Skip to main content
Every workflow has exactly one trigger and at least one step after it. This page lists each type the builder offers. The name in code is the type as it appears in a workflow exported from Hive.

Triggers

The trigger is the first card on the canvas and has the type trigger. Select it, then choose what starts the workflow.
There is no webhook trigger. To start a workflow from another system, publish a public form and post to it through the public form API.

Forms

A form trigger (form or public_form) needs a title and 1 to 20 fields. Each field has a label (up to 120 characters), a key (lower_snake_case, up to 60 characters), an optional placeholder (up to 160 characters), a required switch, and a type: A field’s key is set when the field is created and does not change when you rename its label, so earlier submissions stay readable. Submissions with unknown fields are rejected. The public form’s confirmation message defaults to “Form submitted! Your response has been recorded.” {{ }} placeholders are not filled in, so it cannot repeat answers or anything the workflow produced. It appears as soon as the submission is accepted, before the workflow has run, so do not promise an outcome in it. An in-app form has no shareable link. Once the workflow is deployed, a teammate who can run it selects Fill in form in the builder header (or on the workflow’s row in All workflows), fills in the live release’s form and selects Submit form. The run starts as that teammate.

Schedule

A Schedule trigger runs on this cadence in UTC once the workflow is deployed. Saved schedules on the Scheduled tab take over from it and can use any timezone; see Schedules and public forms.

Passing values between steps

A step can read the trigger’s input and any earlier step’s output:
  • In text such as prompts and messages, write a placeholder like {{trigger.email}} or {{invoice_lookup.total}}. Prompt templates are up to 4,000 characters.
  • In a rule condition, a loop or a wait, enter a bare dotted path such as invoice_lookup.total.
Paths start with the step’s id. Inside a loop, the item alias you choose (for example {{item.name}}) names the current item. Under an agent’s prompt, an AI condition, an Output value and a Create PDF title and body, Insert a value from an earlier step lists what the steps before it produce, so you can add a placeholder without typing its path.

Steps at a glance

Every step except the trigger also has a title (up to 120 characters), a note (up to 500), a team comment (up to 500), an On error policy, and can be deactivated: a deactivated step stays on the canvas and is skipped when the workflow runs.

Hive agent

An agent step sends its prompt to a model and passes the answer on. Later steps read {{<id>.text}} for a text answer, or each named field when structured output is on. If no AI model is configured, a workflow with an agent step cannot be deployed or run, and the card says why.

Saved agent

A saved_agent step runs a deployed Agent Studio revision, pinned with its exact output contract. You map its inputs (up to 50), sources, context and accounts (up to 20 each) explicitly, from an earlier value or a fixed selection. The person running the workflow must still be allowed to run that agent and must use their own sources and accounts. Later steps read the validated result, for example {{meeting.output.data.summary}}.
Saved agent steps are refused where your workspace does not have live saved agents enabled, and a workflow started by a public form cannot run one. The workflow assistant never adds this step.

Parallel agents

A parallel_agents step runs two to five agents at once, for work that splits into independent parts. Each agent has a key (up to 40 characters, unique in the step, not combined) and an optional title, and is one of two kinds:
  • Inline instructions — the same settings as a Hive agent: prompt, model, tools, structured output and read-only data sources. A step reads at most 12 connected accounts across its inline agents.
  • A saved Studio agent — pick a deployed Agent Studio revision in Saved Studio agent for Agent N and map its inputs, sources, context and accounts exactly as in a Saved agent step. Use inline instructions switches the agent back. The saved agent rules apply here too: the workspace must have live saved agents enabled, and a workflow started by a public form cannot run one.
The step succeeds only when every agent succeeds. Each agent retries on its own and keeps its own run receipt, whether it is inline or saved. A new step starts with two inline agents, agent_1 and agent_2.

Condition

A condition step sends the run down one of its paths. Choose a Condition type. A new Condition starts as AI, with Force AI to select a path switched on and two empty conditions.

Rule

Pick a value path, an operator and (except for exists) a value to compare with. Connect the true and false branches to the steps each should run.

