For support and operations teams

Your top ten lookups,
one keystroke each.

For teams whose work lives in SAP, an EHR, a matter system or a stack of admin consoles. We turn the ten lookups your people repeat all day into a keystroke each, inside the systems and permissions you already have. Live within four weeks, fixed fee in writing first, and the second half is due only once your team is using it.

Get a price for your ten commands Book a 20-minute call

Live on real work within four weeks
Fixed fee, agreed in writing first
One pilot at a time

Already on SAP?

Looking Glass does this for SAP support teams today.

Say what you need, or type a code and a number, and the right transaction opens with the number filled in. It asks before anything can change data. Free company beta, on your test system.

Try the free beta See the product

The hunt tax

What does finding things cost your team?

Every lookup that takes a few clicks too many is paid time. Put in your own numbers. These are starting values you should replace, not our claims.

Lost to hunting, every month

0 hours about $0

Could be given back

0 hours about $0 a month

Get a price for your ten commands

The offer

The Ten-Command Pilot: ten lookups, one keystroke each, live within four weeks.

For one support or operations team. You name the ten lookups your people repeat all day and the system they live in. We build them, your team uses them on real work, and you decide what happens next with the numbers in hand.

Week 1: the ten commands, written down

We name the ten lookups with your people and agree the specification and the acceptance criteria. Half of the fee starts the work.

Weeks 2 and 3: built in small steps

Tests at each step and an engineer reviewing every change, so you see it working early.

Week 4: live on real work

Your team uses it on the real systems, and we check the acceptance criteria together.

Two weeks on: used, then paid

Once your team has used it on real work for two weeks, the second half is due, and you decide what happens next with the numbers in hand.

What you get

Ten commands, built around your words. One system connected, the lookups your people repeat all day, each one a keystroke.
Your permissions, not new ones. Each person’s own sign-in decides what they can reach, and a confirm step sits before any change.
The AI you choose, or none. On the computer, on your own cloud account, or no model at all.
Source, documentation and a runbook, yours to keep. Nothing is rented.

Included, at no extra fee

The written specification, agreed before we build
Tests that pass before release, and a data-flow drawing your IT and privacy people can read
Your security questionnaire, answered for you
Thirty days of fixes after delivery

Price, terms and payback

From $15,000, fixed. One system, ten commands. The exact price is written down after a free first call, before any work starts.
Half to begin. The other half only once your team is using it on real work, two weeks after delivery, not before.
The payback, in your numbers. A 25-person team with ten lookups a day that each cost two minutes, at $45 an hour, loses about 175 hours a month, roughly $7,900. Recover half of it and the pilot pays for itself in under four months. That is an illustration, not a promise: the calculator above runs it with your own numbers.
Live within four weeks. You name the ten lookups. We do the building.
Written acceptance criteria. We agree what “working” means before work begins.
Stop afterward, no obligation. If it is not worth building further, you keep the source and what we learned.
One pilot at a time. Ask for the next start date.

Get a price for your ten commands Try the demo first

The guarantee: paid when it is used

Half of the fee starts the work. The other half is due only once your team has used the ten commands on real work for two weeks, measured the way we agree in the specification. If they are not using it by then, we keep fixing it at no extra fee until they are. If 30 days after that they still are not, the second half is waived and you keep the specification, the source and what we learned. Two conditions: the tool is installed for the team, and your people are free to use it.

The written acceptance criteria stand as well. Anything unmet within 10 business days of delivery we fix at no fee, and if we cannot bring it into line within 15 business days of your notice, we refund what you have paid. It does not promise savings or revenue, or the uptime of your other systems.

Proof

The same method, on our own product, checked in public.

Looking Glass finds the right SAP screen from plain words and opens it with the document number filled in. It never saves or posts anything, and it makes no network requests of its own. We report the misses next to the numbers, and the one-page security overview is public.

Read the worked example Watch the 80-second demo

275automated unit tests

160end-to-end checks

92 to 95%right answer in the top three, on test sets we wrote ourselves and did not tune on, against its built-in list of 142 transactions.

0network requests of its own, measured on version 0.1.0 (see its security overview)

What a hotkey tool does

Press a key. Land in the right place, ready to act.

A small desktop tool, one hotkey away, built around the systems your people already use. It is not another place to log in. It is a faster way into the ones you have.

Find

Plain words in

Say what you need, or type a code and a number. It searches across the systems you connect.

Open ready

Values already filled

It opens the right screen with the details in, so nobody hunts through menus or memorizes codes.

Act safely

Asks before it changes anything

Permissions follow your own sign-in. Change screens ask first, and a production lock can refuse risky actions outright.

AI you choose

Local, your cloud, or none

Use a model that runs on the computer, one on your own cloud account, or no AI at all. Nothing is sent to a model unless you turn on a cloud option, and we name the provider first.

Real teams, real habits

People are wild cards. Build for that.

Every team has a process, and every team has someone who does it a little differently. A new system rarely changes that, and forcing it usually makes things worse. So we don’t. A hotkey tool sits on top of what you already run and finds what people need, however they ask for it.

