Turn monitoring alerts into a remediation plan
Takes each monitoring alert, gathers recent repository context, drafts a remediation plan, and hands it to the on-call engineer.
Temporal is a durable-execution engine you program against with an SDK and run on Workers you operate, with the service self-hosted or on Temporal Cloud; Whenever hosts a reviewed TypeScript workflow with managed triggers and integrations, priced per run.
By Whenever team · Updated · Workflow behavior and runtime limits
Whenever hosts the published workflow, its triggers and its credentials. Temporal documents that Worker Processes are hosted and operated by you, whether the Temporal Service is self-hosted or on Temporal Cloud.
Claude Code, Codex or Cursor turns the task into a TypeScript workflow module and saves it as a draft over MCP; you complete Setup and publish.
A run is a run, however many steps it has.
Temporal Cloud bills Actions, storage and a support plan, and a self-hosted Temporal Service runs on your infrastructure. Whenever counts whole workflow runs, with optional runtime AI on top.
Consumption-based: Actions, storage and a support plan
Action (a billable operation) plus storage in gigabyte-hours
Temporal Cloud Developer, Business, Enterprise or Mission Critical plans, or self-hosted
$39/mo
10,000 runs per month
Find the right plan for youTax exempt for this offering.
At full use of 10,000 included runs, $39 ÷ 10,000 ≈ $0.0039/included run. This is an allowance average, not a per-run tariff, overage price or competitor savings claim. The monthly subscription is still $39 if you use fewer runs; unused allowance, runtime AI usage, moving to a larger plan and external charges change your effective cost.
Temporal Cloud counts Actions such as starting Workflows, recording a Heartbeat or sending messages, plus Active and Retained Storage in gigabyte-hours; a self-hosted Temporal Service runs on infrastructure you deploy and operate. Count the Actions one representative run generates rather than equating Actions with runs. No competitor dollar price is asserted.
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.
What changes when you describe the job in plain language and code runs it: to build, to run, and to keep.
A Temporal Workflow Definition must be deterministic to support replay; non-deterministic work such as API calls and model invocations goes in Activities, which the Temporal Service retries by policy.
AI writes the procedure; published code runs its fixed logic. Optional AI steps can vary, and external data, time or randomness can change results. Fixed logic does not guarantee exactly-once delivery.
Temporal Cloud bills Actions (billable operations such as starting a Workflow, recording a Heartbeat or sending a message) and storage in gigabyte-hours, plus a support plan; a self-hosted service runs on your own infrastructure.
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.
Workflows and Activities written in one of eight SDK languages, with Timers, Signals, Queries, Updates and Schedules; your Workers need their own network access and credentials for the services they call.
A TypeScript workflow module with 1,400+ managed integrations, HTTP and MCP calls, and schedule, webhook, event and manual triggers, within the documented runtime limits.
Temporal is open source and MIT-licensed; a Temporal Application is code you write against a Temporal SDK: Workflow and Activity Definitions plus Client and Worker configuration.
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.
The Web UI shows the input, output and Event History of any execution, including which Activity failed; when a Worker crashes, the Temporal Service hands the work to another Worker, which replays the history and resumes.
Each step’s recorded result, a debugger with breakpoints on a saved version, and an email on the first failure. A failed run is not retried or resumed for you.
Temporal puts LLM invocations in Activities in your own code; Temporal Cloud Actions are billable operations between your application and Temporal Cloud.
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.
Once started, a Workflow runs to completion, whether that takes seconds or months; state is captured at every step and a Workflow can be recovered, replayed or paused.
No replay or resume; a run may take up to an hour.
You run the Worker Processes that execute your code; the Temporal Service is self-hosted or Temporal Cloud, and Serverless Workers can run on AWS Lambda or GCP Cloud Run.
Whenever hosts the published workflow, its triggers and its credentials; you deploy a file, not a Worker fleet.
Starter briefs for related jobs, not recorded runs. Connect authorised accounts, confirm trigger and plan requirements, then review and test the workflow before publishing.
Takes each monitoring alert, gathers recent repository context, drafts a remediation plan, and hands it to the on-call engineer.
Weighs recent releases, open incidents and team calendars to suggest the lowest-risk deployment slot and holds it on the calendar.
Celebrates each won deal in Slack with the numbers and a short recap of how it was won.
Checks the search position of every keyword on your list, appends the history to a sheet and reports the moves.
Logs every expense submission in a sheet and alerts a manager in Slack when the amount is over the approval limit.
Pulls open HubSpot deals every Monday, groups them by stage and owner with totals, and shares the write-up in Slack.
When a process must survive crashes and run for days or months with Timers, Signals and human approvals in the middle, or when you already operate Workers and want one durable runtime across teams.
No. Temporal documents that the Temporal Service, including Temporal Cloud, does not execute your Workflow or Activity code; your Workers do. Whenever runs the workflow code on its hosted runtime.
Yes. A Temporal Schedule starts a Workflow Execution at specific times from an interval or calendar spec; Whenever schedules fire at minute granularity in the configured timezone.
Different meaning. Temporal requires deterministic Workflow code so the Event History can be replayed; a Whenever workflow is fixed code that runs its steps, with no replay, and external data or optional AI steps can still vary.
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
Ask your coding agent to turn it into a workflow. Whenever hosts, triggers and runs the code you reviewed.
A Schedule or a Workflow that runs the same steps each time.
Paste “Turn this task into a Whenever workflow and deploy it. Follow www.whenever.dev/skill.md”.
Enter the credentials, run it once by hand, then publish.