AI

Write 1 to 10 conditions in plain text, with {{ }} placeholders. The first reads Go down this path if, and each after it Else if. Later steps read the chosen paths as {{route.routes}} and the model’s reason as {{route.reason}}. Each run of an AI condition is one model call, billed like an agent step. A deploy is refused while a condition is blank. A condition can never be set to continue after a failure.
An AI condition is not a security check: what it reads, including what a visitor types into a public form, can steer its choice. Steps after it still pass every approval and safety check.

Loop

A loop runs the steps inside it once for each item of a list. A finished loop exposes {{each.items}}, {{each.count}} and {{each.truncated}} (whether the list was longer than Max iterations), where each is the loop’s id. With Collect outputs on it also exposes {{each.iterations}}: one entry per item, in list order. A deploy is refused if a later step reads iterations from a loop that does not collect them. With Parallel execution, items finish in any order. If one fails and nothing continues past it, running items finish their current step, no new item starts, and the loop fails. A parallel loop cannot contain a Wait, a Parallel agents step or another parallel loop. A loop multiplies its body’s cost: see runs and errors.

Wait

A wait on a value re-checks every 60 seconds and fails the step with “Workflow wait condition timed out” if the value never arrives. A test run does not wait out a duration.

Action

An action step does one of two things:
  • Internal notification records a note in Hive’s audit trail. Nothing is sent outside Hive. A new step posts “The workflow reached this step.” to the general channel.
  • Integrations steps act through a connected app: posting a message, creating a record, sending an email. They appear in the Integrations section of Add step for apps your workspace has connected, and each needs an account to act through.
An Integrations step lists every field its app takes. Required fields are marked, list fields take one entry per line, and each value can be text or a placeholder. A run, a deploy and an import all refuse a step with an empty required field or a field the app does not take. Your role limits which actions you can put in a workflow you deploy: In a production run, every action passes your workspace’s approval and safety policy. An action that needs approval is recorded as Awaiting approval and the run carries on: the workflow does not pause for the decision. Writes to a connected app always go to human approval.

Output

An output step gives a value a key (up to 80 characters; a new step uses result) and the text or placeholder it holds. The run’s result collects every output by key. Two outputs cannot share a key, and an output cannot be set to continue after a failure.

Web search and Generate image

These two steps can build their text from the run automatically. A Web search step (web_search) searches either:
  • Automatic (default) — built from the run when the step runs; or
  • Fixed — a query you type, up to 1,000 characters, searched exactly as written. A fixed query cannot contain {{ }} placeholders.
It passes on query, text and citations (each with a title and URL). A Generate image step (image) uses a prompt that is either Automatic (the default for a new step) or Manual (up to 4,000 characters, placeholders allowed). Choose a size: 1024x1024 (default), 1536x1024 or 1024x1536. On Automatic, Hive joins the text output of the steps directly before this one, without their field names: up to 1,000 characters for a search and 4,000 for an image prompt. The text is copied as it is, not rewritten by a model. The first step inside a loop reads the current item. If none of those steps produced text, the step fails rather than searching for, or drawing, nothing. The step’s panel says how many steps it reads from. A Generate image step saves the picture to the root of your Library, named after its prompt; a test run saves one too. Later steps read {{<id>.url}}, name, width and height. Both steps run only where your deployment has them configured; otherwise the builder says so and a deploy is refused.

Create PDF

A document step turns Markdown into a PDF and saves it to the Library. Later steps link the file with {{report.url}} and name it with {{report.name}}. A test run saves its PDF too, marked as a test. PDFs use standard fonts, so characters outside Western European alphabets print as ?.

On error

Every step except the trigger has an On error choice: A refusal — not permitted for your role, not funded, or an account that must be connected first — always stops the run, whatever this says. See Runs and errors for retries and budgets.

Build a workflow

Start from a brief, a template or a blank draft.

Test and deploy

Try a draft safely, then release it.

Runs and errors

Follow runs, retries and the step budget.

Limits reference

Every limit in one table.