ThreeStepTech AI Pricing

Most AI projects stall at the demo. Mine run in production.

Multi-agent systems, LLM integration, and internal tooling for companies that already know what they need and cannot hire anyone who can ship it.

One engineer, no account layer. £500-750/day, €10-25k implementations, €2,500-5,000/mo to run them. Remote across the UK, US and Europe.

Systems in production, not prototypes
Direct with the engineer
Fixed-scope audit, costed build plan

You already know what you want to build. Nobody can build it.

The strategy decks are done. The vendor demos were impressive. Nothing is running. This is the gap between an AI proof of concept and a system your operations team depends on.

The demo worked. Nothing shipped.

The pilot never survived contact with auth, rate limits, error handling, and real data volume.

The role has been open for months

Engineers who have actually shipped agent systems are rare, expensive, and not on the market long.

Agents that can't touch anything

An LLM with no access to your ERP, CRM, or document store answers questions. It does not do work.

Nobody owns it after launch

Model behaviour drifts, costs creep, edge cases surface. Without evaluation and monitoring, quality degrades quietly.

The work is the unglamorous part: integration surfaces, evaluation, cost control, and failure modes. That is what gets a system live and keeps it there.

Five things I build and run

Engineering work, scoped and shipped. Not workshops, not strategy decks.

Multi-Agent Systems & Orchestration

When one model call isn't enough and a chain of them isn't reliable.

Specialised agents with defined responsibilities, shared state, and a control layer that decides what runs, in what order, and what happens when a step fails.

  • Agent decomposition and handoff design
  • Shared memory and state across agents
  • Tool exposure via MCP servers
  • Retry, fallback, and escalation paths
  • Evaluation harnesses on real traffic
See pricing →

LLM Integration Into Existing Systems

When the model has to work inside software you already run.

Connecting language models to your ERP, CRM, ticketing, and internal APIs, including the auth, rate limiting, and schema mapping that pilots skip.

  • API and webhook integration layers
  • Structured output and schema validation
  • Auth, permissions, and audit trails
  • Token cost and latency budgeting
  • Fallback behaviour when the model is wrong
See pricing →

Internal Tooling & Operations Copilots

For the team doing the same judgement call two hundred times a week.

Purpose-built interfaces where a model does the first pass and a person approves, corrects, or overrides. Built for the specific workflow, not a general chat box.

  • Review-and-approve interfaces
  • Triage, routing, and classification tools
  • Drafting and summarisation in-workflow
  • Human-in-the-loop checkpoints
  • Correction data captured for improvement
See pricing →

Document & Data Pipelines With Retrieval

When the answer exists somewhere in twenty years of files.

Ingestion, parsing, chunking, embedding, and retrieval built around your document types and access rules, with measurable retrieval quality rather than assumed quality.

  • Ingestion from file stores, email, and databases
  • Parsing for PDFs, scans, and structured formats
  • Vector and hybrid retrieval strategies
  • Permission-aware document access
  • Retrieval accuracy measured, not assumed
See pricing →

Managed Automation Ops

For systems already live that nobody internally is watching.

Build it and run it. Monitoring, evaluation against real traffic, model and cost tuning, and iteration as your data and the underlying models change.

  • Uptime, latency, and error monitoring
  • Output quality evaluated on live traffic
  • Token spend tracking and reduction
  • Model version migration and regression testing
  • Ongoing iteration against new edge cases
See pricing →

Case study: AIOS

A multi-agent system I built and run. It operates a real business every day. Everything described in the services above exists here first.

Five agents, one memory

Each agent owns a domain and has its own tools and instructions. All five read and write the same persistent store, so context carries between agents and across sessions instead of resetting every conversation.

68 tools over MCP

Capabilities reach the agents as schema-typed tools served by MCP servers, not as hard-coded prompt text. The tool surface changes without rewriting agent logic, and every call is logged.

Five-layer retrieval

Vector similarity, keyword search, recent high-importance facts, the cross-agent activity log, and the current thread — merged into one context block per prompt. It also flags contradictions instead of silently picking a side.

Live integrations

Gmail, Google Calendar, Stripe, GoHighLevel and Telegram. Real inbox, real calendar, real payments. There is no staging environment where a failure goes unnoticed.

The stack

A Next.js dashboard on Supabase, a Node service layer holding the agent runtime and integrations, and a Python bridge for voice. The runtime spawns the Claude CLI as a subprocess through the Agent SDK — it is not a chat wrapper over an API call.

Running daily

In continuous operation for months against live accounts, not a demo instance. It has already survived model version changes, API deprecations, and the edge cases nobody scopes at the start.

src/embeddings.ts — memory similarity, no dependencies
export function cosineSimilarity(a: Float32Array, b: Float32Array): number {
  if (a.length !== b.length) return 0
  let dot = 0
  let na = 0
  let nb = 0
  for (let i = 0; i < a.length; i++) {
    dot += a[i] * b[i]
    na += a[i] * a[i]
    nb += b[i] * b[i]
  }
  const denom = Math.sqrt(na) * Math.sqrt(nb)
  return denom === 0 ? 0 : dot / denom
}

AIOS is not a product and it is not for sale. It is the reference implementation: evidence that this architecture has been built end to end by one person and kept running under real load. Systems like it get built for clients as bespoke internal tooling.

