# Welcome Source: https://docs.lancey.ai/index Learn more about Lancey and how to get started ## What is Lancey? Lancey lets you spin up multiplayer agents for your engineering team so you can plan and execute code tasks as a team, in the background. Typically, most engineers rely on IDE-based copilots that can only handle one task at a time with no team visibility. This leaves you waiting for an LLM to complete a single task while unable to work on anything else. Lancey lets you **100x your engineering output** by parallelizing tasks across hundreds of AI agents working in the background. ## What can I use Lancey for? Lancey listens to incoming support tickets and GitHub issues, automatically generating PRs to fix customer-reported bugs. Tell Lancey what to work on and it tackles tasks in the background. Get full visibility across your entire team's progress. Review and approve all changes before merging. Set custom approval workflows and maintain full codebase oversight. ## Do I need to change my CI/CD pipeline? Everything lands where your code already lives. Lancey integrates deeply with GitHub, Linear, Intercom, and Slack, automatically linking PRs to tickets and alerting your team. No one on the team has to change their existing workflow. ## Get started Ready to ship faster with AI agents? Follow these steps: Get up and running in under 10 minutes Learn how to create and manage tasks Connect your tools (GitHub, Slack, Linear, Intercom) Set up automatic task processing from customer feedback Start using Lancey today and transform your engineering workflow. # Github Source: https://docs.lancey.ai/integrations/github How to set up the Github integration. Lancey needs access to your repositories in order to work. Head to [Integrations](https://platform.lancey.ai/settings/integrations) page Click on **GitHub** connector Complete the login flow. Choose all or specific repos that you want to connect to Lancey. You will be redirected back to Lancey. If not, try refreshing the page. Once connected, you’ll see an option to select a **repo** where you want Lancey to work with. # Intercom Source: https://docs.lancey.ai/integrations/intercom Integrate Lancey with Intercom to automatically create PRs for customer support requests and issues. ## Overview Connect Lancey with Intercom to automatically convert customer support conversations, feature requests, and bug reports into pull requests. Keep your support team informed when issues are resolved. Intercom integration enables Lancey to scan customer conversations and automatically generate fixes, turning support requests into deployed solutions. ## Setup Head to the [Integrations](https://platform.lancey.ai/settings/integrations) page in your dashboard Click on the **Intercom** connector You'll be redirected to Intercom to authorize Lancey. Review the permissions and click **Authorize** to proceed Choose your Intercom workspace to connect with Lancey Set up rules for which conversations Lancey should monitor: * Conversations tagged with specific labels * Conversations assigned to certain teams * Conversations with specific keywords ## How it works Once Intercom is connected, Lancey will: * **Monitor conversations** - Watch Intercom conversations for support requests and bug reports * **Identify action items** - Extract actionable technical issues from customer conversations * **Create PRs automatically** - Generate pull requests to address identified issues * **Post updates** - Reply in the original Intercom conversation when a PR is created or merged * **Track resolutions** - Keep customers informed about when their issues are deployed ## Best practices Tag support requests with labels like "bug", "feature-request", or "urgent" for better routing Encourage support team to add technical details in conversation notes for Lancey to reference Configure conversation rules to avoid triggering Lancey on every conversation Regularly review which conversations lead to PRs to improve your rules ## Troubleshooting Ensure that: * You have admin access to your Intercom workspace * You're signed into the correct Intercom account * Granted Lancey the required permissions during authorization * Your GitHub repository is connected to Lancey Verify that: * Your conversation rules are set up correctly in **Settings → Integrations** * Conversations match your configured tags or keywords * The GitHub repository is properly connected * Lancey has permission to read conversations in Intercom Check that: * Both Intercom and GitHub integrations are active * The PR was successfully created in your GitHub repository * Your GitHub repository is properly connected * Conversation rules are matching the right conversations ## Next steps Learn how to configure your GitHub repositories Connect Slack for team notifications Explore advanced integration options Need help setting up Intercom integration? Reach out via the