Coming from Lindy?
Lindy supports model-led assistant work and personal Python routines that can finish without waking the model. Whenever is an alternative for a defined business procedure: describe its rules, review sample results and run the published code with managed connections. Optional AI steps still use models and can vary. AI building has weekly usage limits; the workflow file is yours.
What you get on Whenever
The whole job, one file
Describe the business procedure and AI writes TypeScript with workflow triggers. The file is available to inspect and export; this does not establish that Lindy routines cannot be exported.
Connections come with the workflow
Credentials are managed for you, so the published code already has the API access the job needs. Connecting a service and writing the thing that uses it are not two separate exercises.
Separate runs from runtime AI
A workflow execution counts once. Runtime AI usage is separate from the run allowance and from weekly AI-building limits. Lindy script-only routines may also avoid model calls, so do not assume moving them saves tokens.
A concrete decision
Illustrative scenarios, not customer results or recorded runs.
Greg: no “done” without the invoice receipt
Illustrative decision, not a recorded customer run: Greg wants each paid order checked against Stripe, then an invoice created, its ID saved, and only then a confirmation sent. He specifies that an invoice failure must stop the confirmation, and an already-handled order must not be charged or invoiced again. He checks the summary, sample records, provider receipts and run history—not source code. Test a missing payment, a failed invoice and a duplicate event before publishing. Whenever fits when those prescribed steps matter more than an agent deciding them again; a fixed workflow elsewhere can fit too. No screenshot here claims these actions were actually delivered.
Jaunius: make the edge cases explicit
Illustrative decision, not a benchmark: Jaunius needs all pages of 5,000 contacts, a saved last-seen ID, updates only for changed records and a clear record of which writes failed. He brings the old workflow and sample inputs, reconnects accounts, and tests pagination, an API failure and a repeated event before switching triggers. Choose a single procedure if it makes this logic easier to maintain; the other tools can also support complex logic. An optional model that classifies a note can vary and adds runtime AI usage. Compare the monthly subscription and actual usage, not the number of steps alone.
Compare the routine, not the stereotype.
A model-led assistant routine and a saved Python script have different cost profiles. Whenever offers a focused TypeScript workflow alternative.
Lindy
Seats + shared credits
Subscription credits pooled across the workspace
Usage depends on the work Lindy does. Top-ups, spend caps and overage rules apply.
A Lindy task is not a fixed number of credits. Personal script routines can finish without waking the model, changing the cost profile. Compare the routine mode you actually use, along with your team’s shared credit consumption, not a blanket tasks-per-dollar estimate.
A run is one execution of one workflow, start to finish. AI building and editing are free within weekly usage limits; runs are metered separately.
A closer look
What changes when you describe the job in plain language and code runs it: to build, to run, and to keep.
Repeatable execution logic
Lindy
Personal routines can become Python scripts: finish without waking Lindy, ask it for judgment, or wake it to repair a crash. Workspace routines cannot use that conversion. Not every Lindy run requires a model decision.
Whenever
AI writes it, then published code runs the same execution logic. With identical inputs and dependencies, non-AI logic is deterministic. Changing API data, time, randomness or an optional model step can change results; this is not an exactly-once delivery guarantee.
Runs per dollar
Lindy
Per-user subscriptions contribute credits to a shared workspace pool. Usage varies with the work performed; current docs describe top-ups, no monthly rollover, spend caps and overages.
Whenever
Pro includes 10,000 runs per month; see the pricing page for current US dollar prices. AI building and editing are free within weekly usage limits. Published runs are metered separately: the meter counts the whole run, not individual steps. External services and optional model calls can have their own charges.
What you can express
Lindy
Personal and team routines connect triggers, prompts and destinations for email, Slack, calendar and meeting work. Script mode adds Python for personal routines, alongside conversational team delegation.
Whenever
Describe the rules you already know; AI writes the procedure. Review the summary and sample results, not necessarily the code. Keep an explicit model step for judgment. Agent platforms may also offer fixed workflows or scripts; compare the mode you actually use.
Export and portability
Lindy
Lindy documents versioned files: personal files are editable, team files depend on owner or admin permissions, and system files are read-only. Personal Python routines are real code; do not infer a complete portable runtime from file access.
Whenever
The TypeScript is yours: read it, edit it, export it, take it with you. Moving it to another runtime can require adapting managed connections, triggers and runtime-specific integrations.
Debugging a failed run
Lindy
Inspect routine configuration and versioned files. Script mode can wake Lindy for repair after a crash, which differs from a fixed procedure that stops for you to diagnose and revise.
Whenever
Inspect the workflow code and execution log, then deliberately change and test the procedure. External state and any explicit model call still need to be considered when reproducing a failure.
Where the AI cost lands
Lindy
Model-led work consumes credits, but a personal Python routine can complete without waking Lindy. Script routines do not inherit connected Gmail, Slack or Calendar credentials, so API access must be considered separately.
Whenever
AI writes the workflow once, with free building subject to weekly AI usage limits. A published procedure runs its steps without a model choosing them. Any model call you explicitly include still runs and has its own cost.
When to keep Lindy
Lindy
Keep it for proactive inbox and meeting help, contextual drafts, follow-up tracking and Slack-based delegation. If a personal script routine already handles your status checks predictably, migrating may not improve the job.
Whenever
Consider Whenever when the work is a stable API procedure and you want its TypeScript and managed connections to be the main artifact. It is not a replacement for all of Lindy’s assistant context or team experience.
Sources and scope
Official sources captured on the date shown below. These describe published features and billing rules, not independent performance tests. Check the linked documentation for current modes, plans and limits. No competitor dollar price is asserted.
Checked
Inbox and calendar jobs to start from
Starter briefs for related jobs, not recorded runs. Connect authorised accounts, confirm trigger and plan requirements, then review and test the workflow before publishing.
Build this workflowCapture a form lead and start the follow-upEnriches each form lead, drafts the right follow-up email in Gmail, and opens a task for the rep who owns the contact.
Build this workflowWelcome new contacts from a spreadsheet listWatches a Google Sheets contact list and sends the welcome or follow-up email the status column asks for.Build this workflowDeliver a lead magnet and start the nurtureEmails the download link within minutes of the request and adds them to the Mailchimp audience that runs your nurture.
Build this workflowAcknowledge contact form leads within minutesLogs each contact form submission, sends an acknowledgement within minutes, and alerts the on-duty rep in Slack.
Build this workflowSend outreach from your lead spreadsheetSweeps a Google Sheets lead list and sends the tailored outreach email for every row you mark ready.Build this workflowStart with one Lindy routine.
Start with a routine whose rules are clear. You describe it, Whenever writes it, and what you keep is one readable file.
Identify personal, team or script mode
Record the trigger, prompt or Python script, destination, files and expected result. Separate assistant context from explicit business rules so it is clear what must be recreated.
Review the procedure and API access
Describe the job and Whenever’s AI writes it. Check its summary and sample outputs; code inspection is optional. Reconnect each required service; a Lindy script’s readable code does not mean its integration access transfers automatically.
Test before pausing the routine
Compare safe examples, including missing context and cases needing judgment. Check destinations and permissions, then pause the old routine before enabling the new schedule or webhook.