NEWv0.1 · LangGraph + Claude · Read the architecture

Build a regulated bank
in 30 minutes.

A LangGraph pipeline of 28+ Claude agents — CTO, architect, security, compliance officer — generates a fintech product with code, tests and an EU AI Act / DORA / MiCA audit pack. AI-Agent Bank in beta. Web3 + AI verticals on the roadmap.

LangGraphClaude OpusClaude SonnetClaude HaikuHardhatFoundryPythonTypeScript

minctrl · workflows · thread-3293eb0c

LIVE

Pipeline — fintech · neobroker

0.0s

InitializeRouter · Config Loader

CTO Debate

Arch Design

Security Gate

GATE

Domain Team

DevOps

Ship

streaming consoleagents · 1

[00:00] ▸ detected: vertical=fintech product=neobroker

Stage

Initialize

Tokens

Cost

$0.00

Agents

Compliance frameworks built into every pipeline

EU AI Act →DORA →MiCAMiFID IIAML5/6GDPRNIS2PSD2SOC2ISO27001BaFinFCATFReIDAS 2

400+

Pipelines shipped

28+

Specialist agents

Product types

$1.47

Avg cost per build

~30m

Median time-to-ship

Graph nodes

Why it's different

Not a code generator.
An automated engineering team.

Deterministic pipeline, not a dice roll

LangGraph state machine — 8 fixed stages with checkpoints, security gates, and a human-readable audit trail. Every run follows the same proven process.

Domain expertise, not a generic model

Separate agent teams per vertical. Fintech agents know FIX, MiFID, pre-trade risk. Crypto agents know reentrancy, oracles, MEV. Not templates — specialists.

Full automation, not just code

The board populates itself. The wiki writes itself. Security reviews on its own. CI/CD scaffolds itself. Code is one output of seven.

Under the hood

Built on LangGraph.
Deterministic. Auditable.

A LangGraph state machine coordinates every agent through 8 fixed stages with built-in checkpoints. No black box — full agent log, cost breakdown and audit trail for every run.

Stage 1 · Initialize

Detect pipeline type, load domain config, bootstrap state

RouterConfig Loader

Inputs

→ Natural language goal

Outputs

← Detected pipeline type

← Domain config

← Initial state

Model

Haiku

Avg cost

$0.01

per stage

Strategic agents

Claude Opus

Deep reasoning: architecture debate, security review, meta-critique

CTOSystem ArchitectSecurityQA LeadMeta Critic

Domain agents

Claude Sonnet

Specialists per vertical — fintech, crypto, AI, infrastructure

Domain SpecialistProduct OwnerAPI DesignerDB EngineerTech Lead

Execution agents

Claude Haiku

High-frequency tasks: DevOps config, cost tracking, formatting

DevOpsPrompt EngineerReliabilityCost Optimizer

Verticals

Fintech today.
Web3 + AI on the way.

8 fintech products shipping today, each with dedicated domain agents carrying production-grade knowledge — FIX protocol, MiFID II, KYC/AML. Includes AI-Agent Bank (beta): an EU AI Act–compliant pipeline where AI agents themselves are first-class banking customers. Crypto and AI verticals on the roadmap; previews below.

src/risk/RiskCheck.ts● generated by Fintech domain agent

// RiskCheck.ts — generated by fintech domain agent

export async function checkBuyingPower(

  account: Account, qty: number, price: number

): Promise<RiskResult> {

  const required = qty * price +

    estimatedFees(qty);

  if (account.buyingPower < required) {

    return { ok: false, reason: "INSUFFICIENT_BP" };

}

  // MiFID II pre-trade log

  await mifidLog({ account, qty, price });

  return { ok: true };

}

New · BetaEXPERIMENTAL

Build a regulated bank
where AI agents are customers.

The ai-agent-bank pipeline ships a full design including DID-based agent identity, agentic KYC, stablecoin payment rails, and multi-sig governance — with a mandatory EU AI Act + DORA compliance pack generated automatically. Preempts Catena Labs positioning.

🪪

Agent Identity

W3C DID + Verifiable Credentials for every AI agent. did:web primary, eIDAS 2.0 wallet.

