Looking Glass
For SAP support teams
Say what you need, and it opens the right SAP screen with the document number filled in. It asks before anything can change data, and makes no network requests of its own.
Hotkey tools for company systems
Stop paying your team
to hunt for screens.
One hotkey takes your people to the right screen in the systems you already use. We build it around your company, with engineers reviewing every change and the AI you choose, in a fixed-fee pilot you can stop after.
- Works with the systems you use
- AI you choose
- Asks before it changes anything
Two ways to work with us
Use our product, or have us build yours.
A hotkey tool for your systems
Built custom, with the AI you choose
We build a hotkey tool wired into the systems your team uses. Engineers review every change and AI speeds them up, and you keep the source, the tests and the runbook. Start with a pilot: one system, about ten commands, a fixed fee, and a clear stop point.
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
Arithmetic on your inputs, 21 working days a month. We have not measured your team, and a pilot is how you find the real number.
Get your pilot scopedThe offer
The Hotkey Pilot: your team’s first hotkey, working on real work.
Pick one system and about ten commands your people use most. We build them, you try them on real work, and you decide what happens next.
What you get
- One system connected, about ten commands built around your words
- Permissions that follow each person’s own sign-in, and a confirm step before any change
- The AI you choose, or none
- A written specification, tests that pass before release, and a data-flow drawing
- Source, documentation and a runbook, yours to keep
How it runs
- Pilots start at $15,000, fixed. One system and about ten commands. The exact price is written down after a free first call, before any work starts. Half to begin, half on delivery.
- Two to four weeks. You tell us the ten commands. We do the building.
- Written acceptance criteria. You and we agree what “working” means before work begins.
- Stop afterward, no obligation. If it is not worth building, you keep what we learned.
- One pilot at a time. Ask for the next start date.
The guarantee
If the pilot does not meet the written acceptance criteria, tell us within 10 business days of delivery which criteria are unmet. We fix them at no extra fee. If we cannot bring it into line within 15 business days of your notice, we refund the pilot fee. This covers the agreed deliverables. It does not promise adoption, savings or revenue, or the uptime of your other systems.
Check us before you commit
We have no client case studies yet. Our SAP beta is our own product, tested and published, not a client deployment. Read the worked example with its test results, the security overview and the product video, then decide whether a pilot is a fit.
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.
Where it can connect
ERP
ERP and finance
HR and finance
IT operations
Active DirectoryDirectory- Microsoft Entra IDIdentity
Network
Google WorkspaceWorkplace- Island PacificRetail
AI you choose
OllamaLocal AI
ShopifyE-commerce
Payments
Helpdesk
Physical therapy
SquareRetail POS
When I WorkScheduling- Drake TaxTax software
- ClioLegal
- Your own toolsScoped with you
Systems we build for, and the first one is SAP, in beta. Names belong to their owners. See how each one connects.
Our founder has worked with the interfaces of these systems before. Only SAP is a built connector today, in beta; the rest are scoped with you in a pilot, and each one is marked honestly.
For teams 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.
What we build
Tools your company keeps, not a chat box you rent.
The companies that pull ahead in the age of AI will not be the ones with the thinnest layer over someone else’s model. They will be the ones with their own tools, built around how they actually work, and engineered to last.
Systems, not wrappers
Real software with AI where it earns its place
Deterministic logic, integrations, data flow and a gate before anything changes. A model is one component, never the whole product.
Yours to own
Source, tests and a runbook, handed over
You are not renting access to a prompt. You own a system your own people can run, change and trust.
An edge that compounds
Built around the work only you do
Tools that make your specialists faster at the thing that sets your company apart, which a generic AI product cannot copy.
The difference
Vibe coding hopes. Engineering knows.
AI can write code in seconds. Whether that code is correct, secure and maintainable is an engineering question, and it takes an engineer to answer it. An AI wrapper skips the question altogether: a thin layer over someone else’s model, easy to copy and easy to lose.
Vibe coding
- Prompt, accept, ship
- No written specification
- Nobody can explain why it works
- Tests, if any, written by the same AI that wrote the code
- No one accountable when it breaks
AI-enhanced engineering
- The specification is agreed first
- An engineer reviews every change before release, as set out in the written specification
- Tests and evaluation run before every release
- AI drafts, people decide
- A named engineer is accountable for what ships
Why buyers are right to ask
62%of IT and technical leaders named security and privacy as a top concern with AI in DevOps
54%cited poor-quality or insecure code as a challenge of vibe coding
33%were concerned about unclear ownership of AI-generated code
EMA survey of 206 IT and technical leaders, as reported on PR Newswire. Survey findings, not a measure of every organization. Our answer is a process: review, tests, data-flow drawings, and source you own.
Behind the wheel
Real engineers steer. AI is the co-pilot.
AI drafts code, proposes tests and searches documentation faster than anyone. It does not understand your business, carry responsibility, or know when it is wrong. Our engineers do.
The engineer decides
- Architecture and security
- What is built, and what is not
- What ships, and why
- Accountability for the result
AI assists
- First drafts and refactors
- Test and edge-case suggestions
- Documentation and search
- Nothing ships on its own
- Engineer-reviewed
- Tests before every release
- You own the source
The engineering method
Five stages. Each one ends in something you can check.
01
Specify
Write down what it must do, and what it must never do, before any code.
02
Design
An engineer chooses the architecture, the data flow and the failure modes.
03
Build with AI
AI drafts and suggests. An engineer reads, rewrites and owns every change.
04
Verify
Tests and an evaluation on data we did not tune on gate every release.
05
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. An engineer reviews every change at the gate. 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
A worked example
Our own product, checked in public.
We have no client names to show yet, and we will not invent any. Instead, here is how our method looks on something we built and ship ourselves.
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.
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. Not a guarantee for your system.
0network requests of its own, measured on version 0.1.0 (see its security overview)
Honest about it: it has been tested against a stand-in for SAP. The first results on a real SAP system come from the beta.
Before you ask
Fair questions. Straight answers.
“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.
“How do we know it is worth it before we commit?”
You find out first. A short, paid, fixed-scope discovery ends in a written brief, an evaluation plan and a quote. Stop there if it does not add up.
“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
Straight 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 half on 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.
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 with shared commands, extensions and AI, and some teams should simply use it. Build custom when your people live in systems an off-the-shelf tool does not connect to, when your permissions, privacy rules or compliance needs decide what can be searched and which AI is allowed, when you need it to 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 use AI to build?
Yes, and we say so. AI coding tools are part of our process, under engineers who review everything they produce. What we rely on is a written specification and tests that run before every release, not trust in any tool.
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.
Do you have clients we can ask?
Not yet to name. Our worked example is our own product, and we say so. If we ever publish a client’s name, it will be with their written permission.
Which models do you use?
We choose per project, from cloud models from providers such as Anthropic to open models that run on your own infrastructure, and write the choice into the data-flow diagram.
What do you not do?
We do not sell hype, guarantee savings, or build anything that acts on money or records without a confirmation step.
Where are you?
Lawrenceburg, Tennessee. We work with businesses across the United States.
Start here
Tell us where your team loses time.
Name the system. We reply within two business days, say honestly whether a pilot makes sense, and the first conversation is free.