Skip to content

Copilot Studio alternative: the agent as a workflow

Copilot Studio is Microsoft’s low-code studio for agents that reason through each request and are metered in Copilot Credits; Whenever runs the repeating job as a workflow you reviewed, and calls a model only where a step asks for one.

By Whenever team · Updated · Workflow behavior and runtime limits

What you get on Whenever

  • The same steps every run

    Describe the job in plain words; AI writes the procedure once and the published workflow runs its fixed steps. Keep a model step only where the work needs judgment.

  • One run is one run

    The meter counts a whole run, not each answer, action or token inside it. AI building and editing are free within weekly usage limits.

  • Any tool with an API, hosted for you

    Connect 1,400+ integrations or point Whenever at an API’s documentation. Enter credentials once in Setup; the workflow runs on a schedule, a webhook or an app event.

Copilot Credits, or a run per workflow.

Microsoft meters Copilot Studio agents in Copilot Credits that vary with the feature each response uses. Whenever counts whole workflow runs, with optional runtime AI on top.

Copilot Studio

Copilot Credits per answer, action and token

Copilot Credits

Microsoft meters agents in Copilot Credits bought as prepaid packs, a prepurchase plan or pay-as-you-go through an Azure subscription; the credits counted for a response depend on the feature it used.

Whenever

$39/mo

10,000 runs per month

Find the right plan for you

Tax 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.

A Copilot Credit measures what an agent did in a response: classic answers, generative answers, agent actions, grounding and tokens are rated differently, and one interaction can use several at once. Whenever counts the whole run. 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.

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

Copilot Studio

By default a Copilot Studio agent uses generative orchestration: it chooses topics, tools, knowledge and other agents from their descriptions, and Microsoft notes the same query can get different responses in a fresh and an ongoing conversation. Classic orchestration matches trigger phrases to a single topic instead.

Whenever

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.

Runs per dollar

Copilot Studio

Copilot Credits are pooled across the tenant and enforced monthly; unused credits do not carry over, and once a tenant reaches 125% of prepaid capacity the environment’s agents are blocked unless that environment bills overage to pay-as-you-go.

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

Copilot Studio

Topics authored on a canvas from message, question, condition and tool nodes; tools from Power Platform connectors, agent flows, prompts, REST APIs and computer use; event triggers from a connector library, including a recurrence trigger.

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

Copilot Studio

An agent is built and published from within Copilot Studio and runs on a Microsoft harness; publishing updates every connected channel, and event triggers authenticate only with the maker’s credentials.

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

Copilot Studio

The activity map shows how the agent responded in a test; a published agent records its triggers and reactions on the Activity page, and Microsoft advises testing with the model the agent uses because changing the model can change the result.

Whenever

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.

Where the AI cost lands

Copilot Studio

Each agent response draws Copilot Credits unless the Microsoft 365 Copilot licence inclusion applies; event-triggered runs are billed the same way, so a recurrence trigger every 10 minutes sends a payload every 10 minutes, and a reasoning model adds a per-1,000-token charge on top of the feature rate.

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.

Where it lives

Copilot Studio

Agents publish to Teams, Microsoft 365 Copilot, SharePoint, websites, mobile apps, WhatsApp, Facebook and Azure Bot Service channels such as Slack and Telegram; a Microsoft 365 Copilot licence covers agent use in Copilot Chat, Teams and SharePoint when the agent runs with the user’s identity.

Whenever

A Whenever workflow runs hosted on its trigger and can post to Slack, Telegram or Discord through its 1,400+ integrations; it is not a chat assistant inside Microsoft 365.

Teams and email workflows 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.

Browse all templates

Questions people ask before switching

What is Copilot Studio?

Microsoft Copilot Studio is a graphical, low-code studio for building and managing AI agents and workflows, published to channels such as Teams, Microsoft 365 Copilot and websites. Its agents reason through a request and decide the next step from their instructions and context.

How is Copilot Studio priced?

Microsoft meters Copilot Studio agents in Copilot Credits, bought as prepaid packs, a one-year prepurchase plan or pay-as-you-go through an Azure subscription. The credits counted for a response depend on the feature it used, and some usage is included for Microsoft 365 Copilot licence holders. This page quotes no Microsoft prices; Whenever counts whole workflow runs.

Is Copilot Studio the same as Agent Builder in Microsoft 365 Copilot?

No. Agent Builder in Microsoft 365 Copilot builds declarative agents from knowledge sources and skills; Microsoft says it does not support authoring actions that integrate external services, and points makers to Copilot Studio for connectors and workflows.

When should I keep Copilot Studio agents?

Keep Copilot Studio when the work is a conversation with employees or customers inside Teams, Microsoft 365 Copilot or a website, grounded in Microsoft Graph data. Consider Whenever when the job is a repeating procedure against APIs that should give the same result every run, priced per run.

Sources and scope

Official Microsoft Learn sources captured on the date shown below. These describe published features and billing rules for agents on the standard harness, not independent performance tests. Check the linked documentation for current harnesses, plans and limits. No competitor dollar price is asserted.

Checked

Move one Copilot Studio agent

Describe it, or ask your coding agent to write it. Whenever hosts, triggers and runs the code you reviewed.

  1. Write down what the agent does

    Its trigger, the topics and tools it uses, the knowledge it reads and where its answer goes.

  2. Describe it as a workflow

    Say it in plain words, or ask your coding agent to follow www.whenever.dev/skill.md. Keep a model step only where the work needs judgment.

  3. Test, then publish

    Enter the credentials in Setup, run it once by hand, then publish on its trigger.

Start for freeNo credit card requiredAI building has weekly usage limits.