Agents

An agent is the AI you've connected to withHuman. It could be helping you write code, handling customer support, or doing something else entirely. You give it a name so you can recognise it when a request comes in.

Agent instances

You can run the same agent in more than one place. Each connected copy is an agent instance. That might be the one on your laptop, the one on a server, or the one running an automated job.

Imagine your support agent runs on two servers. That's one agent with two instances. Both do the same job, but you can tell them apart.

Or imagine an AI SRE agent that spins up a new copy in the cloud for each incident. You'd have one agent, and each new copy would be an instance of it.

flowchart TD
    agent["Support agent"] --> first["Instance on server 1"]
    agent --> second["Instance on server 2"]

Agent pipelines

Grouping agents like this allows you to organize instances easily. Each agent has its own pipeline, so you can define rules once for a particular class of agent, then just add new instances as you need them and they automatically have the same rules applied.

flowchart LR
    subgraph requests["Requests from instances"]
        incident1["Incident 1 instance"]
        incident2["Incident 2 instance"]
        server1["Server 1 instance"]
        server2["Server 2 instance"]
    end

    incident1 --> sre["AI SRE agent"]
    incident2 --> sre
    sre --> srePipeline["AI SRE approval pipeline"]

    server1 --> support["Support agent"]
    server2 --> support
    support --> supportPipeline["Support approval pipeline"]