Poppi (AI) Steps

Poppi briefings

A Poppi briefing is an AI-powered step on the canvas that pulls live data from your connected integrations and shows it to staff as a short, written summary before they fill in an element. It is one-way information, designed to give the worker the context they need to do the next step well. Poppi briefings are coming soon: they are not yet available to add on the canvas, so you won't see the add button for now. This page explains how they will work when they arrive.

What a Poppi briefing is for

A briefing reads the data sources you enable, then composes a contextual message based on your prompt. The worker sees it at the top of that step, just above the instruction, when they open that part of the workflow.

Good fits include:

  • Showing today's open Shopify orders above an "Opening kitchen check" element so staff know what to prep first
  • Pulling today's Google Calendar events above a meeting summary element so the worker knows which meetings to write up
  • Surfacing yesterday's unresolved chat threads above a handover element so the next team picks up where the last one left off
  • Reminding staff who is on the team today and what their roles are before a daily briefing element

If you find yourself writing the same context paragraph by hand every day, a briefing is probably the right tool.

Where a briefing sits on the canvas

A briefing attaches to a single element on the canvas and sits to the left of that element as a satellite. It does not change what staff have to fill in, it just adds context above it when they open the step. You cannot attach a briefing to a group — only to an individual element.

The briefing has one connection only — to its parent element. It does not branch, it does not route anywhere else, and it is read-only for the worker.

How to add a Poppi briefing

When Poppi briefings launch, you will add a briefing from the element it should attach to. There is no right-click menu on the canvas; you add nodes using the circular Plus button.

  1. Find the element on the canvas — a small circular Plus button sits just to its left
  2. Click the Plus button to open the add menu
  3. Pick Briefing from the menu
  4. A new Poppi briefing node spawns to the left of the element, already connected
  5. Click the new node to focus it and fill in the fields

The Plus button to the left of an element is always there while the element has no briefing yet, so you do not need to hover over the element to find it.

The header on the new node reads Poppi (AI) briefing with a grey header bar and a small crosshair icon, so you can tell it apart from other node types at a glance.

Configuration fields

The briefing node has two fields to fill in.

Prompt (textarea, required)

This is where you tell Poppi what the briefing should say. The label reads Tell Poppi what information should be added to the [element-type] node, with the element type filled in based on which element the briefing is attached to. For example, a briefing attached to a Text element shows Tell Poppi what information should be added to the text node.

The placeholder text reads: e.g. Brief the worker on yesterday's open issues, today's team, and any calendar meetings they're invited to.

Write the prompt in plain English. Poppi reads your prompt at runtime, looks at the data sources you have enabled, and composes the briefing.

Data sources (multi-select picker)

This is the list of integrations Poppi can read from when it builds the briefing. Click the picker to open it. Pilla itself sits at the top, always available and marked Always on with a green dot, so a briefing can always read your own teams, users, and workflow data. Every other supported service is listed too: those you have connected show a tick you can turn on or off, and those you have not connected yet show a small Connect button you can use to link the service without leaving the canvas.

Tick every service you want Poppi to consider. Poppi will only query the ones you tick, so leaving a service unticked means it will be ignored even if it is connected. The picker button summarises your choice — a single service shows its name, more than one shows a count like "3 data sources".

How a briefing renders for staff

A finished briefing shows up wherever staff open the workflow run, on both the mobile app and the web app. It appears as a full-width card just above the element's instruction, headed Poppi (AI) via {name} in blue, where the name is the person whose briefing it is. It reads like a short message from Poppi. It is read-only — the worker cannot tap, edit, or dismiss it, they just read it and then fill in the element below.

A briefing is not generated the moment a worker opens the step. Poppi composes it shortly before the workflow run is due to start, so the text is ready and waiting by the time staff open the run. A briefing only appears once it has been generated successfully; if Poppi cannot build it (for example a data source it needs is disconnected), no card shows and the rest of the step is unaffected.

Availability

Poppi briefings are coming soon and not yet available to add on the canvas. Connecting outside services from the Manage my integrations screen is available to every account now, so you can link the data sources you want a briefing to read ahead of time.

Tips

  • Keep the prompt short and specific, "show today's open orders from Shopify" works better than "tell the worker everything they need to know about today"
  • Tick only the data sources the prompt actually needs, every extra source adds latency and noise
  • If a service in the data sources list shows a Connect button instead of a tick, it is not linked yet, connect it from the picker (or the Integrations page) before ticking it for a briefing
  • If a data source becomes disconnected after you have set up the briefing, the briefing fails silently for that source, the rest of the briefing still runs with whatever sources remain connected
  • Briefings are one-way, so if you need staff to make a decision based on the context, pair the briefing with a Poppi decision in the same workflow

Poppi decisions

A Poppi decision lets a workflow branch yes or no based on what staff actually answered. You attach the decision to an element on the canvas, write the question in plain English, and Poppi reads the answer and picks the branch. Each branch can run different steps.

What a Poppi decision is for

A decision lets the workflow do something different depending on what happened, not just what was scheduled. You write the question, Poppi gives the yes or no answer, and what runs next depends on that answer.