livechat widget on our platform for quick support or [schedule a call](https://cal.com/pateladi/support) with our team. # Linear Source: https://docs.lancey.ai/integrations/linear Integrate Lancey with Linear to automatically create PRs for issues and sync task status. ## Overview Connect Lancey with Linear to automatically generate pull requests for issues, sync task status across both platforms, and keep your team aligned on what's being worked on. Linear integration allows Lancey to automatically pick up issues and link them to PRs, creating a seamless workflow between issue tracking and code delivery. ## Setup Head to the [Integrations](https://platform.lancey.ai/settings/integrations) page in your dashboard Click on the **Linear** connector You'll be redirected to Linear to authorize Lancey. Click **Authorize** to grant the necessary permissions Choose the Linear workspace you want to connect to Lancey Select which teams or projects you want Lancey to work with. You can update these settings anytime ## How it works Once Linear is connected, Lancey will: * **Automatically detect issues** - Monitor your Linear issues for new tasks * **Create PRs** - Generate pull requests to fix issues based on your issue descriptions * **Link PRs to issues** - Automatically link created PRs back to Linear issues * **Update issue status** - Sync task status between Lancey and Linear * **Assign reviewers** - Reference issue assignments when creating PRs ## Best practices Use consistent labels to help Lancey prioritize which issues to work on Detailed issue descriptions help Lancey understand the context and requirements Use Linear's priority field to guide task prioritization in Lancey Ensure team members have proper Linear access for PR reviews ## Troubleshooting Make sure you: * Have admin access to your Linear workspace * Are signed into the correct Linear account * Have granted Lancey the necessary permissions during authorization Verify that: * The Linear connector is active in **Settings → Integrations** * Your GitHub repository is also connected to Lancey * Issue keys are correctly referenced in your repository names Check that: * Both Linear and GitHub integrations are properly configured * You have update permissions in both Linear and your GitHub repositories * The PR has been successfully merged in GitHub ## Next steps Learn how to configure your GitHub repositories Explore advanced integration options Start creating tasks with your connected integrations Need help setting up Linear integration? Reach out via the livechat widget on our platform for quick support or [schedule a call](https://cal.com/pateladi/support) with our team. # Slack Source: https://docs.lancey.ai/integrations/slack Set up Slack to trigger tasks directly and get notifications when tasks are completed. ## Setup If you want notifications when a new task is created or PR is ready to merge, set up the Lancey Slack connector so you can manage the agents from within Slack. Head to [Integrations](https://platform.lancey.ai/settings/integrations/slack.com) page Click on the **Slack** connector Complete the login flow that pops up in the Slack domain. Choose **the workspace** that you want to connect to Lancey. Pick the **channel** you want Lancey to send notifications in. Typically this would be #engineering or #engineering-alert type of channel if you use something similar internally. Task Pn

Once the connection is set up, you can also connect your personal account to recieve notifications directly from the Lancey bot instead of a channel. Remember to have your [notification](https://platform.lancey.ai/settings/notifications) preferences enabled for Slack after you've completed the setup. ## Starting a task You can assign Lancey to work on a task directly from Slack. Once the Slack connection is established, you can simply mention @Lancey within a thread.

You can also mention @Lancey in comments of a thread if you want it to pick up a task. # List Source: https://docs.lancey.ai/issues/list View and manage your issues in Lancey. ## Overview The Issues list shows all the issues detected from your integrations and feedback sources. This is where you can view, filter, and manage issues before they become tasks. Use the Issues list to monitor incoming problems and decide which ones to prioritize for agent work. ## Viewing your issues Click **Issues** in the left sidebar navigation See all detected issues from your connected integrations and feedback sources Use filters and sorting to find the issues you need to address ## Issue details Each issue in the list displays the following information: | Column | Description | | ---------------- | ------------------------------------------------------------ | | **Title** | Issue name or description | | **Source** | Where the issue was detected (GitHub, Slack, Intercom, etc.) | | **Status** | Current status (Open, In Progress, Resolved) | | **Created