Lower noise
Routine operations collapse into milestones instead of individual alerts.
The short answer
Speak decisions and state changes; compress the rest.
A useful agent notification contains a source, a state change, and an action. “Checkout tests failed in the payments session; three snapshot mismatches need review” is useful. “Agent used a tool” is usually not.
Voice raises the cost of noisy notifications because audio interrupts the room and unfolds over time. Default to fewer, richer updates and let users opt into more context when they are actively listening.
Clear urgency
Questions and failures sound different from progress.
Actionable speech
Every interruption tells the listener what to do next.
Questions and approvals.
Speak immediately when the agent cannot continue without a human decision. Include the session, the decision, and the safest available options.
Blockers and failures.
Report what failed, whether the task stopped, and the most relevant evidence. Avoid dumping an entire stack trace into speech; keep the detailed log available on screen.
Useful
“Checkout tests failed in the payments session; three snapshot mismatches need review.”
Noise
“Agent used a tool.”
Completion and verification.
Say what changed, which checks passed or failed, and what remains unverified. Completion language should never imply a merge or deployment occurred unless it actually did.
Milestones and routine progress.
Aggregate routine activity into periodic milestones. In Focus mode, suppress it. In Companion mode, provide enough context to feel present without narrating every tool call.
Notification template
Build every spoken update from three parts
Source Name the session or task in language the listener can distinguish.
State change Explain what became true: waiting, blocked, failed, passed, or finished.
Next action Say whether the listener must decide, inspect, retry, or simply note the update.
Questions
Frequently asked questions
Should every tool call create a notification?
No. Tool calls are usually implementation detail. Aggregate routine activity and speak material state changes.
What makes a voice notification actionable?
It identifies the session, explains what changed, communicates urgency, and gives the next decision or review step.
How do Heard listening modes differ?
Co-pilot gives short updates while you are at the screen, Companion gives fuller narration when you step away, and Focus stays quiet until an agent needs you: questions, approvals, blockers, and failures. Routine progress and normal final results stay quiet.
Ready when your agents are
Hear the work without watching every screen.
Start with the full Heard Power experience for 14 days. No card required. The open source engine remains free.
Download Heard for Mac macOS 14 or later · Claude Code and Codex supported