> ## Documentation Index > Fetch the complete documentation index at: https://slackhive.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Scheduled Jobs > Trigger any agent on a schedule and deliver reports, alerts, or digests to Slack automatically. ## Your agents don't just wait to be asked Most AI tools are reactive - you ask, they answer. Scheduled Jobs make your agents **proactive**. Set a schedule, point it at any agent, and it fires automatically - running queries, checking metrics, scanning for anomalies, and posting results directly to a Slack channel or DM. No dashboards to check. No reports to pull. The insight comes to you. *** ## What you can build If GMV drops more than 10% hour-over-hour, DM the CEO immediately with a breakdown by channel and cohort. Run a fraud check every hour. If anomalies are detected, post a summary to `#fraud-alerts` with transaction IDs and risk scores. Every morning at 8 AM, post yesterday's key metrics - bookings, revenue, churn, NPS - to `#analytics`. Every Monday, summarize last week's PRs, incidents, and deploy count. Post to `#engineering`. Check stock levels every 4 hours. DM the ops lead if any SKU drops below threshold. Every 30 minutes during business hours, check ticket queue depth. Alert `#support-ops` if SLA is at risk. *** ## How it works Pick an agent, write a prompt, set a schedule, and choose where results go - a Slack channel or a direct message. At the configured time, SlackHive sends your prompt to the agent - exactly like a Slack message, but automated. The agent executes fully - it can run queries, call APIs, check metrics, compare against thresholds, and reason about the results. The response is posted to the channel or DM you configured. Long reports are organized into a parent message and thread so channels stay readable. *** ## Any agent, any schedule Jobs are not limited to boss agents. Assign a job to any agent: | Agent | Job example | | ---------------- | -------------------------------------------------------- | | `@data-analyst` | Run revenue query every morning, post to `#finance` | | `@devops` | Check error rates every 15 min, DM on-call if spiking | | `@fraud-bot` | Hourly transaction anomaly scan, post to `#fraud-alerts` | | `@support-agent` | Check ticket backlog every 30 min, alert if queue > 50 | | `@boss` | Daily summary across all teams, post to `#general` | *** ## Creating a job Go to **Jobs** in the sidebar → **New Job**. Give it a clear name - e.g. `Daily Revenue Digest` or `Hourly Fraud Check`. Select which agent should run this job. Pick the specialist best suited for the task. Write exactly what you'd say to the agent in Slack. Be specific about what to check, what thresholds matter, and what to include in the response. ``` Check GMV for the last hour vs the same hour yesterday. If it's down more than 10%, flag it as urgent and include a breakdown by acquisition channel. Otherwise just post a one-line summary. ``` Use a cron expression or pick a preset: | Preset | Cron | | ---------------- | -------------- | | Every hour | `0 * * * *` | | Every 15 minutes | `*/15 * * * *` | | Daily at 8 AM | `0 8 * * *` | | Weekdays at 9 AM | `0 9 * * 1-5` | | Weekly on Monday | `0 9 * * 1` | The UI shows cron expressions in plain English so you can verify the schedule before saving. Choose where the agent posts its results. Post results publicly to any Slack channel - `#analytics`, `#fraud-alerts`, `#engineering`, etc. **How to get the channel ID:** 1. Open Slack and right-click the channel name in the sidebar 2. Click **Copy link** 3. The link looks like: `https://app.slack.com/client/T.../C08ABCD1234` 4. The channel ID is the part starting with `C` - e.g. `C08ABCD1234` Paste it into the **Target** field and select **Channel**. Make sure the agent's Slack bot has been invited to the channel first. If not, invite it with `/invite @agent-name`. Send results as a direct message to any individual - CEO, on-call engineer, finance lead, or yourself. **How to get the user ID:** 1. In Slack, click on the person's name or profile picture 2. Click **View full profile** 3. Click the **⋯ More** button (three dots) 4. Click **Copy member ID** 5. It looks like: `U012AB3CD45` Paste it into the **Target** field and select **DM**. The message arrives as a direct message from the agent's Slack bot - clean and personal. Add a **Skip notification when...