Running locally · Montréal, Québec

An AI that acts.
And stops when it should.

MIKE runs the repetitive parts of your business end to end, unattended.

or map one of your own workflows first

→ The console beside this is not a recording.

mission · unanswered quote requests
54
Skills
21
MCP servers
114+
Tools
234
Offline tests
35B
Local MoE
0
Paying customers yet

That last number is not a typo.

01The arithmetic

First, what the manual version already costs you.

Move the three sliders to your real situation.

8 h
2
45 $

Loaded cost means salary plus payroll taxes, benefits and overhead.

Cost per year, doing it by hand
37 440 $
22 464 $
Portion a mission could absorb
499 h
Hours returned to your team per year
Stated assumption: 60% absorption of the repetitive portion.
02The difference

A chatbot answers. An operator finishes.

You don't hire people to answer questions. You hire them to close loops.

It plans, acts, verifies, remembers and follows up.

07:00
Briefing sent
08:32
Request detected
08:34
Context pulled
08:36
Reply drafted
08:38
You approve
08:42
Reply sent
12:00
Silence audited
15:00
Follow-ups out
17:30
Day summarised

Shaded = the only moment that needs a human.

03Mission mapper

Describe your bottleneck. Get the real plan back.

Ordered steps, the tool each one needs, what gets checked, where you sign off.

Runs entirely in your browser.

04The evidence layer

Don't trust the log. Break it.

Every row carries a real SHA-256 hash computed in your browser.

Not verified yet.
Time Tool Action — editable Result Check Hash (prev → this)
05Local-first

Your client history shouldn't become someone else's training data.

Here is the honest split.

Stays on your machine

35B MoEThe model that reads your data runs on your GPU.
SQLite · Mem0Persistent memory of clients, prices and decisions.
LightRAGYour documents, indexed and searched locally.
JournalThe audit trail, on your disk, exportable at any time.

Leaves, because you connected it

GmailReading and sending mail means talking to Google.
Shopify · GA4 · AdsSame. Their API, their servers, their logs.
Twilio · TelegramMessages transit through the carrier you chose.
Not claimedThat zero data ever leaves.

Designed with Québec's Law 25 in mind.

06The pilot

One workflow. Four weeks. Bounded before it starts.

A pilot is a fixed scope with a fixed end date, agreed in writing before anyone starts.

Four weeks.
One workflow.

Fixed fee, quoted in writing after a 30-minute scoping call.

  • Week 1 — we bound the workflow and connect only what it needs
  • Weeks 2–3 — shadow mode on your real work
  • Week 4 — measured report with the real absorption rate
  • You keep the full journal, exported
  • Not included — production deployment or new integrations

What happens if it doesn't work

If the measured absorption comes in under 30 %, we say so in writing and do not propose a deployment.

This is a small independent practice, not a platform with a sales quota.

After a successful pilot

Deployment is quoted against the scope the pilot actually measured.

Start with one workflow
07Straight answers

The questions you'd ask on the call.

What does a pilot cost?

A fixed fee, quoted in writing after a 30-minute call.

You get the figure before you commit to anything.

What if it sends something wrong to a client?

Shadow mode means MIKE proposes and a human sends.

The journal tells you exactly which action and who approved it.

Why not just use ChatGPT or Copilot?

The gap is that they wait for you.

If your bottleneck is writing, you don't need MIKE.

What happens to my system if F51 disappears?

MIKE runs on your hardware, in open formats — SQLite, YAML, NDJSON.

What you would lose is support and new skills, not the operation.

Do I need a server room or a data scientist?

A single workstation with a consumer GPU handles a small business workload.

Who has done this already?

Nobody, as a paying customer.

Being among the first is a real risk, and the pilot is structured so that it is a small one.

Can it work in French?

It replies in whatever language the customer wrote in.

08Request a pilot

Give MIKE one workflow.

No demo environment, no deck.

Reply within two business days.
A sentence or two is plenty.
06Commitments

What this practice will and won't do.

The only durable asset is whether the claims hold up.

Will

  • Publish results with their status attached
  • Kill its own impressive numbers when an equivalence check fails
  • Tell a client the pilot didn't work, in writing
  • Keep client systems in open formats

Won't

  • Sell blanket regulatory compliance
  • Let an agent produce independent professional advice autonomously
  • Quote a design-stage idea as a measured capability
  • Put customer logos on a page before there are customers