date** | When the issue was first detected | | **Create Task** | Click to convert the issue into a task for agents to work on | You can filter issues by status to quickly find Open, In Progress, or Resolved issues. ## Creating tasks from issues When you find an issue you want to work on: 1. Select the issue from the list 2. Review the issue details 3. Click **Create Task** to convert it to a task for agents to work on ## Best practices Check your Issues list frequently to stay on top of incoming problems and feedback. Focus on issues that affect customer experience or critical functionality first. Filter by source and priority to quickly find the issues most relevant to your team's focus. ## Next steps Learn how to create and manage tasks Set up automatic processing from your issues Questions about managing issues? Reach out via the livechat widget on our platform or [schedule a call](https://cal.com/pateladi/support) with our team. # Quickstart Source: https://docs.lancey.ai/quickstart Create an account and ship your first PR in minutes Learn about Lancey's capabilities and use cases before getting started ## Get set up in less than 10 minutes Complete these steps to set up Lancey and start shipping PRs with AI agents. Make sure you have admin access to your GitHub repository before proceeding with the GitHub integration step. * Visit the [dashboard](https://platform.lancey.ai) * Sign up with your work email or GitHub account Connecting your GitHub repo lets Lancey automatically draft ready-to-merge PRs * Go to **Settings --> Integrations → GitHub** in your dashboard * Click **Connect GitHub** and authorize access * Select the repositories you want Lancey to publish PRs for You can bring your own keys to use with Lancey or load up the credits to use. * Go to **Settings --> AI Providers** in your dashboard * Add your preferred AI provider credentials (OpenAI, Claude, etc.) * Go to **[Settings --> Models](https://platform.lancey.ai/settings/models)** to configure your model preferences * Test your configuration to ensure everything is working * If you prefer topping up your credit balance, head to **Settings --> Billing** and click on **Add to credits balance** Stay updated on important issues and PRs without leaving Slack. * Navigate to **Settings --> Integrations → Slack** * Click **Connect** and select the Workspace * Choose which channel should receive Lancey notifications You can skip the Slack integration and other steps if needed and come back to them later Collaborate with your teammates so everyone stays aligned. * Open the **Settings > Members** tab * Click **Invite Members** * Enter their emails and assign roles (Admin or Member) Review and approve tasks generated by Lancey. * Go to the **Overview** page in your dashboard * Review suggested fixes or improvements * Approve, edit, or dismiss tasks as needed ## What's next? Learn how to configure your GitHub repositories Set up notifications in Slack Start creating and managing tasks Explore advanced integration options ## Troubleshooting Make sure you have: * Admin access to your GitHub repository * Authorized the Lancey app in your GitHub settings * Selected the correct repositories during setup Verify that: * Your workspace has the Slack app installed * You selected a valid channel to receive notifications * The integration permissions are properly configured in **Settings --> Integrations → Slack** Check that: * Your API keys are valid and have active credits/quota * You've configured at least one model in **[Settings --> Models](https://platform.lancey.ai/settings/models)** * Your AI provider account has sufficient permissions ## Need help? Get support from our team: Use the livechat widget on our platform to get quick answers One-on-one setup assistance from our team # Billing Source: https://docs.lancey.ai/settings/billing Manage your Lancey subscription, payment methods, and usage. ## Overview The Billing section allows workspace admins to manage your subscription plan, view usage metrics, and add credits to your account. Only workspace admins can make changes to billing and subscription settings. Contact your admin if you need to upgrade, downgrade, or add credits. ## Managing your subscription ### View current plan Your current subscription tier and features are displayed at the top of the Billing page: | Information | Description | | ----------------- | ------------------------------- | | **Plan name** | Your current subscription level | | **Billing cycle** | Monthly, annual, or custom | | **Usage** | Current usage for your plan | ### Upgrade or downgrade plan Go to **Settings → Billing** in your dashboard See all available subscription tiers with features and pricing Click on the plan you want to switch to Confirm the pricing impact and billing date changes Click **Confirm** to apply the change ## Adding credits If you need additional capacity