Keep what you have
Your systems stay where they are. No migration, no rip and replace, and no forcing everyone into one way of working.
Centralize the data, without moving it
One search reaches across the tools your team already uses, so the answer lives in one place. The data stays in your systems, and each person sees only what their own sign-in allows.
Search it instantly
One hotkey and a few plain words open the right record or screen. No tabs, no menus, no asking the person who always knows.
Tune it to the quirks
Nicknames, shorthand, the old name everyone still uses. We teach it how your people actually talk, and adjust it as they keep surprising us.

Four ways to ask. One answer.

Example: four people looking for the same order.

4471Warehouse
sofa refundSupport
couch that came brokenNew hire
damaged sofa ordrAccount manager

Same record, every time

Order 4471Sofa, damaged on delivery

Refund pendingOpens ready

Try it in the demo Get a price for your ten commands

Where privacy is not optional

Better search across your systems, without handing over your data.

Healthcare, legal and e-commerce teams need faster lookups and cannot paste records into a chatbot. Our tools keep data in your systems, follow your permissions, and use AI only the way your rules allow, including none.

Healthcare

Open the right screen, copy no chart

Billing, referrals and front desk find forms, policies and screens in your own EHR. Minimum necessary, no shadow records.

Legal

Matters and documents, walls intact

Permission-respecting search with no cross-client index, and no AI unless your firm and clients allow it.

E-commerce

One order, every system

Orders, tickets, tracking and refunds from one hotkey, with payment tokens only and no card numbers.

See all industries and how we design for privacy

How we make sure it works

Five stages. Each one ends in something you can check.

AI drafts, a named engineer decides, and tests gate every release. At the end you own the source, the tests and the runbook, a system your own people can run, change and trust.

Specify

Write down what it must do, and what it must never do, before any code.

Design

An engineer chooses the architecture, the data flow and the failure modes.

Build with AI

AI drafts and suggests. An engineer reads, rewrites and owns every change.

Verify

Tests and an evaluation on data we did not tune on gate every release.

Hand over

Source, tests, runbook and a plain list of limits. You own it.

One change, start to finish

A draft is not a release.

The robot drafts. A named engineer reviews every change at the gate and answers for it. Tests promote it. Only then does it reach release, and nothing skips a stage.

Draft: AI proposes
Reviewed: an engineer approves
Tested: ready to release

Before you ask

Objections, answered.

“Our people can just use ChatGPT.”

They can, and so can your competitors. Everyone gets the same assistant and the same edge. We build tools around your own systems and rules, and you own them.

“Can we trust code an AI helped write?”

Trust the process, not the tool. A named engineer reads and answers for every change, and tests must pass before anything ships. AI drafts. It never approves.

“What happens when the AI gets it wrong?”

It cannot act alone. Anything that changes data or money stops at a fixed gate and waits for a person. We test on data we did not tune on, and show you the misses.

“Won’t we be locked in?”

No. You get the source, the tests and a runbook, and the model can be swapped. Nothing breaks because a provider raised a price or changed a prompt.

“What if our people don’t use it?”

You do not pay the second half until they do. It is due only once your team has used the ten commands on real work for two weeks. If they have not, we keep fixing it at no fee, and if they still are not using it 30 days later, the second half is waived and you keep the source. The first call and the written quote are free, so you know the price first.

“Where does our data go?”

Nowhere without your say. We draw the data flow first, name any model provider before a single byte is sent, and never train on your data.

Questions

The short answers.

What does it cost?

Pilots start at $15,000 as a fixed fee, covering one system and about ten commands. The exact price depends on the system and is written down after a free first call, before any work starts. Half is paid to begin, and the other half only once your team is using it on real work, two weeks after delivery. If access to your system is unclear, we start with a short paid scoping step that is credited to the pilot. A full build and monthly care are quoted after the pilot.

What happens after the pilot?

You decide, with the numbers from the pilot in hand. Keep the ten commands as they are, stop, or go on to a full build: more systems and commands, quoted separately after the pilot, with a monthly care plan if you want the connectors kept current.

Isn’t this just Raycast, or Spotlight, for my company?

It is the same idea, built around your company. Raycast is a capable general launcher, and if your work lives in public SaaS tools it already connects to, use it. Build custom when your people live in SAP, an EHR, a matter system or internal tools an off-the-shelf launcher does not reach, when your permissions and privacy rules decide what can be searched and which AI is allowed, when it must run with no AI or send nothing off the computer, or when you want to own the source. We say so on the first call if an off-the-shelf tool fits.

Is this just an AI wrapper?

No. A wrapper is a prompt and an interface over someone else’s model. We build engineered software: your logic, your data flow, your integrations and a gate before anything changes, with a model used only where it earns its place. You own the result, and it does not stop working when a model provider changes a price or a prompt.

Is this vibe coding?

No. Vibe coding means accepting whatever an AI produces and hoping it works. We write a specification first, an engineer reads and takes responsibility for every change, and tests gate each release. AI makes the engineers faster. It does not replace their judgement.

Do you train models on our data?

No. When a project needs a model provider, we use terms under which your data is not used for training, and we tell you which provider before any of your data is sent.

Start here

Name the ten lookups. Get a fixed price.

Tell us the system and the lookups your people repeat all day. We reply within one business day, say honestly whether a pilot makes sense, and the first call is free.