🔍

Agent KYC

Tiered onboarding: model fingerprint → capability proofs → behavioural monitoring.

⚡

Payment Rails

USDC / EURe stablecoin + CBDC adapter + SWIFT fallback. IVMS101 Travel Rule built in.

🛡️

AI Risk Engine

6 AI-specific scenarios: prompt injection, runaway loop, hallucination, capability creep, model drift, supply-chain.

⚖️

Multi-sig Gov.

m-of-n threshold-sig over agent decisions. Timelock. Append-only audit log. Kill-switch.

📋

EU AI Act ready

Mandatory compliance review: Articles 6, 9–15. DORA ICT risk. MiCA. AML5/6. Evidence pack generated.

Experimental tier · premium pricing · manual onboarding

Human-in-the-loop

Pipeline pauses.
You review. Then it ships.

Choose your level of control. Gates pause the pipeline at critical decision points — a kanban card appears with a GitHub link so you can review the code before approving.

Two checkpoints: architecture sign-off and final ship approval.

Start

CTO

ArchitecturePAUSE

SecurityMANDATORY

Domain Team

DevOps

ShipPAUSE

Done

auto-executingpause for reviewmandatory gate

Full transparency

Watch every agent think.
Every decision logged.

The execution graph shows every agent, every stage, every output in real time. Streaming console gives a live feed of agent reasoning.

Real-time agent execution graph

Watch 9 agents fire sequentially — see status, tokens, cost per node as they stream.

Streaming console — live agent reasoning

Every line the model writes appears in real time. Full chain-of-thought visible, not just final output.

Token-level cost breakdown

Per-agent, per-stage, per-run ledger. Budget alerts before you hit spend limits.

Download all output artifacts

Code, tests, architecture docs, CI/CD config — committed to a Git branch after every run.

Platform

Everything in one workspace

Six integrated modules, built around the agent pipeline. Each one kept in sync with the live run state.

Dashboard

Live workflow status · recent runs · quick switcher

Projects

Pipeline type · goal & config · run history per project

Workflows

Execution graph · streaming console · artifacts

Board

Auto-populated by domain agents · status tracking

Wiki

PRD · arch · API docs · data models · always synced

Analytics

Per-agent cost · token usage · traditional-team compare

Pricing

Pay per pipeline.
Not per developer hour.

Three tiers — start free, pay only when AI ships actual code. Enterprise gets bespoke compliance frameworks and on-prem deploy.

Free

$0forever

Explore what AI engineering can ship. Bring your own LLM key.

1 workflow per day
All 8 product types incl. AI-Agent Bank β
Public GitHub output
Best-effort support

Recommended

Pro

$49per month

For teams shipping multiple products. Priority queue.

50 workflows / month
Private repos + branch protection
All 14 compliance frameworks
Audit-pack generation included
Slack notifications
Email support

Enterprise

Customtalk to founder

For regulated banks and licensed BaaS. SLA + dedicated infra.

Unlimited workflows
On-prem / VPC deployment
Custom domain agents
DORA / SOC2 / ISO27001 attestation
99.9% uptime SLA
Dedicated success manager

Avg cost per pipeline: $0.50–$2 in LLM tokens · Free tier covers your first 30 builds

Benchmark

Minctrl vs. a traditional team

Minctrl

Traditional team

Time to ship

Minctrl~30 minutes

Traditional team2 – 6 weeks

Cost

Minctrl$0.50 – $2

Traditional team$5k – $20k

Output

MinctrlPRD · Arch · Code · Tests · Wiki · CI/CD

Traditional teamCode only

Review trail

MinctrlEvery decision logged

Traditional teamSlack history

Security

MinctrlMandatory gate on fintech/Web3

Traditional teamBest effort

3 pipelines running now

One goal.
20 agents. 30 minutes.

Ship your next fintech, crypto, or AI product with a full engineering team's worth of output — for less than a cup of coffee.

✓ No credit card✓ Full audit trail✓ GitHub-ready output

Build a regulated bankin 30 minutes.

Not a code generator.An automated engineering team.