Services

Strategy, design & AI systems, on engineering that holds.

First-principles thinking in design and software engineering is needed more now, not less. Sixteen years of building products grounds the AI hype in pragmatism. AI does the acceleration; people drive the judgement.

Agentic AI

Agentic systems for your team, your customers, and the teams that build on you.

Knowledge search across internal systems RAGVector searchPermission-aware retrieval
Workflow automation, routing and escalation Workflow graphsTask routing
Review queues and approval steps Review queuesApproval gates
Scheduled digests and operational reporting Scheduled runsSlack
Document intake and structured extraction Extraction schemasValidation

A faster path to proof

Start on a working foundation. Move to yours when the product is proven.

We bring the production-tested, multi-tenant foundation behind our own products, so the MVP effort goes into your agent, your workflows and the experience around them — not rebuilding the same platform plumbing.

Ready foundation Production-tested starting point
Tenant isolation, identity, agent profiles, sessions and memory, knowledge, tools, sandboxes, tracing, evaluations, quotas and deployment.
Working MVP Your agent, workflow and product experience
We put the engagement into the decisions, integrations and interface unique to your business.
Your stack Transition without starting again
Move into your cloud account, preferred frameworks and operating model when the product shape is proven.

Designed for transition from day one: agent logic, typed tool contracts, schemas, evaluation sets and product interfaces travel with the product.

Org AI Transformation

Readiness, training, and a way of working that survives the handover.

Advisory & Readiness

Where AI actually fits in how your organisation works today, and what has to change before it holds.

See how we implement this

Workshops & Training

Sessions that leave your team with a decision they can defend, and the working language to keep making them.

See how we implement this

Installation & Maintenance

The way of working installed in the systems and agent environments your team already uses, and kept running after we hand it over.

See how we implement this

Explore the AI Product Decision Workshop

Web Applications

The product your customers see and the one your team lives in, built from the same foundations.

Rich front-end applications with delightful UX Component frameworksTyped front-endsModern build tooling
Marketing sites, storefronts and content platforms Static renderingSEOHeadless CMSCommerce
Onboarding, account and profile flows Progressive formsValidation
Real-time and collaborative interfaces StreamingOptimistic updates
Analytics and instrumentation Product analyticsEvent schemas
Responsive behaviour down to small screens Fluid typeContainer queries

Backend Systems

This layer should be invisible. Keeping it that way is the work.

APIs with versioned, documented contracts Application frameworksRESTOpenAPI
Data models and safe migrations Relational DBDocument DBGraph DB
Service architecture sized to the team Modular monolithsMicroservicesEvent-driven
Multi-tenant models and tenant isolation TenancyScoped queries
Query performance and derived views Materialised viewsIndexingCaching
Typed clients generated from the schema OpenAPIGenerated clients

Authentication, authorisation and scoped access OAuthPolicy-based authorisation
Encryption and sensitive-data boundaries Encryption at restData boundaries
Audit trails and tamper-evident records Audit logsImmutable records
Deployment pipelines and release automation CI/CDProgressive rolloutRollback
Infrastructure as code across major clouds AWSGoogle CloudAzureContainers
Observability, alerting and recovery paths Structured logsMetricsHealth checks
Security review inside the pipeline Static analysisDependency scanning

Mobile Applications

Native where it matters, cross-platform where it doesn’t.

Fully native applications for iOS and Android SwiftSwiftUIKotlinJetpack Compose
Cross-platform applications from one codebase React NativeNative modules
One design system across web and native Shared tokensThemed components
Native navigation, gestures and platform conventions NavigationHaptics
Accessibility on touch surfaces Screen readersDynamic type
Web content embedded in native shells WebView bridgeNative handoff

Offline behaviour and background sync Local cacheConflict resolution
Push notifications and deep linking Push notificationsDeep links
Camera, media capture and uploads Media captureResumable uploads
On-device inference, with data that never leaves the phone Core MLML KitNeural engine
Vision compute: detection, OCR and scene understanding VisionOCRReal-time detection
Biometrics, secure storage and permissions BiometricsSecure storage
Location and background tasks GeofencingBackground tasks

Strategy, Research & Design

Deciding what to build, by building enough to find out.

User and stakeholder research InterviewsField studies
Jobs, journeys and service mapping Journey mapsService blueprints
Concept definition and product strategy Concept testingPositioning
Prioritisation and roadmapping RoadmapsSequencing
Success measures agreed before the build MetricsSuccess criteria

Engagement

Join at any stage.

Some engagements start with a discovery question and run through to an operating system. Others start with a system that already exists and a decision inside it that has to become dependable.

AI accelerates our process, but it does not replace judgment. We use it to explore, simulate, document and test — the team stays accountable for the decisions.

Strategy, design & AI systems, on engineering that holds.

Agentic systems for your team, your customers, and the teams that build on you.

Start on a working foundation. Move to yours when the product is proven.

Readiness, training, and a way of working that survives the handover.

Advisory & Readiness

Workshops & Training

Installation & Maintenance

The product your customers see and the one your team lives in, built from the same foundations.

This layer should be invisible. Keeping it that way is the work.

Native where it matters, cross-platform where it doesn’t.

Deciding what to build, by building enough to find out.

Join at any stage.

Let's find the work AI should be doing in your organization.

Tell us about the work.

Strategy, design & AI systems, on engineering that holds.

Agentic systems for your team, your customers, and the teams that build on you.

Internal agents Agents your own team works with — in chat, in admin tools, and inside the systems that already hold your process.

Customer-facing agents Agents that act inside your product, where the person on the other end is your customer and a wrong answer is public.

Developer platform agents Agents and primitives other teams build on — exposed as tools, servers and packaged procedure rather than a product surface.

Readiness, training, and a way of working that survives the handover.

Advisory & Readiness

Workshops & Training

Installation & Maintenance

The product your customers see and the one your team lives in, built from the same foundations.

Customer-facing products The app your users log into, where the state is complicated, the permissions matter, and somebody downstream depends on the screen being right.

Internal tools & admin The console your team runs the product from — review queues, support views, and the operations nobody outside ever sees.

Design systems & foundations The shared layer both sides are built from, so a change lands once rather than in every screen that copied it.

This layer should be invisible. Keeping it that way is the work.

APIs & data models The contract everything else depends on — versioned, documented, and hard to use wrongly. We have run our own multi-vertical SaaS platform since 2018, so this is a layer we maintain rather than just ship.

Pipelines & integrations The work that happens after the request returns — jobs, events, and the third-party systems you do not control.

Security, DevOps & operations Correctness, auditability and recovery are the product here rather than the plumbing — through how it ships and how it runs. We build for the on-call rotation, not the demo.

Native where it matters, cross-platform where it doesn’t.

Apps & interfaces A personal device, used on the move — which changes what the app has to survive, and how it is built. Sharing its design system with the web product rather than forking from it.

Device & platform capabilities What a phone can do that a browser cannot, and the states an app has to survive — offline, backgrounded and interrupted.

Release & quality Getting it into the stores and keeping it healthy there, where a bad build is not a rollback but a review queue.

Deciding what to build, by building enough to find out.

Research & strategy Understanding the people who use the product and the decisions the business has to make, before anything gets built. Usually the first engagement, and the reason the ones after it are shorter.

Design & prototyping Making the decision concrete enough to test — prototypes built to answer a question rather than decorate one.

Let's find the work AI should be doing in your organization.