TriggerNew PO arrives from a customer
2 · Read SAPPull stock, MRP & open POs (SAP MM)
3 · CheckOn-hand vs. sales forecast (SAP IBP)?
4 · DraftBuild a production schedule & ship date
5 · GateShortage vs. forecast → planner approves
6 · Write SAPConfirm order, post the plan, alert the floor

Supply chain & forecast, connected: the agent reads live inventory and open purchase orders from SAP for supply-chain visibility, checks demand against the SAP sales forecast, and writes the confirmed schedule back — so the plan reflects what's really on hand and what's really coming.

Rules & escalation matrix

Sample
SituationAgent may…Authority
Standard PO, SAP shows stock on hand, normal lead timeAcknowledge & schedule on its ownAutomatic
Order value $10,000–$50,000Draft the schedule, wait for planner approvalReview
SAP MRP shows a material shortage or supplier delayFlag the gap, propose options, holdHuman only
Demand runs ahead of the SAP sales forecastSurface the variance, recommend a reorderReview
Repeat order, SAP confirms same specs & stockReuse the prior build, schedule directlyAutomatic

Audit log

Sample

Every action logged, traced, and reversible — you can always see what happened and why:

TimeActionDetail
07:42Read SAP · scheduledPO-2214 · 500 units · SAP MM stock ok · ship 3 days · auto
08:03Held for reviewPO-2216 · $28,400 · schedule drafted · planner review
08:03Repeat orderPO-2217 · SAP confirms specs = PO-1980 · scheduled
09:20Forecast variancePart 88-A · demand 18% over SAP IBP forecast · reorder recommended
10:15EscalatedPO-2219 · SAP MRP: steel shortage · options proposed · held
13:48Wrote SAP · slottedPO-2216 · released by planner · schedule posted to SAP · floor notified

What you own at handoff

Yours to keep

At the end of thirty days, this is the package that belongs to you — documented and portable, no lock-in:

  • The workflow map, in plain language
  • The rules & escalation matrix
  • The context layer built for your operation
  • The SAP integration, configured & documented
  • The full audit log and history
  • The agent's learning and corrections
  • Plain-language documentation of it all
  • The right to keep running it, anywhere

These are illustrative — yours would be shaped around your own workflow. But the form is exactly this: concrete, documented, and handed to you. Nothing hidden, nothing you can't take with you.

The compounding advantage

Every prepared agent makes the next one faster.

The first agent builds the foundation — and the workflow map, rules, context layer, integrations, and approval model don't get thrown away. They become reusable company infrastructure. The next agent inherits all of it. Most AI spending gives diminishing returns; prepared work does the opposite. It compounds.

The first thirty days are the hard ones, because that's where the foundation gets laid — how your systems connect, how your rules are expressed, how your operation actually works, all written down and understood. That preparation doesn't get thrown away when the first agent ships. It carries.

So when you're ready for a second agent — materials reordering after PO intake, say, or shipping after scheduling — much of the groundwork is already done. The systems are connected. The rules are known. The trust is built. The second proof moves faster and costs less than the first, and the third faster still. You're not starting over each time; you're building on prepared ground.

That's the quiet advantage of doing preparation properly: it's the one investment in AI that's worth more the more you use it. One workflow proves the method. The method is what keeps paying.

How the knowledge grows

Each agent stands on the ones before it.

Every agent you add inherits what the last one prepared — the connections, the rules, the understanding of your operation. So the work gets faster and the foundation gets stronger with each one.

OrderExample agentInherits from the ones beforeTime to deliver
PO intake & schedulingNothing yet — this is where the foundation is laid: systems connected, rules written down, your operation understood.~30 days
Materials & reorderThe SAP connection, the inventory records, the lead-time rules — already prepared during PO intake.Faster
Shipping & deliveryThe order data, the customer links plus the escalation rules — reused, not rebuilt.Faster still
Quote & RFQ repliesYour pricing, your specs, your whole prepared context layer — shared across every agent.Days, not weeks
Quality & compliance logsNearly everything. The groundwork is deep now; a new agent mostly needs its own specific task defined.Fastest yet

Illustrative order — yours would follow your own priorities. The pattern holds regardless: each agent inherits the prepared ground beneath it, so knowledge accumulates instead of resetting.

段取 EACH AGENT TAKES LESS THAN THE LAST Relative effort to deliver — the prepared foundation carries forward, so each new agent is easier than the one before. 0255075100 1stPO intakeagent2ndMaterialsagent3rdShippingagent4thRFQ repliesagent5thQuality logsagent Effort to deliver → 段取り · prepared ground, built on once, reused always
The shape of the advantage: the first agent lays the groundwork and takes the most effort; every one after builds on it and takes less. Heights are illustrative — the downward slope is the point.
The reinforcement loop

And it gets sharper as it runs.

Beyond reuse, each agent improves from doing the work. Corrections and outcomes feed back into the prepared context — so the foundation every future agent inherits keeps getting better.

Run

The agent does real work in your operation, day after day.

Observe

Every action and correction is logged — what worked, what you fixed.

Refine

Those corrections sharpen the rules and enrich the shared context.

Compound

The better foundation lifts this agent — and every future one.

Most AI spending gives you diminishing returns — each tool a fresh start. Prepared, connected work does the reverse: it's worth more the more you use it, because the foundation never resets. And because everything stays yours and portable, that growing advantage is never something you're locked into — it's something you own.

段取り八分 · Preparation decides the outcome

Pick one workflow. See it proven in thirty days.

It starts with a workshop — no obligation. We'll help you choose the task most worth proving first, and write down exactly what success looks like.

Book a workshop