beyond your plan: 1. Click **Add to credits balance** in the Billing section 2. Choose your credit amount 3. Complete the payment 4. Credits will be available immediately A service fee applies to credit top-ups. Review the fee amount before completing your purchase. Credits roll over between billing periods, so you can use them whenever you need additional capacity. ## Usage and limits Monitor your usage for your plan: * **Task processing** - Number of tasks processed this cycle ## Best practices Ensure automatic billing is enabled to avoid service interruptions from missed payments. Update card information before expiration dates to prevent failed transactions. If you need additional capacity, reach out to our team to discuss volume pricing options. ## Troubleshooting * Verify your payment method is current and not expired * Check that your billing address is correct * Try a different payment method * Contact support if the issue persists You can: * Upgrade to a higher tier plan * Add credits for additional capacity * Contact support to discuss your needs Go to **Billing → Invoices**, find the invoice you need, and click **Download PDF**. Invoices are available for all past billing periods. Need billing support? Reach out via the livechat widget on our platform or [schedule a call](https://cal.com/pateladi/support) with our team for assistance. # MCP Servers Source: https://docs.lancey.ai/settings/mcp-servers Configure Model Context Protocol servers to extend Lancey's capabilities. ## Overview MCP (Model Context Protocol) Servers allow you to connect external tools, data sources, and services to Lancey. This enables agents to access additional context and capabilities beyond the core platform. MCP servers expand what Lancey agents can do. Connect relevant tools to give agents the information and access they need to work effectively. ## What are MCP servers? MCP servers act as bridges between Lancey and external systems: * **Data access** - Connect to databases, APIs, or knowledge bases * **Tool integration** - Integrate with external tools and services * **Context enrichment** - Provide agents with additional context and information * **Custom capabilities** - Extend Lancey with domain-specific functionality ## Connecting an MCP server Go to **Settings → MCP Servers** in your dashboard Click the **Add** button Provide: * Server URL or connection endpoint * Authentication credentials (if required) Click **Add Server** to add the server to your workspace ## Managing MCP servers ### Viewing connected servers Your MCP Servers page displays: * Status (Connected, Disconnected, Error) * Connection type * Actions menu ### Updating server configuration 1. Click the server you want to update 2. Modify the connection details or credentials 3. Click **Save** to apply changes ### Removing a server 1. Click the menu icon next to the server 2. Select **Remove** 3. Confirm the removal Removing a server will stop agents from accessing the resources it provides. Tasks in progress may fail if they depend on this server. ## Server types Common MCP server configurations: * **Database connections** - Connect to PostgreSQL, MySQL, or other databases * **API servers** - Integrate with REST or GraphQL APIs * **Document stores** - Connect to knowledge bases or documentation systems * **Custom tools** - Deploy your own MCP-compatible tools * **Third-party services** - Integrate with SaaS platforms ## Best practices Begin with MCP servers that provide critical context. Add more as needed rather than connecting everything at once. Check connection status regularly and set up alerts for disconnections or errors. Keep clear notes about what each MCP server provides and why it's needed for your team. Update API keys and passwords periodically for security. Remove access for servers no longer in use. ## Troubleshooting * Verify the server URL is correct * Check that credentials are valid * Ensure the server is running and accessible * Check firewall/network rules if external * Review server logs for error details Verify that: * The server status shows "Connected" * Agents have been running after the server was added * The server isn't rate-limiting requests * Check server stability and uptime * Verify network connectivity is stable * Update credentials if they recently changed * Contact the server administrator for support * Consider using a more reliable server endpoint You can build custom MCP servers following the [Model Context Protocol specification](https://modelcontextprotocol.io). Contact our team for guidance on implementing your specific use case. ## Next steps Explore all available integrations Configure your AI model settings Need help setting up MCP servers? Reach out via the livechat widget on our platform or [schedule a call](https://cal.com/pateladi/support) with our team. # Members Source: https://docs.lancey.ai/settings/members Manage your team