** condition when you only want Slack messages for meaningful results. ``` there are no fraud cases to report ``` If the run completes and that condition is true, SlackHive records the run as skipped and does not post a message. *** ## Channel vs DM - when to use which | Use case | Channel | DM | | ------------------------------------------------------ | ------- | -- | | Team-wide reports (daily digest, weekly summary) | ✅ | | | Public monitoring dashboards (`#fraud-alerts`, `#ops`) | ✅ | | | Personal alerts (CEO wants GMV drop notification) | | ✅ | | On-call paging (engineer gets error spike alert) | | ✅ | | Sensitive metrics (revenue, churn - exec-only) | | ✅ | | Cross-team awareness (PM, data, eng all need to know) | ✅ | | You can create multiple jobs for the same agent - one that posts to a channel for team visibility, and another that DMs the team lead for immediate personal attention. *** ## Writing effective job prompts The prompt is the most important part. A few principles: **Be specific about what to check** ``` ❌ Check the data ✅ Query bookings for the last 24 hours and compare to the 7-day average ``` **Define what "notable" means** ``` ❌ Let me know if anything is wrong ✅ Flag if conversion rate drops below 3% or if any single channel drops more than 20% week-over-week ``` **Tell it what to do in each case** ``` ✅ If everything looks normal, post a one-line summary. If something needs attention, include the specific numbers, what changed, and your best hypothesis for why. ``` **Use skip notifications for noisy checks** ``` Prompt: Check failed payments in the last hour and summarize any customer impact. Skip notification when: there are zero failed payments or no action is needed. ``` This keeps monitoring jobs useful without filling channels with "nothing happened" messages. **Give it context it might need** ``` ✅ Note: Tuesday is always lower due to our weekly maintenance window. Don't flag Tuesday dips unless they exceed 30%. ``` *** ## Rich Slack formatting Scheduled jobs aren't limited to plain text. Agents can post **Slack Block Kit** payloads - tables, sections, dividers, buttons - for readable reports. Ask the agent in your prompt: ``` Post the results as a Slack table: columns for channel, conversions, week-over-week change. Use Block Kit. Highlight anything down more than 10% in red emoji. ``` Under the hood the agent emits a `postPayload` with `blocks` - SlackHive delivers it to Slack verbatim. The rendered message has proper columns, section headers, and colored highlights instead of a wall of text. When to use: * Daily digest with multiple metrics - tables are much easier to scan * Fraud alerts with transaction IDs - columns keep fields aligned * Weekly engineering report - sections with dividers between topics For simple one-line alerts, plain text is still best. Reserve rich formatting for reports with structure. ### Keep long reports readable A long report is posted as several messages: the first becomes the channel-visible **parent**, and the rest goes into a thread beneath it. Use the parent for the headline, status, and "what changed"; put detailed tables and evidence in the thread. If you want exact control over where the thread starts, ask the agent to put this break marker on its own line: ``` {your headline summary} *Table 1* | ... | ``` SlackHive removes the marker before posting. *** ## Monitoring job runs Every job run is logged - status, output, duration, and timestamp - visible in **Jobs → \[job name] → Run History**. | Status | Meaning | | --------- | ------------------------------------------------------------------- | | ✅ Success | Agent ran and posted to Slack | | ⏭ Skipped | Agent ran successfully, but the skip-notification condition matched | | ❌ Error | Agent not running, backend error, or Slack API failure | If a job fails, the error is logged in run history. Common causes: the agent's Slack app token expired, the agent wasn't running, or the MCP server the agent needed was down. *** ## Example: GMV drop alert Here's a complete setup for a GMV monitoring job: | Field | Value | | -------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Name** | Hourly GMV Alert | | **Agent** | `@data-analyst` | | **Schedule** | `0 * * * *` (every hour) | | **Target** | DM → CEO's Slack user ID | | **Prompt** | Compare GMV for the last hour vs the same hour last week. If it's down more than 15%, send an urgent alert with a breakdown by channel, device type, and acquisition source. | | **Skip notification when** | GMV is within the normal range and no action is needed | The CEO only gets a DM when something needs attention. When something breaks, they know immediately - with the breakdown already in their pocket. *** ## Who can see and create jobs | Role | Can see jobs | Can create / edit / delete | | ---------------------- | -------------------------- | --------------------------- | | **Superadmin / Admin** | All jobs | ✅ | | **Editor** | Jobs for accessible agents | ✅ (edit-access agents only) | | **Viewer** | Jobs for accessible agents | ❌ read-only | Jobs are filtered by the agents a user can access — an editor only sees jobs assigned to agents they own or were granted access to. Viewers see the same filtered list but cannot make changes. When creating a job, editors can only pick agents they have **Edit** access to. Agents where they only have View or Trigger access won't appear in the agent dropdown. *** ## Next steps Build the specialist agents that power your jobs. Connect agents to your data sources so jobs can query real data.