What LightHouse is
LightHouse manages your agents, models, approvals, access and billing, and reports on them in six areas. It runs on the Atlantic Agentic Engine, which runs in your own cloud account, on your own servers, or in an account Atlantic runs for you.
LightHouse
Section titled “LightHouse”LightHouse is where your people sign in. From it they:
- see every agent, what it is doing now, and every run it has made;
- approve or reject an agent’s output before it counts;
- pause an agent, set its spending cap, or grant a standing pre-approval;
- choose where agents run and which models they may use;
- connect sources, issue API keys and decide who may sign in;
- see cost and usage, set limits, and pay.
Each client has its own tenant, at its own address: https://<tenant id>.atlanticagenticlabs.com. You sign in at platform.atlanticagenticlabs.com with your tenant ID, through your own identity provider. See Tenants.
Everything you can see in LightHouse you can also read from the API and, as read-only tools, from the MCP server.
The engine beneath it
Section titled “The engine beneath it”The Atlantic Agentic Engine runs your agents. It runs where you choose: your AWS, Azure or Google Cloud account, your own servers with Docker, or Atlantic-hosted. It holds:
- the gateway, the only thing that calls a model, where spending caps, the kill switch and the tool gate are enforced in code (The gateway);
- the orchestrator, which runs each agent under its agent card;
- your knowledge: the sources it reads and the index it builds, in your account (Knowledge bases);
- a content reader, so LightHouse can show your content in place without copying it;
- a command channel, so a person’s decision in LightHouse reaches the agent (Handlers).
The engine sends LightHouse operational telemetry: counts and timings, never content. See The telemetry contract and Data sovereignty.
The six areas
Section titled “The six areas”| Area | What it shows |
|---|---|
| Cost | Spend by agent, task and outcome, against budgets |
| Token optimisation | Model choice, cache use, wasted calls, and cost per outcome over time |
| Security and context | Blocked and screened requests, attempts to instruct the model, stop switches, the access audit, and the knowledge each answer was grounded in |
| Reinforcement | Evaluations, approvals and human edits, fed back so agents improve with each release |
| Insights | Time saved, throughput, and value against the agreed baseline |
| Compliance | The evidence pack, the audit trail and reports for a regulator |
Every saving LightHouse shows is estimated, and says so. Cost and token optimisation shows how each figure is calculated, and how to reproduce it.
Where to start
Section titled “Where to start”| You are | Start with |
|---|---|
| Evaluating LightHouse | This page, then Concepts and Security |
| An architect | Clouds, The telemetry contract and Data sovereignty |
| A developer | The Quickstart, then the API and MCP |
| Reviewing security or compliance | Security, Data sovereignty and Trust |
What is on this site
Section titled “What is on this site”Everything on this site is true of what is built. Anything not built yet is marked Coming, with no date promised.