AI automation for small and mid-size businesses. We automate the repetitive tasks that pull you away from the work you love.
Compass AI Consulting is an AI automation firm, registered in Florida and working with clients in the US and Europe, in English, Spanish and Italian. We run short paid discoveries, build the systems that come out of them, and hand them to your team to run.
"My team retypes the same information into four different places."
Quotes, intake forms, reports, invoices, social posts. Work that is necessary, repetitive and quietly expensive.
What we build: workflows that move and check the data for you, with a human approving what matters.
"Everyone says we should use AI. Nobody can tell us where."
Long lists of ideas, no way to rank them, and no honest read on what is actually buildable with the data you hold today.
What we build: a short discovery that ends in a ranked roadmap instead of a wish list.
"Our data is confidential. We cannot just paste it into ChatGPT."
Law firms, healthcare and finance teams that are told to adopt AI and forbidden to send client information anywhere.
What we build: private, self-hosted systems, so the data stays on infrastructure you control.
We interview the people doing the work and map how it actually runs, not how the process document says it runs.
Every candidate gets a feasibility check: what exists off the shelf, what it would cost to build, and the pros and cons of each. You get a ranked roadmap.
We break the project into phases, each one a working piece your team can use before the next starts. Then we train your team and hand over the system, the documentation and the keys.
We interview the people doing the job, map how it actually runs, and check what is realistic with the data you hold today.
Fixed fee, scoped to the size of the business and quoted after a first call.
We build what the roadmap ranked first, in small phases you can watch working, on the tools your team already uses. When the data cannot leave your control, we build it on infrastructure you own.
Fixed fee per phase, quoted once the first phase is scoped.
For clients who would rather not hand the thinking back. It stays the same person who built your systems, now on the inside, without adding anyone to your payroll.
An ongoing engagement, reviewed every quarter.
A small online retailer needed daily posts on Instagram and Facebook. Writing captions, producing images and scheduling them fell on the owner, and it kept slipping.
We built a content pipeline that generates a month of posts at a time, writes captions in the brand's own voice, generates the images with AI, and pulls live inventory from Shopify so it only features products actually in stock. Everything lands in a review queue: the owner approves or edits, and the system publishes on schedule to both channels.
Ten hours a month down to half an hour or one hour is a reduction of 90 to 95%, on the owner's own estimate of the work before and after.
Three posts the pipeline wrote, illustrated and published, captions included. Images generated with AI. Click a post to read it full size. The brand's name and handle are blurred.
The firm handles confidential client matters. Off-the-shelf AI tools were not an option, and the internal appetite for automation was growing anyway.
We stood up and secured a private automation server on infrastructure the firm owns, documented how it runs, and handed it over with a maintenance runbook so their own IT team operates it.
Researching the company, mapping its stack and writing the question list ate an afternoon before every call. Then the write-up, the feasibility checks and the first proposal draft ate another one after it.
We built three AI skills that cover the whole cycle. One researches the company and produces the briefing. One turns the recording into structured notes, action items and CRM entries. One assembles the feasibility pass and the first proposal draft. The judgement stays human. The assembling does not.
The post-call write-up and the first proposal draft came down in the same way. Because the skills are plain instructions, not a product, they run in Claude or on any platform that reads the same skill format, and they plug into the tools the practice already keeps its records in: Notion, Google Drive, a CRM, a shared folder.
Three to five hours down to one is a reduction of 65 to 80%, measured on discovery calls run with the system against the manual process used before it.
The team helped us think through AI in a way that actually made sense for our escape room business. The process was practical, collaborative, and grounded in how we really operate.Locked Manhattan · Escape room, Manhattan, Kansas
Training your team on what we build is part of the hand-off. These are the same explanations, recorded. No slides, no jargon.
If a tool you already pay for can do the job, we tell you. That costs us a project. It also means that when we do say build, you know we mean it. We are here to fix the problem, not to sell you a build.
Every build is split into small phases. Each one starts by measuring how the process runs today and stating where it should land. If nobody measured the before, nobody can honestly tell you the after was an improvement.
Your business is not a template, so your system does not come from one. We start from how your team actually works, quirks included, and build for that. The same solution handed to everyone fits nobody.
Your team keeps the tools it already knows. We connect them, fill the gaps and automate what sits between them. If a tool really is the problem we will tell you. No rip and replace. If something new is needed, we train the people who will use it.
Two founders. Alessandro runs the client work, from the first call to the hand-off. Katherine advises internally on how each engagement should be shaped.
Serving two continents
Two and a half years at Capital One building data pipelines, internal tooling and secure backend services for a bank that cannot afford mistakes. He is your point of contact throughout, and he designs and builds every system we deliver. Works in English, Italian and Spanish.
She was a strategy and operations consultant at EY and Slalom, then led culture integration for global expansion and M&A at DoorDash. Today she is a career and life coach, and the one who finds the process hiding behind the mess. She works mostly as an internal advisor, shaping how an engagement should run rather than fronting it. Works in English and Spanish.
Where we learned how large organizations actually run. Alessandro at Capital One. Katherine at EY, Slalom and DoorDash. Between us, we worked at or delivered work for these organizations:
The systems we build give people their week back. The first call is 30 minutes and free: long enough to hear what is eating your week and tell you honestly whether there is something here worth looking at. What to automate, what it is worth and what it costs comes out of the paid discovery that follows.