Skip to main content
Training Neo lets you refine and improve the AI’s understanding and performance for your specific workflows and agents. When a run should have gone differently, click Train on that run: it opens a conversation with the Neo Support Agent (in Smart mode) with the run’s details attached to the message box as a training card. Describe what should have happened, and Neo investigates the run, proposes a precise edit to the relevant custom instructions, and applies it once you confirm.

​
Why Train Neo?

  • Enhance AI Accuracy: Teach Neo how to better interpret situations and data specific to your environment
  • Tailor Workflow Behavior: Guide Neo to make decisions and take actions that align more closely with your business processes and preferences
  • Improve Automation Outcomes: Get more precise and effective results from your automated workflows by refining the AI’s instructions
  • Iterative Improvement: Continuously make Neo smarter and more helpful through an interactive feedback loop
Train Neo focuses on enhancing custom instructions — for a workflow, the instructions of its actions; for an agent, the agent’s own instructions. Neo shows you exactly what it plans to change and why before anything is written, and it makes a surgical edit rather than rewriting your instructions wholesale. You can always update custom instructions manually in the editor instead.
Train Neo is for runs that should have gone differently — your feedback turns into better instructions. For a run that went right and that you want repeated identically, use the Skillify button on that run instead to capture it as a skill.

​
How It Works

  1. Identify an Execution: Find the past run where the outcome could have been better
  2. Click Train: The Neo Support chat opens with a training card attached to the message box showing the agent, ticket, and run
  3. Describe What Should Have Happened: Type your feedback into the message box — what went wrong, or what Neo should have done instead — and send
  4. Neo Investigates: The Neo Support Agent reads the run’s step-by-step trace, the configuration the run actually used, the ticket context, and its final output, alongside your feedback
  5. Review the Proposed Change: Neo shows you the exact instruction text it wants to add or change, where it will sit, and why — before writing anything
  6. Confirm and Apply: Once you agree, Neo applies the edit to the workflow’s or agent’s custom instructions. Future runs use the updated instructions
Because this is a conversation, you can push back, refine the wording, or ask Neo to take a different angle before anything is applied — and ask follow-up questions afterwards.

​
Step-by-Step Guide to Training Neo

Let’s walk through an example using feedback on a “Triage” workflow run. From the Neo Agent dashboard, go to Workflows. You’ll see a list of your “Triggered Workflows”. Identify the workflow you want to improve (e.g., “Triage”). Click on the “Event History” icon for that workflow to view its execution history.
Accessing Workflow Event History from the Workflows List

​
Select a Specific Event Execution

You’ll be taken to the “Event Executions” page for that workflow. Filter by Ticket ID or Ticket Number to find the specific execution you want to give feedback on, then click the Train button on that run.
Selecting a specific event execution and clicking the Train button

​
Provide Your Feedback

The Neo Support chat opens with a training card attached above the message box, showing which agent, ticket, and run you’re training on. The message box itself asks for your feedback — type specific details about what Neo should have done differently or what it missed, then send. The run details from the card ride along with your message automatically. The more context you provide, the better Neo can learn. Example Feedback: “This ticket should have ‘Printer’ type because it’s related to the HP device in room 2.”

​
Review the Proposed Change

Neo investigates the run — its step-by-step trace, the instructions it ran under, and the ticket — and replies with a concrete proposal: the exact text it wants to add or change in the custom instructions, and the evidence from the run that motivates it. Example proposal: “The triage step set type to None because nothing in the instructions covers printer hardware. I’d add one rule to the Ticket Triage action’s instructions: ‘If the ticket references printer hardware (e.g. an HP device, printer model, or print room), set the type to Printer.’ Want me to apply that?” Review the proposal, and refine it in the conversation if you want it worded differently or scoped more broadly or narrowly.

​
Confirm and Apply

Reply to confirm, and Neo applies the edit. It changes only the targeted instruction text — everything else in your instructions is left untouched — and confirms once it’s done. The workflow will use the updated instructions on future runs.

​
Important Considerations

  • Focus on Custom Instructions: Train Neo refines the plain-English custom_instructions guidance on your workflow actions or agent
  • Manual Updates: You can always manually edit the custom instructions for any action or agent directly in the editor if you prefer
  • Context is Key: Provide clear, specific, and contextual feedback. The better your feedback, the more effectively Neo can learn and improve
  • Not Always an Instruction Fix: Sometimes the right fix is elsewhere — a missing action, a trigger filter, or a missing tool. Neo will tell you when that’s the case and recommend the right change instead
  • Iterative Process: Training Neo is an ongoing process. The more feedback you provide over time, the more aligned Neo will become with your specific operational needs
The more you interact with and guide Neo, the smarter and more helpful it becomes.