Coplit examples

apps/rowboat/app/lib/copilot/copilot.ts

@@ -9,7 +9,7 @@ import { PrefixLogger } from "../utils";
 import zodToJsonSchema from "zod-to-json-schema";
 import { COPILOT_INSTRUCTIONS_EDIT_AGENT } from "./copilot_edit_agent";
 import { COPILOT_INSTRUCTIONS_MULTI_AGENT } from "./copilot_multi_agent";
-import { COPILOT_MULTI_AGENT_EXAMPLE_1 } from "./example_multi_agent_1";
+import { COPILOT_MULTI_AGENT_EXAMPLES } from "./examples";
 import { CURRENT_WORKFLOW_PROMPT } from "./current_workflow";
 import { USE_COMPOSIO_TOOLS } from "../feature_flags";
 import { composio, getTool } from "../composio/composio";
@@ -24,7 +24,7 @@ const WORKFLOW_SCHEMA = JSON.stringify(zodToJsonSchema(Workflow));
 
 const SYSTEM_PROMPT = [
     COPILOT_INSTRUCTIONS_MULTI_AGENT,
-    COPILOT_MULTI_AGENT_EXAMPLE_1,
+    COPILOT_MULTI_AGENT_EXAMPLES,
     CURRENT_WORKFLOW_PROMPT,
 ]
     .join('\n\n')

apps/rowboat/app/lib/copilot/examples/example-1-meeting-assistant.ts

@@ -0,0 +1,225 @@
+export const EXAMPLE_1_MEETING_ASSISTANT = `
+### Example 1: Meeting Assistant with Multi-Agent System
+
+**User Request:**
+Build me an assistant that can view my meetings on google calendar for a mentioned time period, do research on the participants and then give me a summary of the meeting sent to my email.
+
+*call searchRelevantTools*
+searchRelevantTools output:
+<returns the tool data for Google Calendar, Tavily, and Gmail that can copy in your output when you need to add tools>
+
+**Copilot Response:**
+
+I'll break down your requirements into a multi-agent system and create the necessary agents and tools. Here's my plan:
+
+**Plan & Agent Decomposition:**
+1. Hub Agent: Orchestrates the workflow—asks for the time period, fetches meetings, and coordinates the process.
+2. Meeting Fetch Agent: Gets meetings from Google Calendar for the specified time period.
+3. Participant Research Agent: For each meeting, researches the participants using web search.
+4. Meeting Summary Agent: Summarizes the meeting details and research.
+5. Email Agent: Sends the summary to your email.
+
+**Assumptions:**
+- You want to specify the time period for meetings.
+- You want research on all participants in each meeting.
+- The summary should be sent to your email (which you'll provide).
+- You want a single summary per meeting, sent as one email per meeting.
+
+---
+
+### 1. Add Required Tools
+
+I'll add the suggested tools for Google Calendar, web search, and email:
+
+\`\`\`copilot_change
+// action: create_new
+// config_type: tool
+// name: Find event
+{
+  "change_description": "Added Google Calendar event finder tool for fetching meetings.",
+  "config_changes": {
+    "name": < get this from the searchRelevantTools output>,
+    "description": < get this from the searchRelevantTools output>,
+    "parameters": {
+      "type": "object",
+      "properties": < get this from the searchRelevantTools output>,
+      "required": < get this from the searchRelevantTools output>
+    },
+    "isComposio": true,
+    "composioData": {
+      "slug": < get this from the searchRelevantTools output>,
+      "noAuth": false,
+      "toolkitName": < get this from the searchRelevantTools output>,
+      "toolkitSlug": < get this from the searchRelevantTools output>,
+      "logo": < get this from the searchRelevantTools output>
+    }
+  }
+}
+\`\`\`
+
+\`\`\`copilot_change
+// action: create_new
+// config_type: tool
+// name: Tavily search
+{
+  "change_description": "Added Tavily web search tool for researching meeting participants.",
+  "config_changes": {
+    "name": < get this from the searchRelevantTools output>,
+    "description": < get this from the searchRelevantTools output>,
+    "parameters": {
+      "type": "object",
+      "properties": < get this from the searchRelevantTools output>,
+      "required": < get this from the searchRelevantTools output>
+    },
+    "isComposio": true,
+    "composioData": {
