Running workflows¶
When a workflow runs, Malleable carries it out. It works in the background and communicates through the workflow's channels: forms and interactive pages, Slack or Teams messages, emails.
What it can do¶
During a run, Malleable can do exactly what the workflow was built with, no more and no less. The capabilities (the components in each stage) are set up while you build the workflow. During a run, Malleable uses them. It exercises judgment in how it uses them, handling edge cases, choosing what to say, and deciding when to ask. What it can't do is invent a new tool or reach a system the workflow wasn't given. That's what keeps runs adaptable without going off-script.
Each stage is its own objective, and stages gate what comes after them. An action that's meant to happen after a review can't run until that review passes, and if the review is rejected, it doesn't run at all.
How it behaves with people¶
- It asks focused questions when it genuinely needs input, and prefers proceeding with a reasonable assumption (and confirming it) over interrogating the user.
- It avoids interrupting for status updates; pauses are reserved for decisions and information only a person can provide.
- It writes user-facing text in plain language, in your business's terminology, not in internal field names or jargon.
When a run hits a recoverable problem that affected a run's quality, such as a flaky API or ambiguous guidance, it reports what happened, and those reports become suggestions.
Seeing what happened¶
Malleable keeps every run, so you can check on work in progress and look back at work that's done. Open a workflow and choose Runs to see them.
The runs list¶
The runs list has one row per run. Each run is named after what started it, such as "Refund request from Acme". There's a column for each piece of information your runs collect, like the requester or the amount.
Sort by any column. Filter by status or by the information runs collect, for example to show only failed runs or the runs for one customer. For columns with a small set of values, the equals filter offers a dropdown. You can choose which columns to show. You can also export the list. Test runs are hidden unless you turn on Show test runs.
Click a row to see what happened at each stage, the forms people filled in, and any files. If a run is stuck, you can stop it with Terminate run.
The run page¶
Each run has its own page that updates live. The bar at the top says where the run stands. When it's waiting, it says who it's waiting on and how they were asked, for example "Sent via Slack and email 2 hours ago". If nobody could be reached, it says Nobody was notified. While it waits on a timer or a reply, Continue now asks the run to stop waiting and keep going.
Watching a run on the canvas¶
Choose Show on canvas on a run to watch it move through the workflow, live or after it has finished. The canvas shows which stage the run is at, the path it took, and what each stage produced, like a form and its answers. Use the arrows at the top of the panel to step back through what happened.
How much work is at each stage¶
The canvas also shows how many runs are at each stage right now. A stage turns amber when one of its runs hasn't moved in over a day. Click the count to open those runs.
Asking Malleable about runs¶
You can also ask in plain words. Type into the box at the top of the runs list, or press ⌘K to ask Malleable Bot from anywhere in the app. For example: "Find the run for invoice 4021" or "Why did this run fail?"