| 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. | Lindy presents itself as an AI teammate for the whole team, connected to company tools and available through conversational surfaces including Slack, iMessage, Gmail, and the browser. |
|---|
| How work is defined | A routine owns its instructions, model, inputs, schedule or API trigger, connected tools, and delivery settings. | Lindy defines a routine as a saved instruction attached to a user's Lindy rather than a separate bot, with a trigger, a plain-English prompt, and a result destination. Lindy's pricing page places model selection in its common included-feature list and says users can choose a model per task, with most major models available. |
|---|
| How recurring work starts | Routines support five-field cron schedules with an IANA timezone, plus manual and API runs. | Lindy routines can run on daily, weekly, or monthly schedules, or on documented events such as email, Slack, calendar, and meeting events. Personal routine results can go to Lindy chat, text, or Slack DM, while workspace routines post to a Slack thread reply or channel. |
|---|
| How systems are connected | Built-in providers plus generic remote MCP connections expose approved tools to routines. | Lindy's integrations catalog currently advertises 1,000+ integrations and includes Any MCP Server alongside packaged apps. Lindy's Any MCP Server page says a user can ask Lindy to connect a server, approve the connection when prompted, and then delegate plain-language work through it, including repeated work saved as a routine. |
|---|
| How actions are bounded | Every MCP tool begins disabled; enabling it and allowing automatic execution are explicit per-routine decisions. | For shared Slack threads, each Lindy integration has a write guardrail: Always allow, Require approval, or Don't offer; approval requests use Approve and Deny actions in the thread. Lindy documents that these guardrails cover writes only and apply in shared Slack threads, not reads, web-app chat, Slack DMs, iMessage, or SMS; the requester or a workspace owner or admin can approve a guarded write. |
|---|
| How runs and usage are inspected | Work on Repeat persists run, model-step, tool-call, error, usage, and webhook-attempt history. | Lindy documents a versioned file system where users can inspect, edit, and correct files, including a History tab for files. Lindy's pricing page lists team files with version history in its common included features, while audit logs are listed specifically under Enterprise. |
|---|
| 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, Lindy lists Plus at $29.99 per user per month with 3,000 credits per user per month, Pro at $99.99 with 15,000, and Max at $199.99 with 35,000; Enterprise uses contact pricing and lists audit logs among its additions. Each paid seat contributes credits to one shared workspace pool, credits refresh each billing cycle without rollover, and Lindy pauses credit-using actions when the pool runs out. |
|---|
| What switching requires | Users manually recreate one responsibility, connect its systems, prove a manual run, inspect the result, and then schedule it. | The official Lindy sources reviewed for this profile do not document an automatic import into Work on Repeat, so none is promised here. |
|---|
