00 For Forex and CFD brokers

We work inside your brokerage until the workflow is fixed.

Private AI, automation and integrations, delivered on site by a forward-deployed engineer. We find the workflow that actually costs you time, build the smallest thing that improves it, and show the evidence before the scope grows.

  • Fixed-fee discovery

    A written assessment you can use even if you do not proceed to implementation.

  • Broker-controlled data

    A verified data boundary, with every exception written into the contract.

  • Measured before scaled

    A baseline, representative cases, and a decision — not a platform sold in advance.

01 Where the time goes

Four problems we expect to meet first.

These are the recurring operational loads we look for in a brokerage. The first engagement starts with whichever one your own staff can show us, with a recent example and a sequence of handoffs.

  1. 01

    Support knowledge is scattered

    Staff search policies, tickets and colleagues for an answer that should already exist. Entity rules conflict with last month’s version.

    Typical buyer · COO or head of support

  2. 02

    Documents pile up in review

    Onboarding and periodic refresh stall on incomplete files, duplicate entry, expired documents and unclear ownership.

    Typical buyer · Compliance or operations

  3. 03

    Systems do not share a record

    CRM, client portal and trading data are copied by hand. Identifiers drift. Failed handoffs show up late, usually in a spreadsheet.

    Typical buyer · CTO or COO

  4. 04

    Records must stay in bounds

    Client and policy data cannot leave an agreed environment. A general AI tool does not meet that requirement, and a local model alone does not either.

    Typical buyer · CIO and security

02 How we work

Start with the problem. Earn the right to build.

Each stage is a purchase with a deliverable and a reason to continue. We do not ask a broker to buy a platform before one workflow has proved itself.

01

Discover

What you buy A process map, a ranked pain-point register, a quantified baseline and an implementation proposal.

Evidence to continue A named sponsor, a useful problem, viable access and a budget.

02

Prove

What you buy One integrated prototype in a controlled environment. A conventional automation is equally valid when a language model adds little.

Evidence to continue Measured quality and improvement on representative cases.

03

Deploy

What you buy A hardened application, staff training, runbooks and a handover your own team can operate.

Evidence to continue Signed acceptance, an operating owner and support arrangements.

04

Maintain

What you buy Defined support, updates and a bounded improvement backlog. A recurring fee buys a continuing service, not an indefinite subscription for a one-time install.

Evidence to continue Actual usage, reliable operation and a justified renewal.

05

Repeat

What you buy Adaptation of a proven module for another broker or another entity. Customer records and policies are never reused without authorisation.

Evidence to continue Similar demand, and an implementation that is materially reusable.

03 The discovery week

Five days inside the operation. A report you keep.

This is an embedded workflow assessment, not an informal visit. We need people, examples and system documentation. Unrestricted production access is not required. Preparation and the written report sit outside the onsite days.

  1. Day 01

    Map the room

    Meet the sponsor and the process owners. Establish the operating environment.

    Leaves with System inventory, workflow boundaries, success criteria.

  2. Day 02

    Watch the work

    Observe staff handling ordinary cases and the exceptions that actually consume the day.

    Leaves with Current process map, handoffs, an initial time baseline.

  3. Day 03

    Trace the data

    Review documents, integrations, permissions and hosting. Start from synthetic or redacted examples.

    Leaves with Data-flow map, API feasibility, security constraints.

  4. Day 04

    Rank the fixes

    Compare candidate improvements with the people who do the work and the people who own the systems.

    Leaves with Ranked opportunities and a small proposed pilot.

  5. Day 05

    Decide the next step

    Review findings, assumptions, cost and who is responsible for what.

    Leaves with Discovery report and an agreed next-step decision.

What the report contains

  • Current-state workflow and a quantified baseline
  • Pain-point register, each with a process owner
  • Target workflow and what staff will do differently
  • Integration and data-access assessment
  • Deployment options and a costed pilot proposal

04 What we build

Six places a first engagement usually lands.

We integrate the systems you already run. Replacing the CRM, the trading infrastructure or the payment stack is not the opening offer. The model is never the authority that grants a permission or approves a sensitive transaction.

01 · Launch

Knowledge and support

Problem Staff cannot find the current policy for the right entity.