members, roles, and permissions in Lancey. ## Overview The Members section allows you to invite team members, manage their roles, and control who can access your Lancey workspace. Only Admins can invite members, change roles, and remove team members from the workspace. ## User roles and permissions Lancey supports two roles with different permission levels: | Capability | Admin | Member | | -------------------------------------------- | ----- | ------ | | **Full access to workspace settings** | ✓ | ✗ | | **Invite and remove team members** | ✓ | ✗ | | **Change roles and permissions** | ✓ | ✗ | | **Access billing and subscription settings** | ✓ | ✗ | | **Create and modify integrations** | ✓ | ✗ | | **View and manage tasks** | ✓ | ✓ | | **Create new tasks** | ✓ | ✓ | | **Approve or dismiss suggestions** | ✓ | ✓ | ## Inviting team members Go to **Settings → Members** in your dashboard Click the **+** button in the Invitations section Input the email address of the team member you want to invite Choose a role (Admin or Member) for the invitee Click **Send**. The team member will receive an email with an invite link ## Managing team members ### Viewing team members Your Members page displays all current team members with: * Name and email * Role (Admin or Member) * Join date * Status (Active or Pending) ### Changing a member's role 1. Find the team member in the Members list 2. Click the role dropdown next to their name 3. Select the new role 4. Click **Update** ### Removing a team member 1. Click the menu icon next to the team member 2. Select **Remove from workspace** 3. Confirm the removal Removing a team member will revoke their access immediately. Consider exporting any important work first. ## Pending invitations Members with "Pending" status haven't accepted their invitation yet: * **Resend invitation** - Click the menu and select "Resend" to send the invite email again * **Cancel invitation** - Click the menu and select "Cancel" to revoke the pending invite * **Auto-expire** - Invitations expire after 30 days ## Best practices Give team members the minimum permissions they need. Start with Member role and escalate to Admin only when necessary. Monthly, review your Members list to ensure everyone still needs their access level and remove inactive users. Have multiple admins for your workspace in case one is unavailable. At least one other admin should be able to manage billing and settings. Follow up with team members if their invitations are still pending after a few days. ## Troubleshooting * Check that the email address is correct * Ask them to check spam/junk folders * Resend the invitation from the Members page * Verify their email domain isn't blocking Lancey Verify that: * They clicked the invite link in the email * They created their account successfully * Their status shows "Active" (not "Pending") * They're using the correct email address You can change a Member's role to Admin by: 1. Going to **Settings → Members** 2. Clicking the role dropdown next to their name 3. Selecting "Admin" 4. Clicking "Update" Questions about managing your team? Reach out via the livechat widget on our platform or [schedule a call](https://cal.com/pateladi/support) with our team. # Memory Source: https://docs.lancey.ai/settings/memory Configure how Lancey stores and manages context for your tasks. ## Overview Memory in Lancey is automatically managed and saved based on agent interactions. As agents work on tasks, Lancey captures context, decisions, and patterns to help future agents understand your codebase and make better decisions. Memory is automatically saved from every agent interaction. The more tasks agents complete, the better they become at understanding your codebase and making consistent decisions. ## How memory works Memory is captured automatically through: * **Agent interactions** - Context from each task the agent works on * **Code patterns** - Learned patterns from your repository * **Decision history** - Previous decisions and outcomes * **Team preferences** - Common practices and patterns in your codebase Once memory is captured, agents can leverage it on subsequent tasks to make more informed decisions and maintain consistency. ## Viewing your memory To see the memory captured from your agent interactions: 1. Go to **Settings → Memory** in your Lancey dashboard 2. View the context and patterns that have been learned from completed tasks 3. This memory is automatically used by agents on future tasks ## Best practices The more tasks agents complete, the better they understand your codebase. Complete several tasks before expecting agents to reference past patterns. Consistent project structure and naming conventions help agents learn and apply patterns more effectively. Well-documented task requirements help agents learn the right patterns and decisions to remember. Check the first few tasks agents complete. This helps you