Beta: Productboard Spark

Jake Sawyer

Updated June 05, 2026 20:15

Note: Productboard Spark is currently in open beta and available to all customers. The beta is a standalone experience that doesn't integrate with existing Productboard workspaces.

If you're on an Enterprise plan and workspace integration is important to you, contact your Productboard representative to discuss options. Otherwise, you can join the Spark beta here.

Productboard Spark is AI that equips your initiatives from idea to delivery readiness. It's an intelligent system designed for individual product managers who want enhanced strategic capabilities rather than basic productivity tools.

What is Spark?

Productboard's latest intelligent capabilities help you get your initiatives from new idea to delivery-ready in far less time by employing AI that understands your product, customers, and business.

Prompt AI through a conversational interface to explore product ideas and generate product docs like product briefs, requirements docs, launch announcements, and user research briefs.

These are generated based on unique context the AI has about your product and business—captured in a collection of documents containing your product strategy, OKRs, personas, pricing & packaging information, and more.

You can collaborate over these product documents with teammates or with AI, which then serve as additional context AI can use moving forwards.

You can also define templates that guide how AI generates certain types of documents or how it responds to certain types of prompts.

Key features and capabilities

Spark's organizational intelligence enables it to provide enhanced strategic capabilities that amplify your decision-making, helping you hit the bullseye every time rather than throwing darts at the wall.

Conversational AI interface

Productboard Spark has an AI-first conversational interface that guides you through your use case. Just say what you want to do and provide additional context if needed.

You can bring many different types of context into individual conversations:
- Productboard documents and notes
- Filtered feedback from insights boards
- Files from Google Drive or Confluence
- Live data from connected tools like Notion, Amplitude, or Linear Spark can make use of Google Docs, Slides, Sheets, Confluence Pages, plain text, CSV, markdown, and PDFs.
Mentions of documents and folders: When you type "@" or select the "@" icon in the text input field, you can mention documents, folders, or customer feedback to specify context for the given conversation.
Chat history: You can find your past conversations in the chat history, sorted by time.
Reasoning: You can see Spark's reasoning under each of your prompts. This helps you understand what context Spark uses to generate its outputs.
Chats are private and documents are public: All chats that you create are private and cannot be shared with anyone, while documents are public and are available to others (unless you move them into create them within your Personal section).

Manage your company and product context

Spark automatically creates context about your company, competitors, and product from publicly available sources the first time you sign in.

While this is a great start to ensure you receive relevant and context aware AI outputs, it's important to enrich your context even more. We highly recommend adding these foundational documents to your prompt via context management:

Company personas and target customers (segments).
Product strategy and OKRs.
Pricing and packaging information.
Any other relevant details that Spark cannot find online.

Tip: At Productboard, we also add details about our tech architecture, our messaging strategy, and brand guidelines.

To learn all about adding and managing context in Spark, see Context management in Spark.

Templates

Spark already includes templates for the most common product management documents, like briefs, competitive analyses, persona definitions, product requirement documents, or customer interview scripts. You can easily create new templates or customize the existing ones based on your needs.

When you ask Spark to create a document, it'll look in the Templates folder for a good template to use. If you have multiple similar templates, you can @-mention a specific template to make sure it uses the right one.

Tip: Use Spark itself to help you define your templates. Have it insert instructions under each section of the template and it'll use those instructions later to fill in the template with the most relevant content.

For more on working with templates, see Adjusting and adding templates below.

Connect external tools to Productboard Spark

Spark connectors let you bring context from external tools directly into your conversations. Instead of switching between platforms, you can query data, retrieve documents, and take actions through natural conversation.

Two connection methods are available:

Model Context Protocol (MCP) connectors: Query live data from tools like Amplitude, Linear, and Notion through conversation. For example: "Go to Amplitude and show me engagement metrics for the new onboarding flow."
File attachment connectors: Attach documents from Confluence or Google Drive to use as context. For example: attach your competitor analysis doc, then ask Spark to "generate three feature ideas that will help us capture market share."

For details, see Connect external tools to Productboard Spark

Iterate on documents with transparent edits and version history

When Spark edits your document, it highlights the changes it makes, and you can decide whether you accept them or not. This allows you to smoothly iterate until you have a document you are happy to share with your team or stakeholders.

If you need to revert a document to a previous version, go to Version history in the context menu of the document and revert to the right version in the history.

⚠️ Current limitation: If no action is taken, changes are accepted automatically. Highlights persist only for the current browser session.

See Collaborate on documents within Productboard for details on rich text formatting and document collaboration.

Collaborate with your team and stakeholders

Product management is collaborative in nature. Spark is built to boost your team's collaboration. You can share documents with others and they can edit or comment on them.

You will need to invite your teammates into your Spark teamspace and give them the right role:

Makers can create, edit and comment
Contributors can edit and comment

You can find more details about roles and permissions here.

Enabling Spark in your workspace

Space admins can control which users have access to Spark using the Spark visibility setting in Settings > Labs. This lets you configure and validate your workspace before rolling Spark out to your full team.

Changing the visibility scope

To change who can access Spark in your space:

From the Main menu, click Settings > Labs.
Find the Spark visibility card.
Select the visibility scope that fits your current needs.

Note: When expanding access, changes take effect immediately. When restricting access, users in an active Spark session can continue until they reload the page or log in again, at which point, access is revoked.

Visibility options

The visibility setting has three scopes. Choose the one that fits your current rollout stage.

Visibility scope	Who can access Spark	When to use it
Visible to everyone (default)	All users (admins, makers, and contributors).	Standard rollout once your workspace setup is complete.
Visible to admins only	Admin-role users only.	During workspace configuration. Set up context, test Spark outputs, and validate before any maker gets access.
Hidden for everyone	No one, including admins.	When you want to hide Spark in your workspace for all users.

