Coming from Wordware V1?
Wordware V1 combines a document-style flow with generation, logic and code nodes; a Generation node calls a model, not every step. Its V1 FAQ describes its billing and authoring model separately from the company’s Sauna product. Whenever turns a brief into published code you supervise through rules and sample results. Fixed non-AI logic is deterministic; optional model steps can vary and cost runtime AI. Free building has weekly limits; the file is yours.
What you get on Whenever
You describe it once, AI writes it
Describe the job in plain language. Review the workflow summary and test representative outputs before publishing; reading the generated code is optional.
Code you can read
The published procedure is code: the branches, the loops and the data shapes are in the file. You can read it top to bottom, export it, and take it with you.
Published runs count once
AI building and editing have weekly usage limits. A published workflow execution counts as one run within its call budget; runtime AI uses the plan’s separate included AI spend, and external providers may charge separately.
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 English document. A TypeScript file.
Wordware V1’s FAQ describes usage-based credits; Generation nodes use models when reached, while logic and code nodes are distinct. Whenever counts workflow executions and optional runtime AI separately.
Wordware V1
Free credits, then usage
Usage while V1 flows run; confirm current terms
The Wordware V1 FAQ describes free credits then usage billing, or a branded-output arrangement; confirm terms before relying on it.
The captured Wordware V1 FAQ describes free credits, usage billing and an optional branded-output arrangement. Confirm current terms with Wordware. Do not apply these V1 statements to Sauna. Generation nodes use models when reached; code and logic are separate. Compare confirmed terms with Whenever executions and runtime AI, not an assumed cost per flow.
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
Wordware V1
Nodes run in the order they appear in the document, top to bottom, and if-else and loop nodes branch on conditions you wrote. Every Generation node is a model call, so wherever a step is a generation, that step’s output comes from the model.
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
Wordware V1
The captured V1 FAQ describes credits, usage billing and an optional branded-output arrangement. Confirm current terms with Wordware; no exact price or guaranteed allowance is asserted.
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
Wordware V1
A document rather than a canvas, and a wide one: prose, generations and structured generations, if-else, loops, sub-flows, an “Ask a Human” node, 2,000+ integrated apps, and a code node that runs JavaScript or Python. Its docs include a chatbot recipe, so it is not only for fixed procedures.
Whenever
The same English brief, turned into typed TypeScript. Every branch, loop and data shape is ordinary code in one file, so there is no node vocabulary to learn and no code node to open when the document stops being enough.
Export and portability
Wordware V1
A flow lives in the editor and is published as a versioned WordApp: each release has its own URLs and ids, there is an HTTP endpoint that streams results, and you can embed it. The captured documentation describes deploying, versioning and calling a flow; check what an export would contain before planning a move.
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
Wordware V1
Wordware documents node outputs and code logs, errors and return values. Each release is versioned with its own URLs and IDs; API callers can choose an exact version or a caret range such as ^1.0.
Whenever
Read the procedure and its execution log side by side, then re-test the failing input. Fixed logic makes the procedure inspectable, not every failure reproducible; external data and any explicit model call still have to be accounted for.
Where the AI cost lands
Wordware V1
Generation nodes call models when reached. Wordware V1’s FAQ describes usage billing and an optional branded-output arrangement; do not extend those V1 terms to Sauna or assume code-only steps require inference.
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.
Who writes the flow
Wordware V1
You do, in English, step by step, starting from a blank document or a template. Asked whether AI will write the whole workflow, Wordware’s own answer is that “the models are not quite there yet” and that a copilot is being worked on.
Whenever
You describe the job and Whenever’s AI writes the TypeScript. The writing is the part that is automated; reviewing it, testing it and publishing it are yours.
When to keep Wordware V1
Wordware V1
Keep it where the reasoning is the product: chatbots, document and media pipelines, prompts you and a colleague iterate on in the same shared document, and flows you embed in your own product behind a pinned version of its API.
Whenever
Consider Whenever for a defined procedure with explicit inputs, rules and destinations. A chat bot on Whenever is a published workflow; that differs from a hosted conversational-app product.
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
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 Wordware V1 flow.
Keep Wordware where its flows serve you well. Describe one recurring job, and Whenever writes it as code you can read.
Read the flow as its own specification
It is already written in English, which is the hard part done: note the trigger, the generations, the branches, and every action it calls.
Say which steps still need a model
Describe the job to Whenever and keep a model call only where a step needs judgment. Review the workflow summary and sample results; inspect TypeScript if useful and reconnect each service.
Run both against the same inputs
Compare outputs on representative events, the empty and malformed ones included. Make sure only one of the two handles each event before publishing the replacement.