Gateways

Gateways are here to route tickets to appropriate AI Agent from various ticketing systems such as Servicenow, Github, and more. It is the best way to create jobs in an automated way from external services. When a ticket is created in your ticketing system, 2501 parses and handles it through the jobs system. Gateways can parse tickets in two ways:

• Automatic: tickets are parsed as soon as they’re created in the ticketing system
• Semi-Automatic: tickets are parsed only when @2501 is mentioned

After the gateway parses your ticket and any attachments, it determines how many tasks are required to resolve the issue. For each task, it identifies the best agents based on:

• Host information in the ticket (e.g., “target_machine: UNIX_PROD_442”)
• Nature of the incident (e.g., “A service has timed out”)
• Available agents with explicit specialties (e.g., “AWS Manager”)
• Other ticket details that indicate where/how the incident should be resolved

Once all tasks are mapped to agents, a job is created containing these tasks. The gateway may schedule tasks for execution at a specific date and time based on information found in the ticket. After a job is created, you can interact with it by commenting @2501 in the ticket. See Working with Active Jobs to learn how to add follow-up work or update jobs mid-execution.

​

Managing Gateways

Go to Command Center → Gateways and click the cog icon of the gateway you want to manage.

​

Type

Indicates what type of gateway it is, usually a service where IT Tickets are created. Example: servicenow

​

Active Status

To turn on or off the gateway. Useful if you want to temporarely prevent agents from automatically picking up tickets or create jobs when 2501 is mentioned in the ticket.

​

LLM Models

You will find two options:

• LLM Model: representing the LLM in charge of understanding the ticket and routing tasks to the appropriate agent(s)
• Multimodal LLM Model: the agent that will parse the attachments of your tickets

You can allow a smaller weight here as gateways agents require less compute that actual agents to perform tasks. A model between 70b and 300b will perform well-enough for most routing tasks.

​

Routing Prompt

This prompt specifies how to route tickets to the appropriate agent. It extends the gateway’s system prompt to allow routing of specific ticket types that require special handling or particular agents. Best practice: include something like If there is no exact agent for the specified task on the current host - take the closest. But ensure exact matching for hosts. This emphasizes using the ticket’s information to identify the correct agent while providing a fallback when an exact match isn’t available.

​

Working with Active Jobs

After a gateway creates a job from a ticket, you can interact with it by commenting @2501 in the ticket. The system responds differently based on the job’s current state: Key concept: Running jobs get updated with new requirements. Finished jobs (completed or failed) get new follow-up Job that builds on previous results.

​

Follow-Up Jobs

When to use: After a job completes or fails, you need additional Job that builds on what was done. What happens:

1. New job created - Your @2501 comment becomes the instructions for a new job
2. References previous job - The new job has access to what happened in the original job for context
3. Plan shows history - The execution plan includes a “Previous Job” section so agents understand the background
4. Fresh start with context - Agents start new Job but can reference previous actions and outcomes

​

Updating Active Jobs

When to use: A job is currently running and you need to add requirements or change direction mid-execution. What happens:

1. Incomplete tasks cancelled - Any tasks that haven’t finished are stopped
2. Completed tasks remain - Already-finished Job stays as context and isn’t redone
3. New plan generated - The system creates a fresh execution plan incorporating your @2501 comment
4. Job resumes - Agents continue with the updated requirements, building on completed Job

Important note: Use this when you genuinely need to change direction or add requirements. For simple clarifications or questions, waiting for the agent to ask may be more efficient than restarting the entire job. Common scenarios:

• Investigation reveals additional areas to check
• Requirements expanded during execution
• Different approach needed mid-task
• Priority shifted to different aspect of problem

​

Quick Decision Guide

Not sure which flow applies? Use this table: Quick rule: Is the job still running? → Your comment updates the Job. Is the job done (completed or failed)? → Your comment creates new Job.