understand what patterns they're learning and make adjustments if needed. ## Troubleshooting Ensure that: * Multiple tasks have been completed so agents have context to draw from * Memory settings are configured to use historical context * Your tasks and codebase structure are consistent * Provide clearer examples in task descriptions * Ensure your team has established consistent coding practices * Give agents more context through additional completed tasks Questions about memory configuration? Reach out via the livechat widget on our platform for quick support or [schedule a call](https://cal.com/pateladi/support) with our team. # Auto processing Source: https://docs.lancey.ai/tasks/auto-processing Configure Lancey to automatically process tasks based on custom prompts and customer feedback. ## Overview Auto Processing enables you to define custom prompts that tell Lancey which tasks it should automatically work on. Instead of manually triggering tasks, Lancey monitors incoming feedback and customer issues, then intelligently decides which ones match your criteria to start processing automatically. Auto Processing is perfect for teams that want to reduce manual task creation while maintaining control over which issues Lancey should tackle. Set it once and let Lancey handle the rest. ## How it works Auto Processing follows a simple workflow: 1. **You define a prompt** - Write clear instructions about what types of tasks Lancey should work on 2. **Lancey monitors feedback** - Your integrations (Slack, Intercom, GitHub issues) feed customer feedback to Lancey 3. **AI evaluation** - Lancey evaluates each piece of feedback against your custom prompt 4. **Automatic execution** - Matching tasks are automatically added to your queue and processing begins 5. **Team review** - Your team can review and approve tasks before they're merged ## Setup Go to **Settings --> Issues** in your Lancey dashboard In the **Processing instructions** text field, provide specific instructions for how the AI should evaluate and process issues Describe the types of tasks Lancey should automatically process. Be specific about: * Issue types (bugs, features, enhancements) * Priority levels * Source integrations (Slack, Intercom, GitHub) * Any specific keywords or patterns Toggle the **Auto Processing** switch to enable automatic processing for your rules Click **Save** to apply your processing instructions. Lancey will now automatically process matching issues based on your rules ## Writing effective prompts The quality of your auto-processing depends on how well you write your prompts. Here are key principles: Use concrete criteria rather than vague descriptions Include examples of what should and shouldn't be processed Specify minimum severity/priority levels to process Clearly state what NOT to process to avoid false positives ## Prompt examples ### Example 1: Customer bug fixes ``` Process any GitHub issues or customer reports that describe: - Bugs affecting production or user experience - Error messages from users - Features that don't work as documented Do NOT process: - Feature requests or enhancement suggestions - Questions or documentation clarifications - Issues related to non-core functionality Priority: Only process issues marked as "critical" or "high" priority Source: GitHub issues and Intercom support conversations ``` ### Example 2: High-priority enhancements ``` Automatically work on enhancement requests that: - Come from paying customers - Have been upvoted or requested by multiple users - Are tagged with "high-value-customer" or "revenue-impacting" - Relate to core product features Skip: - Low-priority nice-to-haves - Requests from free tier users - Niche or edge-case features Severity: Only process if marked as "medium" priority or higher Source: Intercom feature requests and GitHub discussions ``` ### Example 3: Security and performance fixes ``` Process all tasks related to: - Security vulnerabilities or potential exploits - Performance issues (slow endpoints, memory leaks) - Data integrity problems - Dependency updates and patching Exclude: - Cosmetic issues - Minor UI improvements - Non-breaking technical debt Timeline: These tasks should be processed with highest urgency Source: GitHub issues, security alerts, and internal reports ``` ### Example 4: API and integration issues ``` Automatically handle tasks for: - External API integration failures - Third-party service connectivity problems - Webhook or callback issues - Deprecated API endpoint migrations Do NOT process: - Internal service connectivity issues (handle manually) - Issues requiring database schema changes - Tasks needing manual data migration Severity: Process if there's active customer impact Source: Slack alerts and GitHub integration issues ``` ### Example 5: Documentation and typo fixes ``` Process low-effort improvements: - Typos in documentation or code comments - Broken