AI implementation, architecture and cloud
Expert AI and software engineers who build AI into the systems you run: answers over your own data, Claude Skills and plugins that give AI your team’s tools, agents that finish the work, and AI products taken from idea to live. At a fair rate. The tools on this site are the parts of that work we automated, and they are yours to use either way.
AI implementation
What we build with AI
RAG & knowledge systems
Answers over your own documents, tickets, contracts and data, with citations a reviewer can open. We design access to follow the source system. When the sources do not cover a question, it says so. Retrieval fits the corpus: ranked keyword search where that works better, embeddings and a vector index where they earn their cost.
How we deliver: a test set of the questions your team actually asks, scored before and after every change.
Skills, plugins & MCP integrations
Claude Skills that package your recurring workflows — the steps, the templates, the checks — so the assistant does them the same way every time. Plugins and MCP servers that connect it to your ticketing, databases and internal APIs, with only the permissions each task needs.
How we deliver: each tool scoped and logged, so you can see what the AI did and why.
Agents & workflow automation
Agents that carry a task to the end: document intake, triage and routing, reconciliation, drafting and follow-up. Bounded loops, a human review queue when confidence is low, token budgets that stop runaway spend, and a record of every model call.
How we deliver: automated where it is safe, a person in the loop where it is not — and the threshold is yours to set.
AI product development
From an idea to a live product: the application, the AI features inside it, the cloud it runs on and the pipeline that ships it. We build and run our own — Tally, Stock Tracker, AetherERP and the tools on this site, all live — so we have already worked through many of the hard parts once.
How we deliver: a working slice in front of users early, then iterate on what they actually use.
Architecture & cloud
The ground it stands on
Architecture & modernisation
New systems architected with AI in mind from the start; existing ones modernised to use it without a rewrite you did not need. We decide where a model call belongs and where plain code is the better answer, and design the data paths, integration points and fallbacks so the system still works when a model is slow, wrong or down.
Terraform & IaC delivery
We write the Terraform: modules, environments, state and backends, CI that plans on a pull request and applies on merge, and managed identities instead of keys in config. You get a repository your team can run without us, and the review tooling on this site is pointed at it from day one.
Architecture & security review
An opinionated read on what you already run — public exposure, single points of failure, identity and secret handling, and the configuration choices that cause the 2am page. Findings come with the specific change to make, not a severity label. Start with the free review.
Cloud cost reduction
Where the monthly bill actually goes, and the changes worth making first — instance right-sizing, storage tiers and lifecycle policies, idle and orphaned resources, and commitment coverage. Priced per cloud and region from live pricing data rather than a blended guess.
How an engagement runs
Engagements are deliberately boring to start: we look before we touch anything, and you get the findings before you commit to the work.
How we work
Three ways in
No procurement maze. Most people start at the top of this list and work down only if they need to.
Free
$0
Architecture & AI review
Describe the process you want AI to take on, or send the diagram, the code or the Terraform. You get what we would build, what it would take, and what to avoid. No call required, nothing to sign.
What a free review sends back · illustrative
“Invoice intake: AI reads each invoice and suggests the matching PO; plain rules check totals and tolerances; a person approves anything under 90% confidence. About four weeks.”
Usually back within a few days
Fixed scope
A fair quote, agreed up front
A defined piece of work
A RAG system over your documents, a set of Skills and MCP integrations, an agent taken to production, a new system architected or an existing one modernised, a Terraform rewrite, a cost pass. Scoped and quoted before it starts, so the number does not move.
Typically four to eight weeks
Ongoing
A reasonable monthly rate
AI & software engineers alongside your team
Senior engineers building AI features and the software around them, in your repositories and your review process, on a monthly basis — for as long as it is useful and no longer.
Monthly, cancel with notice
There is no price list because no two scopes are the same. You work directly with expert AI and software engineers at a fair rate, the first review costs nothing, and when a job is small we often just do it. Ask what yours would cost. Engagements run directly and through contract and subcontract partners.
Ask where AI fits — it costs nothing
Tell us the process you want AI to take on, or send the architecture or Terraform you are unsure about. Within a few days you get a short written plan: what we would build or change, what it would take, and what to avoid. No call required. Or try the App Generator and watch it prove its code on real CI.
We reply within one business day.