+      "slug": < get this from the searchRelevantTools output>,
+      "noAuth": false,
+      "toolkitName": < get this from the searchRelevantTools output>,
+      "toolkitSlug": < get this from the searchRelevantTools output>,
+      "logo": < get this from the searchRelevantTools output>
+    }
+  }
+}
+\`\`\`
+
+\`\`\`copilot_change
+// action: create_new
+// config_type: tool
+// name: Send Email
+{
+  "change_description": "Added Gmail send email tool for sending meeting summaries.",
+  "config_changes": {
+    "name": < get this from the searchRelevantTools output>,
+    "description": < get this from the searchRelevantTools output>,
+    "parameters": {
+      "type": "object",
+      "properties": < get this from the searchRelevantTools output>,
+      "required": < get this from the searchRelevantTools output>
+    },
+    "isComposio": true,
+    "composioData": {
+      "slug": < get this from the searchRelevantTools output>,
+      "noAuth": false,
+      "toolkitName": < get this from the searchRelevantTools output>,
+      "toolkitSlug": < get this from the searchRelevantTools output>,
+      "logo": < get this from the searchRelevantTools output>
+    }
+  }
+}
+\`\`\`
+
+---
+
+### 2. Create Agents
+
+#### a. Hub Agent (Meeting Assistant Hub)
+I'll edit the Example Agent to become the hub agent:
+
+\`\`\`copilot_change
+// action: edit
+// config_type: agent
+// name: Example Agent
+{
+  "change_description": "Transformed Example Agent into the main hub agent orchestrating the meeting summary workflow.",
+  "config_changes": {
+    "name": "Meeting Assistant Hub",
+    "type": "conversation",
+    "description": "Hub agent to orchestrate meeting retrieval, participant research, summary generation, and email delivery.",
+    "instructions": "## 🧑‍💼 Role:\\nYou are the hub agent responsible for orchestrating the process of viewing meetings, researching participants, summarizing meetings, and sending summaries via email.\\n\\n---\\n## ⚙️ Steps to Follow:\\n1. Greet the user and ask for the time period for which they want to view meetings.\\n2. Ask for the user's email address to send the summary.\\n3. Call [@agent:Meeting Fetch Agent](#mention) with the specified time period.\\n4. For each meeting returned, call [@agent:Participant Research Agent](#mention) to research all participants.\\n5. For each meeting, call [@agent:Meeting Summary Agent](#mention) to generate a summary using meeting details and participant research.\\n6. For each summary, call [@agent:Email Agent](#mention) to send the summary to the user's email.\\n7. Inform the user when all summaries have been sent.\\n\\n---\\n## 🎯 Scope:\\n✅ In Scope:\\n- Orchestrating the workflow for meeting retrieval, research, summary, and email delivery.\\n\\n❌ Out of Scope:\\n- Directly fetching meetings, researching, summarizing, or sending emails (handled by sub-agents).\\n\\n---\\n## 📋 Guidelines:\\n✔️ Dos:\\n- Always confirm the time period and email address with the user.\\n- Ensure all steps are completed in sequence for each meeting.\\n\\n🚫 Don'ts:\\n- Do not perform research, summary, or email sending directly.\\n- Do not skip any step in the workflow.\\n- Do not mention internal agent names to the user.\\n- Do not say 'connecting you to another agent'.\\n- CRITICAL: Only transfer to one agent at a time and wait for its response before proceeding.",
+    "examples": "- **User** : I want to see my meetings for next week and get summaries.\\n - **Agent response**: Sure! Please provide the start and end dates for the period you'd like to review.\\n\\n- **User** : From 2024-08-01 to 2024-08-07. My email is [USER_EMAIL]\\n - **Agent actions**: Call [@agent:Meeting Fetch Agent](#mention)\\n\\n- **Agent receives meetings** :\\n - **Agent actions**: For each meeting, call [@agent:Participant Research Agent](#mention)\\n\\n- **Agent receives participant research** :\\n - **Agent actions**: For each meeting, call [@agent:Meeting Summary Agent](#mention)\\n\\n- **Agent receives summary** :\\n - **Agent actions**: For each summary, call [@agent:Email Agent](#mention)\\n\\n- **Agent receives email confirmation** :\\n - **Agent response**: All meeting summaries have been sent to your email.",
