# Schedules for Managed Deep Agents: Cron jobs, prompts, and Slack delivery

## Executive summary

This video demonstrates how to implement automated, recurring tasks using Schedules for Managed Deep Agents. By configuring cron jobs, agents can run autonomously to generate and deliver structured reports (e.g., a weekly Salesforce pipeline summary) to external channels like Slack, without manual intervention. The process involves defining the schedule syntax, deploying the agent to LangSmith, and ensuring the agent has access to necessary tools and context.

## Key takeaways

- Automated Reporting via Cron Jobs: Schedules allow agents to send recurring messages that invoke tools or leverage context, such as generating a weekly pipeline summary for the sales team.
- Schedule Configuration: Schedules are defined by creating a file in the schedules directory, specifying a cron job, a time zone, a prompt, and optional input context.
- Deployment and Monitoring: The scheduled agent must be deployed to LangSmith using a deploy command, allowing users to inspect the configured cron jobs and prompts within the LangSmith UI.

## Technical details

- Agent Architecture: Managed Deep Agents can be configured with instructions and tools (e.g., access to Salesforce) to perform complex tasks.
- Scheduling Syntax: Schedule definition requires a cron expression, a specific prompt, and the ability to configure input context (e.g., a user message).
- Integration and Tools: Real-world tool connections, such as Salesforce, should utilize an MCP server. The agent can also be configured to deliver results directly to specific channels, such as Slack.
- Deployment Workflow: To activate the schedule, the agent must be deployed to LangSmith, which publishes the agent and configures the cron job.

## Practical implications

- Automating routine business intelligence reports (e.g., weekly sales summaries) directly into communication channels like Slack.
- Building reliable, scheduled workflows that leverage LLM reasoning and external tool access (e.g., Salesforce data).
- Ensuring that scheduled agents retain the capability to answer ad-hoc questions when needed, maintaining flexibility.
- Using LangSmith as the central platform for deploying and monitoring scheduled agent runs.

## Topics

Managed Deep Agents, LangChain, LangSmith, Cron Jobs, Automation, LLM Orchestration, Salesforce Integration, Slack API, Schedules docs, Connect a Slack channel

Source: https://www.youtube.com/watch?v=-mWWsvv19jE