| Who each product is built for | Work on Repeat is built for solo businesses, consultancies, startups, and lean teams putting recurring knowledge work on a schedule. | Gumloop presents hosted agents and workflows for teams automating work, including recurring agent tasks and a canvas for orchestrating multi-agent workflows; its workbooks provide a shareable visual automation surface. |
|---|
| How work is defined | A routine owns its instructions, model, inputs, schedule or API trigger, connected tools, and delivery settings. | Gumloop documents agents as adaptive assistants that decide which tools to use, workflows as fixed-path automations, and workbooks as canvases that can contain multiple workflows in tabs. |
|---|
| How recurring work starts | Routines support five-field cron schedules with an IANA timezone, plus manual and API runs. | A Gumloop agent can use an app trigger, a recurring scheduled trigger such as every weekday at 9 AM, a one-time trigger, or a trigger created with AI. Gumloop workflows support daily, weekly, or custom time-based schedules, webhooks, and service-specific events; manual time settings include minute, hour, day of month, month, day of week, timezone, and maximum failure count. |
|---|
| How systems are connected | Built-in providers plus generic remote MCP connections expose approved tools to routines. | Gumloop documents 150+ connectors, including Gumloop-managed connectors and custom MCP servers; the connected apps determine what an agent can access. For connected apps, Gumloop can use a personal default, a pinned specific account, or a team default for team agents, and its Tool Management panel can set allow, ask, or deny behavior per tool. |
|---|
| How actions are bounded | Every MCP tool begins disabled; enabling it and allowing automatic execution are explicit per-routine decisions. | Gumloop agents support human approval presets and per-tool allow, ask, or deny controls; App Rules can block or flag specific tool calls at the agent or organization level. Gumloop documents additive organization and team roles on Pro and above, with some feature roles and custom restrictions requiring Enterprise; the pricing page lists agent-scoped connector guardrails on Pro and organization-wide guardrails plus role-based access control on Enterprise. |
|---|
| How runs and usage are inspected | Work on Repeat persists run, model-step, tool-call, error, usage, and webhook-attempt history. | A Gumloop workbook run report shows real-time node progress, and Previous Runs exposes current and past executions, success or failure status, and detailed node information. Gumloop agent conversations remain available in chat history unless incognito mode is used, and the Pro plan lists 5 concurrent workflow runs and 25 concurrent agent chats. |
|---|
| How packaging is measured | Free is $0 with no card and includes 1 active routine, 10 run starts per UTC month, 1 connection, 7 days of history, 1 concurrent run, 3 model steps per run, read-only API access, and $0.50 of upstream AI usage. Pro is $39 monthly and includes 10 active routines, 250 run starts per Stripe billing month, 10 connections, 90 days of history, 2 concurrent runs, 4,000 model steps per run, full API access, signed result webhooks, and $10 of upstream AI usage. Business is agreement-based, with allowances configured for the customer's operating requirements. | As reviewed on 2026-08-13, Gumloop lists Pro starting at $37 per month with 7,400 credits plus 12,600 bonus credits (20,000 per month), unlimited seats, 5 concurrent workflow runs, and 25 concurrent agent chats. |
|---|
| What switching requires | Users manually recreate one responsibility, connect its systems, prove a manual run, inspect the result, and then schedule it. | The official Gumloop sources reviewed for this profile do not document an automatic import into Work on Repeat, so none is promised here. |
|---|
