Coming from Relevance AI?
Relevance AI offers agents, no-code tools, workforces, triggers and approvals; the captured pricing places Agent Evaluations on Enterprise. Whenever fits a defined procedure you want to supervise through rules and results. AI writes the code, which runs fixed non-AI logic deterministically with the same inputs and dependencies. Optional model steps and external state can change outcomes and costs. Free AI building has weekly limits; reading code is optional.
What you get on Whenever
Runs and runtime AI on one plan
Whenever meters each workflow run, and runtime AI draws on the plan’s included AI spend; AI building and editing are free within weekly usage limits. Relevance AI counts each run of a Tool as one Action, so compare both on the same workload.
Review it, then publish
The same plain-language brief becomes a TypeScript workflow; review its summary and sample results before publishing, as Relevance AI also keeps edits in a draft until you publish. The published procedure decides its steps. This applies to fixed non-AI logic with the same inputs and dependencies; optional AI and changing external state can change outcomes. You can review the summary and results without reading code.
A model only where you add one
AI writes the workflow once, and a published run calls a model only at the steps you include. Relevance AI tool-to-tool connections can likewise run without an agent; agents are where its model chooses the tools.
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.
An action per tool call, or a run per workflow.
Relevance AI counts Tool runs directly or through agents and workforces. Vendor credits separately cover model and tool costs. Whenever counts executions plus runtime AI; price the actual workload.
Relevance AI
Actions + vendor credits
Tool executions, plus vendor credits for model and tool costs
Published tiers from Pro to Enterprise, with build users and end users counted separately.
Relevance AI counts an Action when a tool runs, directly or through an Agent or Workforce, including failed runs. Vendor credits cover LLM and tool costs separately; bringing your own API keys bypasses Vendor Credits, not every usage cost. Apply the relevant allowances and overages to a representative workload; counts alone do not establish a cheaper dollar bill.
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
Relevance AI
Relevance AI says agents “decide how to use tools to achieve goals prompted by you”. The platform also documents tool-to-tool connections that run “without requiring agent intervention”, so a chain you configure that way is not model-directed.
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
Relevance AI
Actions count tool executions, whether run directly or through an Agent or Workforce, including failures. Vendor credits separately cover model and tool costs. Both the execution path and selected services affect the bill.
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
Relevance AI
Relevance AI offers a no-code tool builder, API and Python steps, agents and workforces. Its Python documentation supports custom packages; CPU, GPU and memory options depend on the backend, including Modal Labs.
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
Relevance AI
Relevance AI documents data exports as CSV, Excel or JSON and hosted agent configuration. Exporting data is not the same requirement as moving the agent runtime; confirm that separately before migrating.
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
Relevance AI
Relevance AI documents task history, including filtering tasks by tool, and agent version history. Its captured pricing lists Agent Evaluations on Enterprise; confirm the plan needed for your diagnostic workflow.
Whenever
Read the procedure and the execution log together, then re-test the failing input. External data and any explicit model call still have to be accounted for when reproducing a failure.
Where the AI cost lands
Relevance AI
Vendor credits cover model and tool costs, and bringing your own API keys bypasses them; fixed tool-to-tool connections need not ask an agent to choose the next step.
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 Relevance AI
Relevance AI
Consider Relevance AI when agent judgment, human approvals, evaluations and team controls are central to the job. Check the plan and deployment requirements for those features rather than assuming a fixed procedure replaces the platform.
Whenever
Consider Whenever for the part that has stopped needing judgement: the same records, the same rules, the same destinations, every time. That is a narrower product on purpose, and it does not replace an agent platform.
Where it runs
Relevance AI
The documented managed deployment uses a selected region and a multi-tenant architecture, with a separate service and database for Enterprise customers with fine-grained access controls. The security page says the region cannot be changed after the organization is created, with support available to discuss options, and describes single-tenant options as in development; confirm deployment needs directly.
Whenever
Hosted and scheduled: a webhook, a cron schedule or on demand, with credentials managed for you.
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
- Pricing - Relevance AI Documentation
- Plans and credits - Relevance AI Documentation
- Tool to Tool Configuration - Relevance AI Documentation
- Security overview - Relevance AI Documentation
- Agents - Relevance AI Documentation
- Triggers - Relevance AI Documentation
- Python Tool step - Relevance AI Documentation
- Approvals and Escalations - Relevance AI Documentation
- Tools - Relevance AI Documentation
- Give Your Agent Tasks - Relevance AI Documentation
- Build with Invent - Relevance AI Documentation
- Version history - Relevance AI Documentation
Start with a workflow brief
Pick a starting point, connect your accounts and review what Whenever builds before publishing.
Build this workflowAnnounce closed-won deals in SlackCelebrates each won deal in Slack with the numbers and a short recap of how it was won.
Build this workflowPublish Instagram posts from a calendarPublishes due rows from your Instagram calendar on the cadence you choose and writes each post link back.
Build this workflowLog survey responses and alert on low scoresAdds each survey response to Google Sheets within minutes and emails the owner when the score falls below your threshold.
Build this workflowTrack keyword rankings in a sheet each weekChecks the search position of every keyword on your list, appends the history to a sheet and reports the moves.
Build this workflowRoute large expense claims to a managerLogs every expense submission in a sheet and alerts a manager in Slack when the amount is over the approval limit.Build this workflowStart with one agent task you already trust.
Bring one repeatable task. Describe it once, and Whenever writes it as a workflow you review before it runs.
Pick a task with a fixed shape
Choose an agent task whose inputs, rules and destination no longer change between runs. Record its trigger, the tools it calls in order, and what a correct result looks like.
Separate the judgement from the procedure
Keep the steps that need a model in Relevance AI, or make them one explicit call inside the workflow. Describe the rest and Whenever’s AI writes it. Review the workflow summary and sample results; inspect TypeScript if useful, then connect each integration in Whenever.
Run both, then switch the trigger
Test with safe records, including the ambiguous cases and a repeated event. Compare the outcome against the agent’s, then pause the original trigger before publishing the new one so the work is not done twice.