Build A staff assistant that searches approved documents, shows the source, and prepares drafts for review.

Control Permissions and entity boundaries apply before retrieval. Missing evidence is escalated, not invented.

02 · Launch

Document workflow

Problem Onboarding and refresh create rework: incomplete files, unclear owners, expired documents.

Build Intake, extraction with confidence, completeness checks, expiry alerts, review queues and version history.

Control Originals stay original. Broker staff keep the acceptance decision. The model does not repair a date of birth or manufacture evidence.

03 · Launch

Integrations

Problem People copy between CRM, portal, documents and trading systems.

Build A small adapter set: field mapping, scheduled or event-driven jobs, reconciliation and a visible error queue. MCP is used where it simplifies approved tool access. A direct API is used where it does not.

Control A successful read does not silently become permission to change trading or account records.

04 · Foundation

Private AI

Problem The workflow needs a model, and the records must stay inside an agreed boundary.

Build A broker-controlled runtime with retrieval, identity, monitoring and one application. Candidate models are benchmarked before hardware is bought.

Control Inference, OCR, embeddings, logs, backups and support sessions are all in the data-flow review.

05 · Expansion

Management analytics

Problem Spreadsheets disagree, and decisions wait on the argument.

Build Dashboards for onboarding, support, document refresh and backlogs. Natural-language questions only over a governed reporting layer.

Control Queries stay inside authorised data. Definitions and freshness are published. Totals reconcile to the source systems.

06 · Selective

Custom development

Problem A portal, migration or connector is genuinely needed, and an existing product will not do it economically.

Build A tight scope, a working prototype, user validation and milestones. Customer-specific logic stays out of the shared core.

Control Supported systems, data ownership, acceptance and an exit are agreed before the work starts.

The rest of the portfolio, sold only against a funded scope
  • Client service assistant Authenticated account queries, statements and case status inside the broker’s portal. Read-only first. The broker remains the client-facing operator.
  • Compliance operations Policy versions, evidence registers and review tasks. The application assists the compliance function. It does not certify the broker.
  • Finance operations Reconciliation exceptions, payment-status views and commission records. Totals are deterministic. Payment authority stays with the broker.
  • Sales and CRM automation Lead routing, consent records and approved follow-ups. Sold against operational results, not promised deposit growth.
  • Partner and IB portal Agreements, attribution, statements and dispute cases for the broker’s own partners.
  • Trading control tools A later, specialist line. First work is read-only diagnostics or post-trade reconciliation. Language-model output does not authorise a trade.
  • Copy platform software Allocation and reporting software for an authorised operator. Operating a copy-trading service is outside this offer.
  • Broker academy Branded platform courses and assessments, licensed to the broker. Educational material, not a performance claim.
  • Infrastructure and security Monitoring, recovery and access reviews for the systems we deliver. Not a promise to run the broker’s entire estate, and never described as certified before it has been assessed.

05 Private AI, defined

A controlled foundation for one real workflow.

Retrieval-augmented generation pulls approved source material into the answer. A system prompt sets behaviour. Fine-tuning changes model weights. They are different tools. We start with an existing model, prompts and retrieval, and commission fine-tuning only when a measured shortcoming justifies the cost.

  1. 01

    Identity and data

    Authenticate staff. Connect approved records. Enforce entity, role and document permissions.

  2. 02

    Knowledge

    Parse, index and retrieve approved documents. Keep sources, versions and access restrictions.

  3. 03

    Model runtime

    Run the selected model inside the agreed boundary. Benchmark quality, languages, latency and cost.

  4. 04

    Applications

    Search, draft preparation and workflow tasks, with clear actions, review queues and evidence.

  5. 05

    Integration

    Connect CRM, documents and other approved systems. Narrow permissions. Validate every write.

  6. 06

    Operations

    Monitor, update, back up and recover. Named owners, change control and a tested restoration.

On premises

The runtime sits in the broker’s own environment. Patching, capacity, licences and recovery are part of the design, not an afterthought.

Private cloud

A dedicated environment the broker controls. A private cloud is not a server in the office, and we do not describe it as one.

Managed region

We operate the environment in an approved region. Hardware, inference, monitoring and support are priced as themselves.

