Operating system
Platform
An operating system for AI.
AI operating system
Platform is an operating system for AI.
Agents, tools, memory, permissions and controls that let AI operate around the work your organisation already does.
Applied intelligence for real organisations
Linear Horizon understands how work actually happens, identifies the points of friction, and builds intelligent systems that turn insight into action.
We work with organisations that need AI to do real work, not sit in a demonstration. That means training your people, designing the system properly, and taking it into production.
Experience in the work
01
Training
More than twenty years of professional technology training — experience in the work, not the age of the company.
02
Courses
Hundreds of technical courses delivered for engineering teams and large organisations.
03
Engineering
Deep software engineering and architecture experience, including senior and principal work.
04
AI
A formal academic background in Artificial Intelligence.
05
Production
Hands-on delivery of production systems, including applied AI.
What Linear Horizon does
Two complementary sides of the same practice. You do not have to choose one or the other.
Services
Work with Linear Horizon directly to develop capability, design AI systems and deliver them into production.
Products
Linear Horizon Platform is an operating system for AI. Specialist applications apply it to analysis, research, strategy, growth and customer service.
Platform
An operating system for AI.
Stack
Agents that analyse. Ask open-ended questions of your data.
Solve
Agents that reason. Start a run. The tree is the ledger.
Wargame
Agents that strategise. A machine that can predict the future.
Funnel
A local agentic CRM. Your data never leaves your desktop.
Callcenter
Agents that serve customers. One conversation, across every channel.
Query
Agents that investigate usage. Understand what users actually do.
Chat
Agents you can talk to. A conversation on top of your agents.
Linear Horizon Products
Linear Horizon Platform is an operating system for AI. Specialist products then apply that system to analysis, research, strategy, growth and customer service.
Figure · Product system
Operating system
Platform
AI operating system
Platform is an operating system for AI.
Agents, tools, memory, permissions and controls that let AI operate around the work your organisation already does.
Applications
Stack
Analysis
An agentic data analysis system that investigates open-ended questions, tests hypotheses and produces a structured analytical deliverable.
Solve
Research
An unattended problem solver: each tree node is axioms, reasoning and an evaluating agent. A run wakes high-scoring or interesting nodes to ideate, Horn-generate or GA-mix.
Wargame
Strategy
An agentic strategy system that models actors, incentives and possible responses, then simulates how they interact — a machine that can predict the future.
Funnel
Growth
A desktop agentic CRM that researches organisations, qualifies opportunities and drafts outreach locally. Your data never leaves your desktop.
Callcenter
Customer Service
Resolve customer needs across voice, messaging and email, with intelligent human handoff when judgement matters.
Query
Analytics
Privacy-conscious product and website analytics, where agents investigate the numbers rather than leaving you to read another dashboard.
Chat
Interface
A conversational interface to your agents — streaming answers, visible working and voice, on top of the Linear Horizon Platform.
How the products differ
| — | PlatformAct | StackUnderstand | SolveSolve | WargameDecide | FunnelDiscover | CallcenterServe | QueryMeasure | ChatConverse |
|---|---|---|---|---|---|---|---|---|
| Purpose | An operating system for AI | Investigate your data | Search programmes of attack on a hard claim | Predict the future | Local agentic CRM | Serve customers | Measure product usage | Talk to your agents |
| Input | Events, requests, knowledge and tools | Open-ended questions and organisational data | A conjecture, modelling question or precise statement | Strategic problem and actor model | ICP and market signals | Voice, messaging, email and customer context | Product and website events | A question, an agent and a conversation |
| Agentic process | Orchestration, tools and workflows | Hypothesis generation and testing | Choose, expand, evaluate | Actor modelling and simulation | Discovery, research and qualification | Understand, retrieve, act, resolve or hand off | Instrument, measure and investigate | Route, retrieve, act and stream |
| Output | Agentic workflows and actions | Evidence, analysis, visualisations and presentations | A scored tree of attack programmes | Scenario distributions and strategic options | Evidence-backed opportunities | Resolution, action or context-rich human escalation | Metrics, cohorts and investigated findings | A streamed answer with its working shown |
| Channels | Events, APIs and operational interfaces | Analytical environments and presentations | Research chat, node agents, run controls | Strategic briefs and simulation outputs | Desktop app; local CRM data | Voice, WhatsApp, SMS, email, Teams, Slack, Salesforce | Dashboards, event API and MCP | Web chat, voice and token streaming |
| Human role | Oversight and escalation | Review and interpretation | Start, pause, stop; review scores and what remains open | Assumption review and strategic judgement | Approval and relationship building | Judgement, takeover and the work that still needs a person | Interpretation and prioritisation | The person asking, and taking over when needed |
Platform
Act
Stack
Understand
Solve
Solve
Wargame
Decide
Funnel
Discover
Callcenter
Serve
Query
Measure
Chat
Converse
Services · Train. Advise. Build.
We teach AI, design it, build it, and provide the technology to run it.
TRAIN
Build AI capability inside your organisation.
Technical training led by practitioners, grounded in real engineering experience.
ADVISE
Work out what to build — and how to build it properly.
Strategy, discovery and architecture from people who still work with the underlying technology.
BUILD
Take AI into production.
Agents, RAG, intelligent applications and bespoke AI systems designed around real organisational requirements.
Start where you need us
Book a programme, bring us in for architecture, commission a system, or deploy a product. You should not be forced into a single path — the capabilities reinforce each other.
01
TRAIN
Teams understand the technology
02
ADVISE
Identify opportunities and architecture
03
BUILD
Implement bespoke systems
04
PRODUCTS
Accelerate using reusable Linear Horizon technology
Four layers
01
Understand AI
Build the language and judgement your team needs before it designs a system.
02
Decide what to build
Identify where AI is useful, what the architecture should be, and what good looks like.
03
Deploy working systems
Take a design into production against real data, interfaces and ownership.
04
Accelerate with products
Use existing Linear Horizon technology where the problem already has a product shape.
You might start with
Train
Practitioner-led training for teams who have to ship. A catalogue covering foundations, engineering, RAG, agents and architecture — shaped to your organisation, not a public timetable.
TrainingSelected capabilities
Generative AI and LLMs
Applied AI for engineers
RAG and agentic RAG
AI agents and workflows
AI architecture
Workshops and discovery
Model integration
Production systems
Practice
A specialist applied AI engineering company. Training, consultancy, production systems and proprietary agentic technology — led by people who still do the work.
Linear Horizon is both a training company and an engineering practice. The same people who design and build AI systems also teach how they work — and provide the technology used to run them.
AboutPrincipal
Nicholas Johnson
AI architect and software engineer
The work is led from practice: architecture, engineering, and the teaching of both.
Talk to us
From first understanding to a working production system.
Tell us about your organisation and the problem. We can help with training, architecture, delivery, a product deployment — or the path that actually fits.
Engagement notes — forthcoming
Selected work will appear here when it can be discussed. Until then, we are happy to talk about it directly.