PromptisePromptise
PlatformSoonEnterprise
DocsGitHub
Talk to usGet started
Use cases/Event-driven operations
Use case · Operations

Event-driven operations.

An agent starts the moment something happens: an alert, a failed payment, a new file.

The first response no longer waits for someone to notice. Routine steps are done in a minute. Changes still wait for a person.

Watch it workTalk to our engineers
How it works

Step by step.

Press play, or click through it yourself. Try the switch above the drawing.

Try it · What happens
alertagentlogsrecent deploysrunbookon-call engineerteam chat
waiting

01The agent waits. While nothing happens, it costs nothing.

01 / 06
Where it's used

One idea, many industries.

  • 01EngineeringAn alert fires. The agent pulls the logs and the runbook before anyone is at a laptop.
  • 02PaymentsA failed payment starts a friendly follow-up with the customer.
  • 03LogisticsA delayed shipment starts a new delivery plan and a note to the customer.
  • 04SecurityA suspicious login gets checked against recent activity, with a summary for the team.
HarnessInterfaceAgent
How Promptise makes it work

All three parts, working together.

  • AgentSmart and reliable.Investigates, follows your runbook and writes the report.
  • InterfaceAny system, agent-ready.The agent reads freely. Changes wait for approval.
  • HarnessAutonomous, under control.Wakes agents from webhooks, events and files. Unsigned events never start a run.
In code

A peek at the code.

  1. 01A signed webhook wakes the agent.
  2. 02Calls without a valid signature are refused.
  3. 03Only firing alerts start a run.
Read the docs
on_alert.pypython
from promptise.runtime import ProcessConfig, TriggerConfig on_alert = ProcessConfig(    model="openai:gpt-5-mini",    instructions="Investigate the alert. Follow the runbook.",    triggers=[        TriggerConfig(            type="webhook",            webhook_path="/alerts",            hmac_secret=WEBHOOK_SECRET,            filter_expression="payload.status == 'firing'",        ),    ],)
A real project you can run
high error ratecheckout-serviceincident agenterrors %v2.14.0fixedrunbookapprovalroll backcheckout-serviceto v2.13.4?yesnoon-call
Engineering

On-call incident agent

An alert wakes the agent, it investigates and follows the runbook, and risky fixes wait for a person.

A reference application with local stand-ins for the outside systems.

See the projectGet the code
Next steps
  • The frameworkGet startedOpen source. Build your first agent in a minute.
  • Our engineersTalk to our engineersWe design and build it with your team.
  • Next use caseAgent teamsAgents that work a case together.
Promptise - AI Framework LogoPromptise

The full-stack framework for agentic systems. Build with the framework. Run it on the platform. Launch it with our engineers.

pip install promptise

[01] Product

  • Framework
  • Platform (coming soon)
  • Enterprise
  • How it works
  • Contact

[02] Framework

  • The Agent
  • The Interface
  • The Harness

[03] Resources

  • Documentation
  • GitHub
  • Why Promptise
  • Use cases
  • Roadmap
  • Guides
  • Learning Paths
  • Questions

[04] Company

  • About
  • Terms of Service
  • Privacy Policy
  • Cookie Policy
  • Subprocessors

© 2026 Promptise by Manser Ventures. All rights reserved.

hello@promptise.com