What “data stays local” must mean

We define exactly which data stays where. The review covers inference, OCR, embeddings, logs, telemetry, backups, support sessions, external screening providers and update mechanisms. Unapproved outbound traffic is disabled and checked. If a KYC provider receives documents, or a backup leaves the premises, the contract says so. An absolute claim that nothing ever leaves would be false, and we will not make it.

06 After a broker is qualified

A twelve-week target, not a promise made before discovery.

Procurement, hardware delivery and access approvals can extend this sequence. A prototype shows feasibility. A pilot tests value with a limited group. Production adds the operating controls. A successful API call is none of those three.

  1. Weeks 1–2

    Contract the discovery

    Scope, access and a baseline. Participants are named before anyone arrives.

  2. Week 3

    Onsite assessment

    The forward-deployed engineer works with process owners. The week ends with an agreed problem and a candidate workflow.

  3. Week 4

    Validate, then sign the pilot

    APIs and the deployment boundary are checked. The sponsor approves the economics and the acceptance criteria.

  4. Weeks 5–7

    Smallest useful application

    Built in a controlled environment. One entity, one team, a defined dataset, a small set of permitted actions.

  5. Weeks 8–9

    Staff test real cases

    Representative work runs beside the existing process. Quality and benefit are written down, including what did not improve.

  6. Weeks 10–11

    Harden

    Training, recovery checks and a production-readiness decision by the technical and operational owners.

  7. Week 12

    Limited rollout

    Acceptance and handover, with a support scope that matches what was actually built.

A first pilot we prefer, once discovery confirms it: an internal policy and support assistant, or document-expiry management with a staff review queue. An illustrative acceptance starting point for a knowledge pilot is a 20% reduction in median handling time without a drop in reviewer-rated correctness. That is a negotiating position, not a result we claim in advance.

07 Indicative fees

Three purchases. Each one stands on its own.

Figures are planning ranges in US dollars, excluding tax, travel beyond the stated allowance, and hardware or cloud the broker owns. The contract fixes the number. A pilot is priced so its cost is covered even if it does not convert.

Discovery

from $6,000

8 days · 5 of them on site

  • Preparation, the onsite week and the written report
  • Process map, baseline, ranked opportunities
  • A costed pilot proposal, or a recommendation to stop
  • 50% on booking, 50% on delivery of the report

Focused pilot

from $20,000

About 25 delivery days · one workflow

  • One integrated application in a controlled environment
  • Evaluation on representative cases
  • Staff training and a handover path
  • 40% at signature, 40% at the demonstration, 20% at acceptance

Managed improvement

from $2,000/month

Up to 2 planned support days

  • Agreed hours, response targets and exclusions
  • Updates and a bounded improvement backlog
  • Not continuous coverage, and not a 24/7 service
  • Change requests and licences priced separately

Broader scope, unfamiliar APIs or additional entities are estimated separately. Deposits are collected before we make material supplier commitments. Fees are not tied to trader losses or to trading performance.

08 Scope

What the first engagement will not include.

The opening pilot stays inside an internal workflow, with controlled access and actions a person can review. Anything below needs its own case, its own operating design and the applicable approvals. It is not added quietly to an implementation contract.

  • Handling or controlling client money
  • Discretionary trading or investment advice
  • Automated onboarding decisions
  • Operating a copy-trading or portfolio service
  • Letting model output approve a permission or a sensitive write
  • Replacing the CRM, trading stack or payments as the first job
  • Describing an unassessed deployment as certified or compliant

09 Who does the work

Founder-led, until the work no longer depends on one person.

The first discovery and the first implementation are led by the founder, with contracted specialists where the job needs them. Buyers can already reach AI tools, and many have capable engineers. The advantage we offer is operating knowledge of a brokerage, connecting systems safely, taking delivery responsibility, and writing down the result. That advantage is earned in the engagement. It is not established by a label.

From the first deployment we separate a reusable core — identity, document ingestion, permission-aware retrieval, evaluation, audit events, deployment — from the adapter that belongs to one broker. A second customer should not mean rebuilding everything. It also should not mean reusing another broker’s records.

10 The first step

Bring one recurring workflow problem.

The first step is a fixed-fee discovery week. You leave with a process map, a baseline and a costed proposal — useful whether or not the pilot goes ahead.