Start with the audit

One fixed-price entry point. Everything after it is scoped from what the audit finds, not from a guess.

Start here

Fixed price, fixed scope, fixed timeline. You keep the output either way.

Consulting Day Rate
£ 500-750 /day

For teams that need embedded engineering or technical direction rather than a fixed deliverable. Booked in blocks, minimum three days.

  • Architecture and technical direction
  • Hands-on implementation alongside your team
  • Code review on existing agent work
  • Vendor and build-versus-buy assessment

Implementation

Scoped from the audit. Ranges reflect integration count and data complexity, not headcount.

Implementation Build
10-25k

Building and shipping the system the audit specified. Typically four to ten weeks, delivered in reviewable increments rather than one handover at the end.

  • Multi-agent systems and orchestration
  • LLM integration into your existing systems
  • Internal tooling and operations copilots
  • Document and data pipelines with retrieval
  • Evaluation harness and monitoring shipped with it
  • Code and infrastructure in your accounts

Running it

Agent systems drift as models and your data change. These are for teams that would rather not staff for that.

Managed Automation Ops
from 2,500 /month

Monitoring, evaluation, and iteration on a system already in production.

  • Uptime, latency, and error monitoring
  • Output quality evaluated on live traffic
  • Token spend tracking and reduction
  • Model migration and regression testing
Embedded AI Partner
5,000 /month

Reserved capacity for companies running several systems or expanding into new functions.

  • Everything in managed ops, across multiple systems
  • Reserved build capacity each month
  • Technical direction on your team's own AI work
  • Priority response and direct access

The audit is the only fixed price on this page, and it is deliberately the only one. Implementation and retainer figures are ranges because scope depends on how many systems have to be touched and how clean the data is — both of which the audit establishes. Day-rate work is available without an audit where you already know what needs building.

How this is different

Three structural differences, not values statements.

No delivery layer

You brief the engineer and the engineer writes the code. Nothing is relayed through an account manager or passed to a subcontracted team you never meet.

Production is the deliverable

A demo is not a milestone. Engagements are measured by what is running against real traffic with monitoring attached, not by what was shown on a call.

You own the output

Code and infrastructure live in your accounts. The audit plan is yours whether you continue or take it to someone else. No hosted black box you cannot leave.

How it works

Three stages. The first one is priced and the second one is scoped from it.

01

Audit

Two weeks mapping processes and integration surfaces. Output is a costed build plan naming what is automatable, what is not, and in what order.

02

Build

Implementation in reviewable increments. Evaluation and monitoring ship with the system rather than being added after something breaks.

03

Run

Handover to your team, or managed ops if you would rather not staff for model drift, cost creep, and new edge cases.

Audit: two weeks. Implementation: four to ten weeks depending on integration count. Remote across UK, US and European time zones, with overlap hours agreed before work starts.

Common Questions

What is the AI Automation Audit?

+

Two weeks, fixed scope, €3,500. It maps your current processes, identifies what is actually automatable with current models, and returns a costed build plan with sequencing and risk. You own the plan whether or not you continue with the build.

Who does the work?

+

One engineer, directly. There is no account manager layer and no offshore delivery team. You talk to the person writing the code. That is a constraint as well as a feature: capacity is limited and scheduling reflects it.

Do you work with UK and US companies remotely?

+

Yes. Engagements run remotely across UK, US and European time zones, with overlap hours agreed at the start. Most implementation work is asynchronous with scheduled review calls.

Our last AI project never made it past the demo. What is different here?

+

Demos fail on the parts nobody scopes: auth, rate limits, error handling, evaluation, cost control, and the integration surface of systems that were never designed for agents. The audit prices those in before anyone writes code, and the build treats them as the work rather than as edge cases.

What does an implementation cost and how long does it take?

+

Implementations run €10,000 to €25,000 depending on scope, typically four to ten weeks. Day-rate engagements are £500 to £750 per day where you need embedded engineering rather than a fixed deliverable.

What happens after launch?

+

Managed automation ops runs €2,500 to €5,000 per month: monitoring, evaluation against real traffic, model and cost tuning, and iteration. Agent systems drift as models and your data change. Handing over a repository and walking away is how they degrade.

Where does our data go?

+

Every build is a separate deployment with its own database. There is no shared tenancy and no pooled data — the system runs in your cloud account, or one provisioned for you and handed over. Documents and internal data are never used to train external models, and data boundaries are agreed in writing before any build starts.

Two ways to start

Start the audit

€3,500, two weeks, fixed scope. A costed build plan you own regardless of what you do next.

Start the Audit
or

Book a technical call

Thirty minutes on what you have tried, what stalled, and whether this is worth either of our time.

Book a Technical Call

Replies within one business day.