Good fits include:

  • After a number element, run an extra check on the No branch when the reading is out of range, and skip straight on when it is fine
  • After a photo element, send the work down a "looks clean" or "needs attention" path
  • After an inspection checklist, add a follow-up step only when something failed
  • After a complaint note, route the work down a "minor" or "major" path based on what the worker wrote

If the workflow needs to take a different path based on what a worker entered, a Poppi decision is the step that decides which path.

How a Poppi decision works now

You no longer add a separate decision node. Instead, you attach the decision directly to the element whose answer you want Poppi to judge. Every input element on the canvas (text, number, photo, checklist, and so on) can carry one Poppi decision.

When you write the question, two branch dots appear under the element: a green dot on the left for the Yes branch and a pink dot on the right for the No branch. You then add a step to each branch. After staff complete the element in a work run, Poppi reads their answer, decides yes or no, and the workflow follows the matching branch.

Guidance elements (written, photo and video guidance) cannot carry a decision, because there is no answer to judge. Elements inside a group cannot carry one either, because group steps do not have their own branches.

How to add a Poppi decision to an element

You add a decision in the element's own card on the canvas. There is no separate menu item for it.

  1. Click the element on the canvas to open its card
  2. Find the field labelled Instructions for Poppi (AI) to make a decision near the bottom of the card
  3. Type your question, for example is the entered number above 8
  4. A green Yes dot and a pink No dot appear under the element card

Write the field as a yes or no question. Poppi reads the worker's answer to that element, answers your question, and follows the Yes or No branch you build next. The field placeholder shows e.g. is the entered number above 8 as a guide.

How to build out a branch

Each branch starts empty with its own circular Plus button. The green Plus on the left builds the Yes branch and the pink Plus on the right builds the No branch.

  1. Click the Plus button under the Yes dot or the No dot
  2. Pick an element type from the toolbar that opens (the same element types as the rest of the canvas)
  3. The chosen step is added at the end of that branch, already connected
  4. Fill in the new step like you would any other

You can also drag a branch dot onto an existing element to connect it, instead of adding a new step. You can only attach one step directly to each branch dot; to add more, chain extra steps off that first step. You do not have to build both branches. If a branch has no step, the workflow simply carries on after the decision when Poppi picks that branch.

How to remove a Poppi decision

To remove the decision, clear the Instructions for Poppi (AI) to make a decision field on the element card.

If you have already wired up Yes or No branches, a confirmation popup appears headed Remove this Poppi rule? It warns that removing the rule also deletes its Yes and No connections, and that the steps on those branches stay on the canvas as unconnected steps so you can re-wire or delete them. Click Remove rule to confirm, or Cancel to keep the decision. If you have not wired any branches, the decision is removed straight away with no popup.

Validation warnings

The canvas flags an unfinished decision when you try to save.

  • A red border around the question field means the decision has a question but neither the Yes nor the No branch is wired to a step
  • The save warning lists it as {N} Poppi rules with no steps wired, where N is the number of decisions that still need at least one branch connected

Connect at least one branch, or clear the question, and the warning clears.

The satellite decision that runs actions

There is a second kind of Poppi decision that sits beside an element as its own node and branches to Poppi actions rather than to ordinary steps. This kind is coming soon and is not yet available to add on the canvas, so you will not see its add button for now. It is for when you want Poppi to judge an answer and then run an integration action, like posting to Slack, only on the matching branch.

When satellite decisions arrive, you will add one by hovering over an element to reveal the circular Plus button on its right, clicking it, and picking Decision from the menu. This adds a separate node to the right of the element, headed Poppi (AI) decision with a grey background. It has a single question field labelled What should Poppi decide? with the placeholder e.g. Were all critical items ticked? Was the photo clean and well-lit?. Poppi evaluates the question when the element is saved.

Each branch has a green Yes dot and a pink No dot on the right of the node. Clicking the Plus button on a dot adds a Poppi action to that branch. A red border means the node is not connected to anything. The play icon in its header tests the decision; it is greyed out with the tooltip Add a question first until you type a question.

Tips

  • A decision is most useful right after the element whose answer it judges, so phrase the question about that one answer, for example is the entered number above 8
  • Phrase the question so Yes is the "happy path", it makes the canvas easier to read at a glance
  • You do not have to build both branches. Wire only the branch that needs an extra step, and the workflow carries on as normal on the other one
  • A decision needs at least one branch wired before the canvas will save, so either connect a branch or clear the question
  • Clearing the question on a decision that has wired branches always asks you to confirm, and leaves the branch steps on the canvas so you can re-use them

Poppi actions

A Poppi action is an AI-powered step you add on the canvas (web only) that runs a single instruction through one of your connected integrations. Poppi reads the answers from the steps above it plus your written instruction, works out the right details, and carries out the action through the service you chose. Poppi actions are coming soon: they are not yet available to add on the canvas, so you won't see the add button for now. This page explains how they will work when they arrive.

What a Poppi action is for

An action is the "do something useful" step at the end of a chain. The element gathers the answer, a Poppi decision picks a branch, and the action gets the work done in another tool. Actions run quietly in the background when a workflow run reaches that point, so staff never see the action node on their phone.