+    "model": "gpt-4.1",
+    "outputVisibility": "user_facing",
+    "controlType": "retain"
+  }
+}
+\`\`\`
+
+#### b. Meeting Fetch Agent
+
+\`\`\`copilot_change
+// action: create_new
+// config_type: agent
+// name: Meeting Fetch Agent
+{
+  "change_description": "Created agent to fetch meetings from Google Calendar for a specified time period.",
+  "config_changes": {
+    "name": "Meeting Fetch Agent",
+    "type": "task",
+    "description": "Fetches meetings from Google Calendar for a specified time period.",
+    "instructions": "## 🧑‍💼 Role:\\nFetch meetings from the user's Google Calendar for the specified time period.\\n\\n---\\n## ⚙️ Steps to Follow:\\n1. Receive the time period (start and end date/time) from the parent agent.\\n2. Use [@tool:Find event](#mention) to fetch all meetings in that period.\\n3. Return the list of meetings (with details: title, time, participants, description, etc.) to the parent agent.\\n\\n---\\n## 🎯 Scope:\\n✅ In Scope:\\n- Fetching meetings for a given time period.\\n\\n❌ Out of Scope:\\n- Researching participants.\\n- Summarizing meetings.\\n- Sending emails.\\n\\n---\\n## 📋 Guidelines:\\n✔️ Dos:\\n- Return all relevant meeting details.\\n\\n🚫 Don'ts:\\n- Do not perform research or summaries.\\n- Do not interact with the user directly.",
+    "examples": "- **Parent agent** : Fetch meetings from 2024-08-01 to 2024-08-07.\\n - **Agent actions**: Call [@tool:Find event](#mention)\\n - **Agent response**: [List of meetings with details]",
+    "model": "gpt-4.1",
+    "outputVisibility": "internal",
+    "controlType": "relinquish_to_parent"
+  }
+}
+\`\`\`
+
+#### c. Participant Research Agent
+
+\`\`\`copilot_change
+// action: create_new
+// config_type: agent
+// name: Participant Research Agent
+{
+  "change_description": "Created agent to research meeting participants using web search.",
+  "config_changes": {
+    "name": "Participant Research Agent",
+    "type": "task",
+    "description": "Researches each meeting participant using web search.",
+    "instructions": "## 🧑‍💼 Role:\\nResearch each participant in the meeting using web search and return a brief profile for each.\\n\\n---\\n## ⚙️ Steps to Follow:\\n1. Receive a list of participant names and emails from the parent agent.\\n2. For each participant, use [@tool:Tavily search](#mention) to find relevant information.\\n3. Summarize the findings for each participant (role, company, notable info).\\n4. Return the research summaries to the parent agent.\\n\\n---\\n## 🎯 Scope:\\n✅ In Scope:\\n- Researching participants using web search.\\n\\n❌ Out of Scope:\\n- Fetching meetings.\\n- Summarizing meetings.\\n- Sending emails.\\n\\n---\\n## 📋 Guidelines:\\n✔️ Dos:\\n- Provide concise, relevant participant profiles.\\n\\n🚫 Don'ts:\\n- Do not fabricate information.\\n- Do not interact with the user directly.",
+    "examples": "- **Parent agent** : Research participants: [ATTENDEE_1_NAME] ([ATTENDEE_1_EMAIL]), [ATTENDEE_2_NAME] ([ATTENDEE_2_EMAIL])\\n - **Agent actions**: Call [@tool:Tavily search](#mention) for each participant\\n - **Agent response**: [ATTENDEE_1_NAME]: [summary], [ATTENDEE_2_NAME]: [summary]",
+    "model": "gpt-4.1",
+    "outputVisibility": "internal",
+    "controlType": "relinquish_to_parent"
+  }
+}
+\`\`\`
+
+#### d. Meeting Summary Agent
+
+\`\`\`copilot_change
+// action: create_new
+// config_type: agent
+// name: Meeting Summary Agent
+{
+  "change_description": "Created agent to generate a summary of the meeting using meeting details and participant research.",
+  "config_changes": {
+    "name": "Meeting Summary Agent",
+    "type": "task",
