Mace Innovations
Fabric · by Mace Innovations

Production software,
built by AI agents.

Fabric is the platform Mace uses to build real software with AI — now available to you. Pick your path below: have Jerry build and ship it for your business, or run Neo's matrix of coding agents to scale your dev team.

JerryFor your business

Describe what you need. Jerry builds it, tests it, previews it live — then ships it to production himself. 97% of our releases last month went out with no engineer in the loop.

Meet Jerry
NeoFor dev teams

Run a matrix of coding agents in parallel against your own codebase — up to 16 at once. Scale AI development without scaling headcount.

Meet Neo
Book a demo →
Jerry · for your business

Build your software.
No dev team required.

You don't need engineers, agencies, or six-month timelines to build the software that runs your business. You need a conversation.

Build it by talking to Jerry.

Describe what you need in plain English. Jerry — a full coding agent pinned to your app — edits, builds, and tests it, then pushes to your live preview. Click through it, send feedback, watch it get fixed. When it's right, ship to production with one button. Real software, running your business.

  • Full git → your live preview → production
  • One-button go-live — no deploy, no hand-off
  • Sandboxed per customer — your workspace never mixes
  • Your design, your data, your brand
Built for mortgage: origination, pricing, credit, title, HELOC, voice and messaging — eleven vendor integrations, live in production today.
Book a Jerry demo →
// concept → production, in one conversation
01
Describe it
“Add a co-borrower to the 1003 and email them a portal link.”
02
Jerry builds it
Edits your app, runs the build and tests, pushes to your live preview.
03
You review it live
Click through the preview. Send feedback in plain English; Jerry fixes it.
04
Ship it
One button. It's in production — real software running your business.

"I've put about 25 hours into it and it's working almost perfectly. Every issue I flag, it's already fixed by the time I check back."

"If we're going to take over the mortgage world, it's going to take a lot."

— John, early Fabric customer (mortgage)
// While you're doing something else

You're not the bottleneck anymore.

For two years the limit on AI-built software was a person to review it and press deploy. Jerry closes that loop himself — he builds, tests, fixes what review finds, and ships. Last month 97% of everything that reached production went out without an engineer touching it.

476
releases shipped by Jerry
14
shipped by a human
July 2026, measured across every Mace repository — 490 production releases in total. The split is straight from commit authorship, not an estimate.

Runs the build before you ever see it

Jerry compiles, type-checks and runs the test suite on his own work. A red build is his problem to fix, not yours to discover.

Fixes his own review findings

Automated review runs against every change. When it flags something, Jerry corrects it and pushes again — the round trip happens without a person in it.

Ships to production himself

In July, 476 of 490 production releases were made by Jerry. Fourteen were a human merging by hand. That's 97% going live with no engineer in the loop.

Tells you when he can't

If something genuinely needs a human — a vendor contract, a credential only you can grant — Jerry says so in plain English instead of failing quietly.

// Wired in, not bolted on

The systems your business already runs on.

Eleven of these are live in production today. You keep your own vendor relationships — your Encompass account, your pricing contract, whatever you already have. All we need is an API key. The integration itself is already built and maintained, so connecting a system is a one-time handoff, not a project.

And that key never goes into your app. It's stored on our side, encrypted, and used server-side when your software makes a request — so it can't leak out of your code, show up in an error message, or walk out the door with someone. One key, handed over once, kept somewhere built to hold it.

Origination
Encompass / ICE
MeridianLink / LendingQB
Loanscape
Pricing & products
Optimal Blue
Figure HELOC
Borrower data
Experian credit (soft pull)
ResWare title & closing fees
Communication
Feather voice AI
Twilio SMS
Transactional email
Secure one-time delivery
// Mace UI Kit

Screens that already exist don't get rebuilt.

A private component registry Jerry pulls from — pipelines, data tables, dashboards, forms — installed into your app in one step and then styled to your brand. Interface only: no hidden math, no data wiring, nothing to untangle later. The parts that are the same for everyone come off the shelf, so the build time goes into the parts that are yours.

Data tablesDashboardsPipelines & boardsForms & wizardsDocument viewersYour brand, applied
Neo · for dev teams

Scale AI development.
Run a matrix of agents.

For engineering teams and agencies who want the controls. Neo drives a wall of live Claude Code sessions — building, testing, reviewing, and shipping in parallel — inheriting your team's rules. We run it at up to 16 agents at once on a single codebase. Sixteen things at a time, without sixteen more engineers.