Good fits include:

  • Posting a summary of a daily inspection to a #site-updates Slack channel after a step is completed
  • Creating a Google Calendar event for a maintenance follow-up after the No branch of a Poppi decision
  • Uploading a generated report to a Google Drive folder after a closing step
  • Sending a polite team message inside Pilla to thank staff after the Yes branch confirms a clean handover

If the workflow ends with "and then this should happen in tool X", that is an action.

Pilla acts on your behalf

Actions run under the identity of whoever connected the service, not as a separate Pilla robot.

If you connected Slack, a message posted by a Poppi action appears in Slack as if you posted it. The same goes for Google Calendar (the event shows you as the organiser), Google Drive (the file is created in your Drive), and WhatsApp (the message is sent from your WhatsApp Business number).

This applies to every outside integration. The only exception is Pilla itself, where the team message is sent from Pilla, so the on-behalf-of note does not apply.

The reason is consistency. Most integrations have no robot mode at all, so a single "your account did this" model is simpler to explain and matches how a person would have used the tool by hand.

How to add a Poppi action

When Poppi actions launch, you will add an action node with the circular Plus button on the canvas; there is no right-click menu.

From the right of a step

  1. Hover over a step on the canvas to reveal the round + button on its right side
  2. Click the + to open the add menu
  3. Pick Action (the menu also offers Decision for a Poppi decision)
  4. A new action node appears to the right of the step, already joined to it

From a Poppi decision's Yes or No branch

  1. Add a Poppi decision to the right of a step first (it has a green Yes branch and a pink No branch on its right side)
  2. Click the round + button next to the Yes branch or the No branch
  3. A new action node appears at the end of that branch, already joined — there is no menu to pick from here, because an action is the only thing a branch can lead to

The header of the new node reads Poppi (AI) action with a grey background. The grey is the same on every action node, whichever branch it sits on.

Configuration fields

The action node has three fields, filled in top to bottom. Later fields only appear once earlier ones are picked. Until you choose a service the field shows Pick a service, and until you choose a tool it shows Pick a tool.

Service (picker, required)

This is the integration the action will run through. The picker only lists services that have actions ready to use, which today are Pilla, Slack, Google Calendar, Google Drive, Shopify and WhatsApp. Pilla itself sits at the top and is always available; the rest only become selectable once they are connected. A service that is not connected yet shows a small Connect button you can use to link it on the spot. Other services you may see on the "Manage my integrations" screen do not appear in this picker until they have actions wired up.

To connect a service ahead of time instead, open the avatar menu in the top-left corner of the top bar and pick Manage my integrations (managers and admins only).

Tool (picker, required)

Once a service is picked, the Tool picker appears. It lists the actions available on that service, which vary by service. The connected services that have tools wired up today are:

ServiceTools available
PillaSend team message
SlackPost message to channel
Google CalendarCreate event, List today's events
Google DriveUpload file, Create folder
ShopifyList orders
WhatsAppSend message

Pick one tool. The instruction field below updates to match the chosen tool.

Instruction (textarea, required)

This is where you tell Poppi what to do. The label changes based on the tool you have picked, for example:

  • Pilla "Send team message" — Tell Poppi what to send *
  • Slack "Post message to channel" — Tell Poppi what to write on your behalf *
  • Google Calendar "Create event" — Tell Poppi what event to create on your behalf *

A short helper line below the label reminds you where the action will run (for example "The message will be posted in Slack as you."). The helper line is only shown for outside integrations, not for Pilla.

Write the instruction in plain English. Poppi reads your instruction, looks at the answers from the steps above the action, and works out the details when the workflow runs.

For example, the placeholder for Slack reads: e.g. Post a polite summary to the #ops channel. Mention the worker and how many issues were raised.

Availability

Poppi actions are coming soon and not yet available to add on the canvas. Connecting an outside service such as Slack, Google Calendar, Google Drive, Shopify or WhatsApp from the "Manage my integrations" screen is available to every account now, so you can link your services ahead of time. Pilla itself, used for "Send team message", needs no connection.

Validation warnings

A red border around the action node means it is orphaned: it is not joined to the rest of the workflow, so nothing leads to it from the trigger. This usually happens when the step it was attached to is deleted, or when you drag the node away from the chain. The fix is to connect it back into the flow, either to the right of a step or to the Yes or No branch of a Poppi decision.

The test button (the play icon in the header) is disabled until the action has a service, a tool and an instruction. The tooltip tells you what is still missing — "Add a prompt first" if there is no instruction, or "Pick a service and action first" if the service or tool is empty. When everything is filled in, the tooltip reads "Test this action".

Tips

  • Be specific in the instruction. "Post a polite one-line summary to #ops mentioning the worker and the issue count" works better than "let Slack know"
  • Mention channel names, calendar names or folder names directly in the instruction. Poppi uses those names to pick the right destination
  • Test the action with the play button before you save, so you can see what Poppi sends through the integration on a real workflow run
  • If you delete the step an action was attached to, the action node is left with a red border because nothing leads to it any more — reconnect it into the flow before you save
  • Use a Pilla "Send team message" action when you want an action that needs no outside connection