Skip to main content

Conversation Agent Refinement

Use Orchestrate copilot Prompt-Tune to When you run this command, make sure to activate an environment. Orchestrate copilot uses the active environment to fetch tools and data, helping you build more useful and relevant instruction
BASH
orchestrate copilot prompt-tune
Command examples
  • Basic Refinement
  • Refinement with Output
  • Refinement with Samples
  • Dry Run Refinement
Refine an existing agent and overwrite the input file
BASH
orchestrate copilot prompt-tune -f input.yaml
Orchestrate copilot interation example The following example shows how you interact with Orchestrate copilot to refine an agent. In this case, you already created and imported the string_reverser tool into your local instance.
BASH
[INFO] - Please provide 3 sample utterances you expect your agent to handle:
 >: reverse "xyz"
 >: flip "abc"
 >: invert "123"
[INFO] - You provided the following samples:
  1. reverse "xyz"
  2. flip "abc"
  3. invert "123"

๐Ÿค– Copilot: Based on your task description, I'll create an initial prompt. 

**Role** - 
You are an agent that can reverse strings according to the given command.

**Tool Usage Guidelines** - 
1. Before you call a tool, make sure you have all the required tool parameters.
2. Do NOT assume any tool parameters
3. Do NOT pass parameters to the tool that are not explicitly defined
4. Do NOT call the same tool multiple times with the same parameters

**How To Use Tools**

- When the user wants to reverse a string, call the string_reverser tool with the string as a parameter.

How would you like the output to be formatted? Should it be a simple reversed string, or would you like any additional information included?

๐Ÿ‘ค You: I want the result formatted as a github markdown table with 2 coulmns. The left column should be the input and the right should be the output. Please include headers on the table

๐Ÿค– Copilot: Based on your requirements, I'll refine the prompt.

**Role** - 
You are an agent that can reverse strings according to the given command.

**Tool Usage Guidelines** - 
1. Before you call a tool, make sure you have all the required tool parameters.
2. Do NOT assume any tool parameters
3. Do NOT pass parameters to the tool that are not explicitly defined
4. Do NOT call the same tool multiple times with the same parameters

**How To Use Tools**

- When the user wants to reverse a string, call the string_reverser tool with the string as a parameter.
- Format the output of the string_reverser tool as a GitHub markdown table with two columns, "Input" and "Output", where the input string is in the "Input" column and the reversed string is
in the "Output" column.

Here's an example of what the output table might look like:
| Input | Output |
| --- | --- |
| xyz  | zyx  |

Are you interested in continuing to refine the prompt, or is this sufficient for your needs?

๐Ÿ‘ค You: That is sufficient

Automatic Agent Refinement (Autotune)

You can automatically refine an agent using feedback from chat sessions. To do this, start by creating an agent and chatting with it. You will see two icons below each agent response which allow you to provide either positive or negative feedback. copilot-feedback-section.png After providing feedback, run the following command to refine an agent using feedback from chat sessions:
BASH
orchestrate copilot autotune
Command examples
  • Basic Autotune
  • Auto Dry Run
  • Autotune Last Chat
Autotune and agent with interactive message selection
BASH
orchestrate copilot autotune -n <agent_name> -o <output_path>.yaml
Orchestrate copilot interation example The following example shows how you interact with watsonx Orchestrate Copilot to refine an agent. Suppose youโ€™ve already created and imported a healthcare management agent, chatted with it, and provided feedback.
BASH
                                                            10 Most Recent Chats                                                            
โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ณโ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”“
โ”ƒ Number โ”ƒ Chat Date                    โ”ƒ Title                        โ”ƒ Last User Message            โ”ƒ Last User Feedback                 โ”ƒ
โ”กโ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ•‡โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”ฉ
โ”‚      1 โ”‚ October 01, 2025 at 12:49 PM โ”‚ Show me healthcare providers โ”‚ Show me healthcare providers โ”‚ ๐Ÿ‘Ž This would be better as a table โ”‚
โ”‚        โ”‚                              โ”‚                              โ”‚                              โ”‚                                    โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
Please enter up to 5 indices of chats you'd like to select, separated by commas (e.g. 1): 1

[INFO] - Your agent refinement session finished successfully!
[INFO] - Agent YAML with the updated instruction saved in file: <output_path>.yaml