Every agent below comes from the same first-party catalog inside Boring. Selecting one creates a private, editable draft — never a live agent. Connect the required tools, review its permissions and approval gates, test it, then publish when the behavior is right.
Agents
38 agents
pipelines, reporting & alerting
Every morning, digest Linear, Fireflies, Gmail & Calendar into a stack-ranked Slack brief.
Turn meeting decisions into reviewed tasks and a lasting decision log.
Draft a source-linked weekly update from project systems for human review.
Every morning, catch Shopify items below their reorder point and draft supplier purchase emails for approval.
Every morning, list the threads where you are waiting on someone and the promises you made that are coming due.
CI, releases & on-call automation
Propose and apply reviewed cleanup for stale, duplicate and unowned issues.
When PagerDuty opens an incident, start the Slack thread, open the ticket, and draft status updates for approval.
When a Jira bug is filed, check for duplicates, propose priority and component, and flag critical ones in Slack.
Review a labeled Linear queue for stale, canceled and completed agent-created issues without editing them.
Find failed, disabled and unusually old workflow runs across a configured repository list without rerunning anything.
invoicing, approvals & reconciliation
Route invoices described in email bodies for approval; flag attachment-only invoices for review.
Record invoice and receipt details from email bodies in a duplicate-safe ledger; flag attachment-only items for review.
Each week, draft tone-matched reminders for overdue QuickBooks invoices and send only what you approve.
Compare last month's QuickBooks P&L to your budget sheet and explain the variances that matter.
Each week, warn owners about vendor contracts nearing renewal, with the notice deadline worked out from your register.
Track vendor and subcontractor insurance certificates, and request renewals before they lapse.
onboarding, offboarding & employee workflows
provisioning, access & incident response
Review Okta access and prepare a Slack handoff.
Check a supplied departure list for remaining GitHub access and report gaps without changing accounts.
Compare selected repositories with an explicit visibility and branch-protection policy and report unverified checks.
Review a bounded set of dependency alerts against available source evidence and recommend what needs human attention.
campaigns, content & social automation
Check public pages for accessibility issues, broken links, and copy mistakes.
Turn a research question and public sources into a cited brief and review-ready Notion draft.
Rewrite weak Shopify product titles and descriptions in your brand voice, and publish only approved changes.
Each week, check your competitors' pricing, product, and news pages and report only what changed, with sources.
When a customer pays in full, draft a personal review request that mentions their actual job, sent after your approval.
lead routing, enrichment & follow-up
Enrich and route new leads to reps.
Every weekday morning, a Slack brief on each external meeting covering who is attending, what HubSpot knows, and what changed.
Every Monday, show where the HubSpot pipeline moved, what is stuck, and what is likely to close.
When a HubSpot deal reaches a pricing stage, check its discount and route anything outside policy for approval.
Catch proposals and quotes with no reply, read the thread, and draft a follow-up that answers what they actually said.
Each evening, log the day's customer emails and calls to the right HubSpot records so the CRM matches what happened.
Read incoming invitations to bid, score them against your criteria, log them, and hold the deadlines on your calendar.
ticket triage, replies & escalations
Summarize, search docs and open a ticket.
Turn a week of Zendesk tickets into a ranked, quote-backed feedback digest in Notion.
Answer "where is my order" emails with real Shopify order and tracking details, sent only after you approve.
Turn Zendesk tickets tagged as bugs into clean, deduplicated Jira issues engineering can act on.
Every Friday, draft each client a status update from the week's Asana work, meetings, and email, sent after your review.
An AI agent starts with a definition of work your team already understands: the inputs it needs, the steps it should attempt, and the rules it must follow. It is useful when the same outcome comes up repeatedly but the path depends on context. An invoice may need a purchase-order check, a support email may need a severity decision, and a weekly update may need evidence from several project systems. The agent gives that work a concrete starting point.
