Runtime and access state
Check whether the tenant runtime is available and whether access controls permit the intended work.
Agent health
How do I monitor health across hosted AI agents?
Monitor hosted AI agent health by checking tenant runtime state, lifecycle events, scheduled work, recent run outcomes, access state, and usage evidence for each managed runtime. Hermes Hub provides these operator-facing control and observability surfaces for hosted Hermes Agent runtimes; health conclusions should be based on recorded runtime evidence.
A practical health view
Use several signals together rather than treating one status field as a complete health verdict.
Runs and schedules
Compare scheduled markers with actual starts, completions, stops, and recent outcomes.
Usage evidence
Review model and token usage alongside operational activity and policy context.
Health investigation paths
Hosted agent health FAQ
Which signals should operators check first?
Start with runtime and access state, recent run lifecycle, schedule markers, outcomes, and model or token usage.
Does a healthy status prove an agent produced a correct answer?
No. Health evidence describes operational state; answer quality requires the applicable evaluation and review process.
Where are hosted Hermes Agent runtimes managed?
Hermes Hub is the control plane for tenant lifecycle, policies, schedules, releases, runs, and operational evidence.
Design an agent health view
Discuss the runtime, lifecycle, schedule, access, and usage evidence your operations team needs.
Architecture conversation
Tell us what your team needs to control
Share your deployment boundary, number of agents, work surfaces, and governance requirements. We will reply by email to arrange a focused technical discussion.
Email the Bewize teamThis opens your email application. Read our Privacy Policy.