What needed solving
AI agents now call real tools: they push code, run shell commands, query databases and read files. Most teams have no single place that decides which of those calls an agent may make, stops a dangerous one before it runs, or keeps a record they could show an auditor afterwards.
How we're building it
Every agent tool call passes through one pipeline: an emergency kill switch, a per-agent tool allow-list, policy rules, governed operations, budget limits and, where needed, human approval. Governed operations are 19 named dangerous actions such as force-push, DROP TABLE, rm -rf and reading secrets, each mapped to the OWASP LLM Top 10 and OWASP Agentic, and to MITRE ATLAS where a technique applies. Every decision, whether allowed, held for approval or blocked, is written to a tamper-evident evidence ledger with downloadable receipts. An MCP proxy brings any MCP server under the same rules, alongside local posture scanning, compliance-style reports and role-based console access.
What we learned
Built test-first with AI-assisted engineering: 980 automated tests across six suites as of 6 October 2026. Governance only earns trust when every decision can be replayed: the ledger and its receipts matter as much as the block itself.
What we are testing next
Can AI-assisted risk scoring catch the dangerous tool calls that pattern rules miss, without holding up normal work?
Where it is
- Sep 2026Gateway pipeline, governed operations and evidence ledger built test-first
- Oct 2026Invite-only beta console and MCP proxy; Claude Code governed live through a hook that checks every Bash, Write and Read before it runs
- NextAI-assisted risk scoring, then the private beta opens
Private beta opening soon. The screenshot shows sample data.

- R-039Vantage: Health Operations Twin
A geospatial digital twin for hospital operations, from a national 3D map of hospital estates down to room-level floor plans, queried in natural language.
- R-025Connected Highways
AI planning and risk copilots for major highways programmes.
- R-026CivilMap - Construction Command Center
Real-time visibility across complex infrastructure programmes.