Pick a workflow whose owner can explain a good result and recognize a bad one. That person should also know which exceptions deserve attention. Avoid starting with an entire department or a promise to automate everything in an inbox. A narrow job is easier to test, easier to review, and easier to stop when the instructions do not match reality. Keep one person accountable for the first version, even if several teammates will review its work.
Every published agent shows the instructions behind its workflow and the tools it expects to use. Read those details before treating the title as a fit. Invoice approval routing, for example, is about checking and routing an invoice; it is not permission to make payments. Lead routing assigns work internally; it is not an outbound sales campaign. The guardrails explain where the draft should stop, ask, or hand a decision to someone else.
Compare those assumptions with your team's process. Write down the source of truth for amounts, ownership, severity, or access rights. If two systems disagree, decide which one wins before the agent runs. A useful draft makes missing information visible. It should not guess an approver or silently choose a customer record because that is the quickest way to finish the task. Review any instruction that leaves that choice ambiguous.
Review the invoice approval agentThe integration names on an agent describe its expected working environment. You still need to connect the accounts in your workspace and review the exact actions available to the agent. A logo in the catalog does not establish that your account has the necessary access, that a particular action is enabled, or that a destination exists. Check the mailbox, project, channel, folder, and account before testing a write.
Keep the first setup small. If the work needs Gmail and Jira, begin with the relevant mailbox and project rather than attaching every tool your team uses. Record who owns each connection and who can repair it if access changes. When adapting an agent to a different system, review the instructions as well as the tool selection. Replacing a CRM name does not automatically translate field mappings, duplicate rules, or team ownership.
Check the integrations catalogReview should happen where a decision matters. Reading a source document and drafting an internal summary may need different controls from sending a customer reply, changing access, or writing to a shared system. Name the reviewer for consequential actions and make sure they can see the destination, proposed change, and supporting context. A request that says only approve or reject leaves too much work with the person holding the gate.
The agent's written guardrails describe intended behavior; review the configured permissions and approval gates during setup too. Decide what should happen when the reviewer rejects a request or the required information is missing. Keep the first draft private until those paths make sense. Starting from the library does not publish an agent, connect its tools, or grant permission for every action mentioned in the instructions.
Plan the approval pathA clean example proves less than it appears to. For invoice routing, include a missing purchase order, an amount mismatch, and a duplicate invoice. For support triage, include an unclear product area and a message that needs immediate human attention. For onboarding, leave out a required field and verify that the workflow asks instead of inventing it. These examples reveal whether the instructions express your real policy.
Inspect the result and the run trace together. Confirm that the right records were read, the intended destination was used, and the reviewer saw enough information. Use controlled accounts or destinations for tests that may write to connected systems. Keep a short record of what passed, what failed, and which instruction changed. The goal is a workflow the owner can explain, not just a run that reaches a completed state.
Choose the trigger only after the draft behaves as expected. A schedule, an event, and a manual run each need a clear input boundary. Decide who checks the first runs and where unresolved cases should go. When the workflow reports a partial result, read what actually happened before trying again. Repeating a run without checking existing records can create extra work in the very system you are trying to simplify.
Keep dependable fixed automations where they already serve the team well. An agent earns its place when context, judgment, and review are part of the job. If you want help shaping that first workflow, Boring's services team can discuss the process and implementation with you. The same questions still apply: who owns it, which tools it touches, what needs approval, and what evidence counts as a successful result.
Discuss implementation helpNo. It creates a private, editable draft. Connect the tools, review permissions and approval gates, test representative cases, and publish only when the behavior is right for your workspace.
Yes. Treat the agent as a starting point. If you change a system or destination, also review the instructions, expected fields, permissions, and exception handling. Test the adapted draft before publishing.
Choose a recurring job with a clear owner, available inputs, and a result you can check. Start where review or coordination takes time, and keep the first workflow small enough to evaluate with real examples.
No. Connected account access, input quality, configured actions, and human decisions all affect a run. The agents include guardrails and setup requirements so you can evaluate the workflow before using it for live work.
Request access and tell us which agent fits — or bring your own workflow and we'll shape the private draft with you.