links in docs or README files - Outdated code examples - Missing API documentation Exclude: - Major documentation rewrites - Complex API documentation from scratch - Content requiring SME review Batch size: Process up to 5 of these tasks daily Source: GitHub issues labeled "documentation" and "typo" ``` ## Best practices Begin with a narrowly focused prompt that targets a specific type of task. Once you see it working well, you can expand or create additional prompts for other use cases. Review which tasks Lancey auto-processes during the first week. Refine your prompt if you see too many false positives or misses important issues. Include specific keywords, labels, and patterns from your integrations. Reference your Slack channels, GitHub labels, and Intercom tags explicitly. Prompt quality affects results. A vague prompt like "fix bugs" will have lower accuracy than "fix critical bugs affecting the login flow reported in Slack #bugs channel." Even with auto-processing enabled, always require manual review before tasks are merged. This maintains code quality and prevents unintended changes. Track which auto-processed tasks succeed or fail. Use this data to refine your prompt over time. ## Troubleshooting Check that: * Your prompt is enabled in the Auto Processing settings * Your integrations (Slack, Intercom, GitHub) are properly configured * Your feedback sources are actively sending messages * Your prompt criteria match the incoming feedback Your prompt might be too broad. Try: * Adding more specific keywords or criteria * Increasing priority thresholds * Excluding more edge cases * Testing with fewer sources initially Verify that: * Your AI model configuration is set up correctly * Your GitHub repository and credentials are valid * Your team has available capacity to review PRs * Your prompt isn't requiring unnecessary manual approval steps You can: * Temporarily disable a prompt by toggling it off in Auto Processing settings * Edit an existing prompt to adjust criteria * Delete a prompt and create a new one * Create multiple prompts for different task types ## Next steps Learn how to manually create and manage tasks Update and refine your tasks Configure integrations to feed feedback to Lancey Need help crafting the perfect auto-processing prompt? Reach out via the livechat widget on our platform for quick support or [schedule a call](https://cal.com/pateladi/support) with our team. # Task overview Source: https://docs.lancey.ai/tasks/create Tasks are the core unit of work in Lancey. They represent actionable fixes or improvements that your team can review, approve, and resolve, all powered by AI. ## What is a task? A task is a suggested change or bug fix that Lancey generates based on incoming issues or manual input. Each task includes: * **Context**: The source of the issue (GitHub, Zendesk, Intercom, etc.) * **Proposed plan**: How Lancey suggests solving the problem * **Next actions**: Approve, edit, or dismiss the task ## How tasks are created ### 1. From GitHub issues * When a new issue is opened in your connected GitHub repository, Lancey automatically analyzes it. * If the issue is deemed to be a bug or feature improvement, a task will be created and linked back to the original GitHub issue. ### 2. From customer support tickets * Lancey integrates with Zendesk, Intercom, and other platforms. * High‑impact customer tickets are converted into tasks with relevant context for Lancey to work on. ### 3. Manually created by users * Go to the **Tasks** tab in your dashboard. * Give a prompt in the chat input box * Lancey will plan out a resolution path, including any code changes required. ## Best Practices * **Prioritize**: Focus on tasks tied to critical bugs or customer impact first. * **Collaborate**: Tag team members on tasks to review solutions. * **Stay aligned**: Use Slack notifications to keep your team in the loop. *** ## Next Steps Set up GitHub to automatically create tasks from issues Configure automatic task processing based on your criteria Learn how to update and refine your tasks Get team notifications about new tasks and updates # Managing tasks Source: https://docs.lancey.ai/tasks/modify View and manage created tasks within Lancey ### Reviewing a task * Open a task from your dashboard. * Review the context and Lancey’s proposed solution. * If applicable, view the linked draft PR. ### Approving a task * Click **Approve** to confirm the suggested fix. * Lancey will automatically create a pull request in GitHub. ### Editing a task * You can refine the task description or solution plan before approval. * Changes will be reflected in the generated PR. ### Dismissing a task * If a task is irrelevant, click **Dismiss** to remove it from your queue. *** ## Best Practices * **Prioritize**: Focus on tasks tied to critical bugs or customer impact first. * **Collaborate**: Tag team members on tasks to review solutions. * **Stay