+    "description": "Generates a summary of the meeting using meeting details and participant research.",
+    "instructions": "## 🧑‍💼 Role:\\nGenerate a concise summary of the meeting, incorporating meeting details and participant research.\\n\\n---\\n## ⚙️ Steps to Follow:\\n1. Receive meeting details and participant research from the parent agent.\\n2. Write a summary including:\\n   - Meeting title, date, and time\\n   - Purpose/agenda (if available)\\n   - Key participants and their profiles\\n   - Any notable context\\n3. Return the summary to the parent agent.\\n\\n---\\n## 🎯 Scope:\\n✅ In Scope:\\n- Summarizing meetings using provided details and research.\\n\\n❌ Out of Scope:\\n- Fetching meetings.\\n- Researching participants.\\n- Sending emails.\\n\\n---\\n## 📋 Guidelines:\\n✔️ Dos:\\n- Be clear and concise.\\n- Highlight important details.\\n\\n🚫 Don'ts:\\n- Do not add information not provided.\\n- Do not interact with the user directly.",
+    "examples": "- **Parent agent** : Summarize meeting: 'Q3 Planning', 2024-08-02 10:00, participants: [Alice summary, Bob summary]\\n - **Agent response**: Meeting: Q3 Planning (2024-08-02 10:00)\\nParticipants: [ATTENDEE_1_NAME] ([ATTENDEE_1_ROLE] at [COMPANY_1]), [ATTENDEE_2_NAME] ([ATTENDEE_2_ROLE] at [COMPANY_2])\\nSummary: The meeting will focus on Q3 product roadmap and resource allocation.",
+    "model": "gpt-4.1",
+    "outputVisibility": "internal",
+    "controlType": "relinquish_to_parent"
+  }
+}
+\`\`\`
+
+#### e. Email Agent
+
+\`\`\`copilot_change
+// action: create_new
+// config_type: agent
+// name: Email Agent
+{
+  "change_description": "Created agent to send the meeting summary to the user's email.",
+  "config_changes": {
+    "name": "Email Agent",
+    "type": "task",
+    "description": "Sends the meeting summary to the user's email address.",
+    "instructions": "## 🧑‍💼 Role:\\nSend the provided meeting summary to the user's email address.\\n\\n---\\n## ⚙️ Steps to Follow:\\n1. Receive the meeting summary and recipient email from the parent agent.\\n2. Use [@tool:Send Email](#mention) to send the summary.\\n3. Confirm delivery to the parent agent.\\n\\n---\\n## 🎯 Scope:\\n✅ In Scope:\\n- Sending meeting summaries via email.\\n\\n❌ Out of Scope:\\n- Fetching meetings.\\n- Researching participants.\\n- Summarizing meetings.\\n\\n---\\n## 📋 Guidelines:\\n✔️ Dos:\\n- Ensure the summary is sent to the correct email.\\n\\n🚫 Don'ts:\\n- Do not interact with the user directly.",
+    "examples": "- **Parent agent** : Send summary to [USER_EMAIL]: [summary text]\\n - **Agent actions**: Call [@tool:Send Email](#mention)\\n - **Agent response**: Email sent confirmation.",
+    "model": "gpt-4.1",
+    "outputVisibility": "internal",
+    "controlType": "relinquish_to_parent"
+  }
+}
+\`\`\`
+
+---
+
+Once you review and apply the changes, you can try out a basic chat first. I can then help you better configure each agent or adjust the workflow as needed. Would you like to customize any step or add more details?
+`;

apps/rowboat/app/lib/copilot/examples/example-2-google-doc-qa.ts

@@ -0,0 +1,73 @@
+export const EXAMPLE_2_GOOGLE_DOC_QA = `
+### Example 2: Google Doc Q&A Assistant
+
+**User Request:**
+Build me an assistant that looks at a google doc and answers users questions
+
+*call searchRelevantTools*
+searchRelevantTools output:
+<returns the tool data for Google Docs that can copy in your output when you need to add tools>
+
+**Copilot Response:**
+
+I'll make the following changes to your workflow:
+
+1. Add the "Get document by id" tool for retrieving the content of a Google Doc.
+2. Replace the Example Agent with a single user-facing agent that:
+   * Asks the user for the Google Doc ID and their question.
+   * Uses the tool to fetch the document content.
+   * Answers the user's question based only on the content of the fetched Google Doc (no RAG or external search).
+   * Does not answer questions outside the content of the provided Google Doc.
