01
Engineering teams
Tickets turned into reviewable steps with proposed edits attached.
Agentic software development · coming soon
AI Code
Codebase-aware AI for planning, editing and shipping faster.
An agentic development workspace that maps dependencies, breaks work into task lists and proposes multi-file edits. For engineering teams, product squads and platform organisations. Coming soon.
- context: dependencies, history, structure
- Repo-wide
- suggested edits, reviewable step by step
- Multi-file
- ask to join the preview
- Coming soon
A moment with AI Code
A ticket arrives. The context engine reads the dependency graph and the change history, splits the feature into five reviewable steps, and proposes the cascading edits across the three files that actually need to change — with the mockup from the design file attached to the first step.
The problem it removes
Assistants that see one file at a time propose edits that break the other nine.
Real work spans the repository, its history and the tools around it — tickets, docs, chat — and that is where an agent has to live.
01 / 06Capability 1
Context engine
Analyses dependency graphs, change history and repository structure so proposals fit the codebase as it is.
02 / 06Capability 2
Task lists
Splits features or tickets into reviewable steps with the files and tests each one touches.
03 / 06Capability 3
Suggested edits
Proposes cascading changes across files, ready to review and apply.
04 / 06Capability 4
Native integrations
GitHub, Jira, Linear, Notion and Slack, so work starts where the ticket is.
05 / 06Capability 5
Multimodal input
Mockups and design files become part of the task context.
06 / 06Capability 6
Ship faster, safely
Every change is a proposal with a diff and a reason; nothing lands without a reviewer.
How it works
Sense. Understand. Decide. Act.
- 01SenseCameras, radar, microphones, environmental and access sensors — chosen for the space, not the brochure.
- 02UnderstandVision and speech models run on an edge gateway in the room, so nothing waits for the cloud and nothing leaves it without consent.
- 03DecideScene rules and safety policies turn detections into decisions: escalate, notify, actuate, or stay quiet.
- 04ActLights, locks, motors, doors, screens, speakers and people — through open protocols and one operations console.
Operations
One console. Every event, with its evidence.
Live status, detections with the clip or image that triggered them, who was notified and what happened next. Per room, per car, per gate, per site.
| Status | Coming soon — preview on request |
|---|---|
| Context | Dependency graph, change history, repository structure |
| Integrations | GitHub, Jira, Linear, Notion, Slack |
| Input | Tickets, docs, mockups, design files |
| Output | Task lists and multi-file suggested edits |
Integrations
Deployments
Where it goes to work.
02
Product squads
Mockups and specs become implementation plans the team can argue with.
03
Platform organisations
Cross-repository changes planned with the dependency graph in view.
Questions
What clients ask first.
When is it available?
AI Code is in development. Send an inquiry to join the preview list and tell us about your stack.
Does it push code on its own?
No. It proposes task lists and edits; people review and apply them.
Which repositories does it support?
Git repositories hosted on GitHub first; others follow.
NT-05 · AI Code
Tell us about your site. We come back with a design and a written quote.
A floor plan, deck plan, yard layout or garden drawing is the best start. Hardware is sourced from factories Outsource China inspects, and delivered on one contract.
Related
Works well with
NT-01Omni-channel front officeAI SupportUnified customer care and live-linked sales documentation.Explore →
NT-02Operational performance analyticsAI ProductionMonitor output, track targets and ask in plain language.Explore →
NT-03Flexible computer visionAI VisionIdentify, localise and highlight any user-defined element.Explore →