aligned**: Use Slack notifications to keep your team in the loop. # Watcher agent Source: https://docs.lancey.ai/tasks/watcher-agent Monitor and guide tasks to completion with Lancey's Watcher agent feature. ## Overview The Watcher agent is a Lancey feature that assigns an AI agent to monitor your tasks and provide intelligent nudges to keep them progressing, just like a human would. This allows you to work on more things simultaneously while your agent ensures tasks move forward efficiently. Watcher agent is assigned to every task by default, giving your team more bandwidth to focus on high-level decisions while agents handle the execution details. ## How it works Once a Watcher agent is assigned to a task, it continuously: * **Monitors progress** - Tracks task execution and identifies blockers * **Detects issues** - Identifies when a task gets stuck or encounters problems * **Provides nudges** - Suggests next steps or adjustments to keep momentum * **Maintains context** - Keeps track of task history and requirements * **Adapts dynamically** - Adjusts approach based on task progress and results This creates a more human-like workflow where an agent actively helps move work forward rather than just executing a single planned path. ## Key features Assigned by default to every new task you create Watches task progress and identifies when intervention is needed Suggests course corrections and next steps in real-time Easily unassign or reassign agents as needed ## Managing Watcher agent ### Viewing assignment status When you open a task, the **Properties panel** on the right side of the screen shows whether a Watcher agent is currently assigned to the task. ### Unassigning Watcher agent If you want to disable the Watcher agent for a specific task: Navigate to a task you want to modify Look at the right-hand side of the screen for the Properties panel Click the **Unassign** button next to the Watcher agent Confirm the action when prompted ### Reassigning Watcher agent To re-enable Watcher agent on a task that has been unassigned: 1. Open the task 2. Look in the Properties panel for an **Assign Watcher agent** option 3. Click to reassign a new agent to monitor the task ## When to use Watcher agent Use Watcher agent in these scenarios: * **Complex tasks** - Keep complex, multi-step tasks on track automatically * **Low-priority work** - Let agents handle routine tasks while you focus on important decisions * **High volume** - Manage more tasks simultaneously with agent assistance * **Uncertain requirements** - Agent can adapt when requirements shift during execution ## When to unassign Watcher agent Consider unassigning Watcher agent when: * You need full manual control over task execution * The task is simple and doesn't need monitoring * You're running experiments that require precise, non-adaptive behavior * You want to review and approve each step before the agent proceeds * You're working with sensitive or high-risk changes ## Best practices Let Watcher agents handle standard fixes and improvements. This frees your team to focus on strategic decisions and complex problems. For critical or sensitive tasks, consider unassigning the Watcher agent to maintain tighter control and require explicit approvals at each step. Pair Watcher agent with Auto Processing for a fully autonomous workflow that monitors and executes tasks with minimal human intervention. Check the task history to see how Watcher agent guided the task. Use this insight to refine your auto-processing rules and task instructions. Establish team guidelines about when Watcher agents should be assigned or unassigned based on task type, complexity, and risk level. ## Troubleshooting Verify that: * The Watcher agent is still assigned in the Properties panel * Your task instructions are clear and specific * The agent has sufficient context about the issue * Your AI model configuration is set up correctly Try: * Checking the task history to see what the agent attempted * Reviewing error messages or logs for specific blockers * Providing additional context or clarification to the task * Manually unassigning and reassigning a fresh agent When you unassign a Watcher agent, a new agent will be automatically assigned on next task update. All Watcher agents have the same capabilities, so you're not selecting between different types. Review the task history and activity log to see: * Actions the agent suggested * Changes it made or attempted * Course corrections it provided * Any errors it encountered ## Next steps Create new tasks and let Watcher agent manage them Learn how to update and refine your tasks Combine with auto-processing for fully autonomous workflows Connect more sources for Watcher agent to monitor Questions about Watcher agent? Reach out via the livechat widget on our platform for quick support or [schedule a call](https://cal.com/pateladi/support) with our team.