// The Matrix — configurable panes · 3×3 shown
agent-01RUN
auth · middleware
● editing verify.ts
✓ 24 tests passing
agent-02
api · /quote
● writing handler
→ zod schema added
agent-03
ui · dashboard
● <DataTable/>
✓ build clean
agent-04
db · migration
● 0007_index.sql
→ applied
agent-05
infra · terraform
● main.tf
✓ plan ok
agent-06
review · PR #482
✓ 0 findings
→ approved
agent-07
tests · e2e
● contact flow
✓ 12 / 12
agent-08
docs · runbook
● README.md
→ 3 sections
agent-09
deploy · preview
→ vercel build
✓ live
1 · 2×1 · 1×2 · 2×2 · 3×3 — pick your layout, then scale to whatever your machines can take

Persistent pane grid

Pick a layout — 1, 2×1, 2×2, 3×3 and beyond. Each pane is its own Claude Code session that keeps state and history, auto-reconnects on drop, and can be dragged, labeled, and color-coded.

Neo

Talk to Neo in any pane. It works against your repo in an isolated workspace — editing, building, testing, committing, and pushing to a PR, with full logs and diffs the whole way.

Fan out without collisions

Run a dozen-plus agents on one codebase at once. Each worker gets its own isolated clone, and landing work rebases onto whatever shipped while it was busy — so parallel agents never overwrite each other's results.

Hypervisor agents

Overnight, supervisor agents read the day's transcripts and commits and surface ranked recommendations — new rules, tighter permissions, docs — with one-click actions.

MCP connectors

Wire your databases, APIs, and custom tools into every agent over the Model Context Protocol — local or remote, with encrypted credentials.

Your context, inherited

Every agent automatically inherits your org, company, and project rules — so a whole wall of sessions builds the way your team does.

Approvals that scale with you

Approving an agent's action used to get more expensive the more agents you ran — the thing that quietly caps every matrix. We cut the cost of a pending approval by 15×, so eight running at once now costs less than one did.

Usage and cost per person

Token usage and approximate spend broken out by user and by project, so a wall of agents is a line item you can actually read instead of one number at the end of the month.

Hosts that heal themselves

Workspace hosts keep themselves current and report their own health — a dead token or a crash loop surfaces as an alert instead of an agent that mysteriously stops answering.

// Compliance & audit

Every session, on the record.

Every keystroke, command, agent response, and tool call — in every Jerry and Neo session — is captured to an append-only, encrypted transcript: input and output, per user, per project. When compliance asks what the AI did and when, you have the receipts.

Append-only & encryptedSecrets auto-redactedTenant-isolatedAudit-ready
matrix_pane_events · jerry · saxton
14:02:11user▸ add a co-borrower to the 1003
14:02:13agent● editing app/api/quote/route.ts
14:02:19tool✓ 24 tests passing
14:02:24agent→ pushed to preview
14:02:25redact[redacted: SUPABASE_KEY]
// The questions you should be asking

“You want an AI to deploy to our production?”

Reasonable. Here are the answers, without the hedging — if any of them made you uncomfortable we'd rather you find out now than six weeks in.

What happens when it breaks something?

Nothing reaches production without passing a build and a test run, and every change goes to a live preview first — so you see it before your customers do. If something does get through, going back is a redeploy of the previous version, not a rescue operation. It's ordinary software with ordinary version control underneath; the agent didn't replace any of that.

Who owns the code?

You do. It's a normal repository full of normal code — TypeScript, SQL, the same stack a developer would hand you. No proprietary runtime, no generated black box, nothing that only works while you're paying us. If you walked away tomorrow you'd walk away with a working application and its full history.

Where does our data live?

In your own database, under your own account. Fabric orchestrates the work; it isn't a place your customer records go to live. Vendor API keys you give us are stored encrypted on our side and used server-side, which is what keeps them out of your codebase and your build logs.

Can we bring our own developers?

Yes, and plenty of customers do. It's a git repository — your team can read it, branch it, review it and push to it like any other project. Jerry is a very productive contributor, not a gatekeeper.

What if it just does the wrong thing?

Then you say so, the same way you would to a person, and it gets fixed and re-shipped. That loop is the fast part — the whole reason iteration matters is that being wrong is cheap to correct. When something genuinely needs a human decision, it says so rather than guessing.

How do we prove what the AI did?

Every prompt, command, response and tool call is written to an append-only transcript, per user and per project, with secrets redacted. It's queryable. That's the difference between answering a compliance question and reconstructing one.

// We run on it too

A team of three builds all of this.

Three engineers, working with a fleet of AI agents, ship everything you see here — our own numbers from last month, pulled live from the GitHub and Anthropic APIs. The best proof it works is that we run the whole company on it.

490
publishes to production
97%
shipped by Jerry, not us
3,401
commits / month
3
engineers
Real data — not marketingPulled live · GitHub + Anthropic APIsSee the monthly reports →
// Bring us something real

Come with a problem.
Leave with software.

Not a slide deck and not a sandbox. Bring the thing your business actually needs and we'll build a piece of it live, against your own systems, while you watch.

Book a demo →See last month's numbers

Every statistic on this site is real. Development figures are pulled live from the GitHub API; token & cache numbers from the Anthropic Admin Usage API. Nothing fabricated.