Build software with AI — without giving up sovereignty
Circuit is the AI build-platform for all of you that care where data goes. Describe what you want; AI agents plan and build it as governed tasks, inside your sovereign Stackship instance, on the models and providers you choose. You decide where inference runs, and policy enforces it.
- Your choice of model and provider
- Human-in-the-loop on every sensitive step
- Signed, auditable evidence trail
Circuit — project overview
Circuit runs on Stackship
Circuit is the AI build layer. Stackship is the sovereign control plane underneath. Circuit produces code, infrastructure and reviews; Stackship governs them with policy, audit, RBAC and compliance.
Circuit — the AI build layer
Owns the conversation, planning and agent runs. Turns intent into governed tasks and a reviewable, evidence-grade result.
Stackship — the sovereign platform
Platform as a Service primitives, policy engine, audit ledger, identity, deploy and local LLM inference. Where everything runs and where the rules live.
Platform capabilities like policy, compliance and the audit log live in Stackship. Circuit surfaces them as live views that deep-link into the platform.
From an idea to software
A guided loop, governed end to end.
- 1
Describe
Tell the planning agent what you want in plain language. It reads, asks follow-ups and proposes a plan, and never touches any code.
- 2
Plan → Tasks
Approve the plan and Circuit compiles it into concrete tasks of type build, infrastructure or review.
- 3
Runs on Stackship
Each task runs the agent workers inside your sovereign boundary, leveraging the model you chose, behind policy gates — streamed live.
- 4
Review & merge
Circuit never pushes code directly into source code repositories, it always uses PR/MR with its review cockpit. A human reviews and merges the code.
- 5
Evidence
A signed, hash-chained evidence package is produced and mapped to your compliance controls, ready for audit at all times.
See Circuit work
From a one-line idea to a governed, audited change — here's the actual product.
Describe what you want and set the boundaries
Pick a project type — web app, integration, agent, data platform — then scope it: the goal, who it's for, what it must include and what's explicitly out of scope. Clear boundaries keep the planning agent on track.
- A plain-language brief, no ticket-writing
- Tasks and conversations stay scoped to the project
- The planning agent proposes a way forward
Every agent run, streamed and logged
Each task runs as a governed job with a named agent and a model you chose. Follow the run log live — model calls, plan updates, shell commands — ask the copilot what's happening, and open “What the AI saw” for the exact prompt behind any step.
- Live run log you can pause and answer mid-run
- Token usage and changed files per task
- A signed evidence package attached to the run
A local model pool, inside your boundary
Run tasks against a curated pool of OpenAI-compatible models on your own endpoints. Mark one as the planning model, tag each by capability, and let the planner pick per task — or choose yourself. You own the model and endpoint catalog.
- Models and endpoints you control
- Per-task model choice, or auto-selected by the planner
- Capability tags: infra, build, review
Everything regulated delivery needs
Traceability, policy and human approval are woven through the whole product.
Conversational planning
Describe what you want and a read-only planning agent turns it into a concrete plan of tasks. Nothing is built until you say so.
Tasks run as governed ephemeral workers
Every task compiles to an ephemeral agent worker that only pulls in what is needed to execute the task at hand, using your chosen model.
Live agent runs
Watch every step — plan, policy, edit, tool — stream in real time. Pause, or answer the agent's blocking questions mid-run.
“What the AI saw”
Inspect the exact prompt and context behind any model call. PII and secrets are masked by PII_GUARD before they ever reach the model.
Review cockpit
File-by-file diff with line comments and the policy verdict. A human merges in your own source code provider — Circuit never holds merge rights.
Signed evidence packages
Every task yields a hash-chained, exportable evidence package (SHA-256) mapped to NIS2, GDPR, MSBFS and ISO 27001 controls.
Built sovereign by design
The five principles Circuit never compromises.
Sovereignty
You choose the models and providers — any OpenAI-compatible endpoint. Policy decides which endpoints agents may reach, so you can keep inference fully inside your boundary or point it at a sovereign provider you trust. You stay in control of where data goes.
Human-in-the-loop
Agents can't complete sensitive actions — merge, production infra — without human approval. Multi-step approval with quorum and separation of duties.
Total traceability
Every action by a human, agent or policy is written to an immutable audit log. Each task can produce a signed evidence package for audit.
Compliance built-in
NIS2, GDPR, MSBFS and ISO 27001 are first-class objects: framework → control → evidence, traceable in real time.
Full-stack
Build complete systems — frontend, backend, database and infrastructure — all provisioned through Stackship primitives.
Made for regulated environments
Framework → control → evidence, traceable in real time.
Questions
The things regulated buyers ask first.
Where you decide. Circuit is model- and provider-agnostic: you pick the OpenAI-compatible endpoints, and policy controls which ones agents may reach. Lock it down to models inside your boundary for zero egress, or allow a sovereign provider you trust — either way it's your choice, enforced by policy and recorded in the audit log.
Join the Circuit early-access pilot
We're working with a small group of public-sector and regulated organisations to shape Circuit before general availability.
Who it's for
- Public-sector bodies — agencies, regions, municipalities
- Regulated industries with sovereignty or NIS2/GDPR requirements
- Teams that want AI-assisted delivery on models and infrastructure they control
- Organisations already running — or planning to run — Stackship
What you get
- Hands-on access to Circuit on a sovereign Stackship boundary
- A direct line to the team building it — your feedback shapes the roadmap
- Help mapping your compliance frameworks (NIS2/GDPR/MSBFS/ISO) to evidence
- Early-access pricing
Circuit is in active development. Pilot scope and availability are agreed per organisation.
Request a demo
Tell us what you’d like to see and leave your email — we’ll be in touch to set up a demo.
What are you interested in?
Circuit runs on Stackship, so it’s included automatically.
No commitment — just a conversation and a walkthrough.