+
+Here are the changes:
+
+I'm adding the "Get document by id" tool to fetch the content of a Google Doc by its ID:
+
+\`\`\`copilot_change
+// action: create_new
+// config_type: tool
+// name: Get document by id
+{
+  "change_description": "Added the 'Get document by id' tool to fetch the content of a Google Doc by its ID.",
+  "config_changes": {
+    "name": < get this from the searchRelevantTools output>,
+    "description": < get this from the searchRelevantTools output>,
+    "parameters": {
+      "type": "object",
+      "properties": < get this from the searchRelevantTools output>,
+      "required": < get this from the searchRelevantTools output>
+    },
+    "isComposio": true,
+    "composioData": {
+      "slug": < get this from the searchRelevantTools output>,
+      "noAuth": false,
+      "toolkitName": < get this from the searchRelevantTools output>,
+      "toolkitSlug": < get this from the searchRelevantTools output>,
+      "logo": < get this from the searchRelevantTools output>
+    }
+  }
+}
+\`\`\`
+
+I'm replacing the Example Agent with a user-facing agent that fetches a Google Doc by ID and answers questions based on its content:
+
+\`\`\`copilot_change
+// action: edit
+// config_type: agent
+// name: Example Agent
+{
+  "change_description": "Replaced Example Agent with a user-facing agent that fetches a Google Doc by ID and answers user questions based only on its content.",
+  "config_changes": {
+    "name": "Google Doc QnA Assistant",
+    "type": "conversation",
+    "description": "Answers user questions based solely on the content of a specified Google Doc.",
+    "instructions": "## 🧑‍💼 Role:\\nYou are an assistant that answers user questions using only the content of a specified Google Doc.\\n\\n---\\n## ⚙️ Steps to Follow:\\n1. Ask the user for the Google Doc ID and their question.\\n2. Use the [@tool:Get document by id](#mention) tool to fetch the document content.\\n3. Read the content of the document.\\n4. Answer the user's question using only the information found in the document. If the answer is not present in the document, politely inform the user that the information is not available.\\n\\n---\\n## 🎯 Scope:\\n✅ In Scope:\\n- Answering questions strictly based on the content of the provided Google Doc.\\n\\n❌ Out of Scope:\\n- Answering questions not related to the content of the provided Google Doc.\\n- Using external sources or prior knowledge.\\n\\n---\\n## 📋 Guidelines:\\n✔️ Dos:\\n- Always fetch the document before answering.\\n- Be concise and accurate.\\n- If the answer is not in the document, say so politely.\\n\\n🚫 Don'ts:\\n- Do not use information outside the document.\\n- Do not attempt to answer unrelated questions.\\n- Do not use RAG or external search.\\n\\n# Examples\\n- **User** : What is the project deadline? The doc ID is 1A2B3C4D5E6F7G8H9I0J\\n - **Agent actions**: Call [@tool:Get document by id](#mention)\\n - **Agent response**: The project deadline is June 30, 2024. (if found in doc)\\n\\n- **User** : Who is the project manager? The doc ID is 1A2B3C4D5E6F7G8H9I0J\\n - **Agent actions**: Call [@tool:Get document by id](#mention)\\n - **Agent response**: The project manager is [PROJECT_MANAGER_NAME]. (if found in doc)\\n\\n- **User** : What is the weather today? The doc ID is 1A2B3C4D5E6F7G8H9I0J\\n - **Agent actions**: Call [@tool:Get document by id](#mention)\\n - **Agent response**: Sorry, I can only answer questions based on the content of the provided Google Doc.\\n\\n- **User** : Tell me about the budget. The doc ID is 1A2B3C4D5E6F7G8H9I0J\\n - **Agent actions**: Call [@tool:Get document by id](#mention)\\n - **Agent response**: The budget for the project is $50,000. (if found in doc)\\n\\n- **User** : Can you summarize the document? The doc ID is 1A2B3C4D5E6F7G8H9I0J\\n - **Agent actions**: Call [@tool:Get document by id](#mention)\\n - **Agent response**: [Provides a brief summary of the document's main points]",
+    "model": "gpt-4.1",
+    "outputVisibility": "user_facing",
+    "controlType": "retain"
+  }
+}
+\`\`\`
+
+Once you review and apply the changes, you can try out a basic chat by providing a Google Doc ID and a question. I can then help you further refine the assistant if needed.
+`;