Things to know

Admins always retain access to the Labs setting. Even when Hidden for everyone is active, the Spark visibility control remains visible and editable by admins. You can restore access at any time without contacting support.
Expanding access takes effect immediately. When you widen the scope (for example, from Visible to admins only to Visible to everyone), newly eligible users see Spark right away.
Restricting access is applied gracefully. When you narrow the scope, users in an active Spark session can continue until they reload the page or log in again, at which point access is revoked.
Each space has its own visibility scope. Settings don't cascade from parent to child spaces. Each space admin manages their own space independently.
Restricted users see a blocked entry point. Users without access see the Spark entry point grayed out, with a prompt to contact their admin.

Getting Started: Orientation, context, and templates

Here's what you need to know to get started with Spark right away.

UI orientation

Spark is made up of four main interface elements:

Main menu: The left edge of the screen helps you navigate between the main areas of Spark. You'll spend most of your time at the top in Home, and you'll find Settings at the bottom.
Submenu: This panel provides additional navigation options. For example, when you click Home from the Main menu, the Submenu will display your documents organized into folders.
Board panel: When you select a board or document from the submenu or have Spark create a new one, it will appear in the center of the screen.
Chat panel: This is where you interact with Spark. If no board is open, this panel takes up most of the screen.

Invoking Spark

There are many ways to start chatting with Spark. Here are the two easiest ones:

From the Main Menu > Home, click Spark to open the main Spark landing page. You can start a new chat from here.
Whenever you're viewing a board or document, click the Spark AI button in the top right corner to open the chat panel without leaving the board you're on.

Initial context and default templates

When you log into your Spark workspace for the first time, Spark uses publicly available information to learn about your company, product, and competitors. This context is called Company Knowledge, and it lives in its own section near the top of the Submenu.

In this section, you'll also find templates you can use to structure your information.

However, unless you've published all your strategic documents publicly (not recommended), Spark will need your help to become a true strategic assistant. That means feeding it more context.

Note: You should set aside 20-30 minutes to finish setting up Spark with the context and templates it needs.

Adding competitors and personas

Spark gathers enough data from the internet to populate a Competitors folder and a Personas folder in Company Knowledge. If Spark missed important competitors or personas in its initial data compilation, you can add more. You can even use Spark to help you do this efficiently!

In any Spark chat field, ask Spark to add a new competitor or persona. Give the competitor or persona a name so Spark knows where to start.
(Optional) You can specify a template for Spark to use by @-mentioning it. You don't have to do this if you haven't created any templates yet; Spark will always look in the Templates folder for a relevant template to use, and it comes with templates for competitive analyses and personas by default.
Wait for Spark to finish generating the new document.
(Optional) Edit the generated document directly in the document panel that appears on the right, or use the chat panel to have Spark make edits for you.

Spark is smart enough to know where new documents should go. For example, if you ask it to create a new persona, it'll place that document in the Personas folder (unless you tell it otherwise).

Adding strategic documents

Spark works best when it's working from the same planning documentation that you are, but it needs your help to access those plans. You (hopefully) have documents detailing things like company OKRs, product strategy, and pricing. Spark will need these documents to build a complete understanding of your product.

Tip: If you don't have such documents, or you want to start from scratch, open a new chat and ask Spark to write some for you!

You can't upload PDFs or other files directly into Spark (it's not a file manager), but you can attach files to chats and have Spark work with those files to create documents. To attach files to a chat, click Context > Attach file.

Alternatively, you can bring information directly into Spark by copying text and pasting it into a new document. To do so:

In your Spark workspace, hover over Company Knowledge and click the Create a new board or folder button.
Select Document.
The new document will appear in the document panel. Give it a name.
Leave your Spark workspace and open a relevant strategic document. Copy the text from that document to your clipboard.
Return to your Spark workspace and paste the information into the document you just created.
(Optional) Use the chat panel to have Spark edit the document or format it for clarity.

Once your strategic documents are in Spark, it'll be able to reference them when you prompt it.

Adjusting and adding templates

Spark comes with several templates to help structure information logically. You'll find these templates in the Templates folder in Company Knowledge.

These default templates cover a wide variety of document types. Whenever you prompt Spark to create a new document, it'll check this folder to see if there are any templates it should use.

Example: If you prompt Spark with "Create a LinkedIn post summarizing our newest initiative," it will automatically format its response according to the LinkedIn Initiative Post Template.

Of course, these templates might not align with your preferences, so feel free to change them! You can open a default template and edit it directly or have Spark rewrite it for you.

If your PDLC includes document types that don't have associated default templates in Spark, it's easy to add new templates:

Create and name a new document in the Templates folder.
Copy a template from your external source and paste it into the new Spark document's description, or prompt Spark to create a template for you.

Working with feedback notes

Good feedback management makes Spark even more powerful. For details and videos, see Customer feedback management in Spark.

Supported use cases

Spark supports the complete product discovery journey, helping you avoid reinventing the wheel and context recreation for each initiative. Below is a list of great use cases for Spark.

You should also check out our prompt library for more actionable tips.

AI-powered initiative development

Transform product ideas into context-aware initiative briefs.
Receive recommendations for next steps in product discovery and delivery.
Transform initiative briefs into detailed product requirements (PRDs).
Break down requirements into detailed user stories with acceptance criteria.

Smart research and discovery

Generate targeted interview questions to validate hypotheses.
Compare opportunities against existing market solutions with enhanced capabilities.
Identify differentiation opportunities using advanced strategic context.
Transform raw interview transcripts into structured insights.
Write personalized customer emails referencing specific feedback.
Design user testing scenarios with success criteria and measurement plans.
Generate beta program materials that understand your business priorities.

Collaborative documentation and stakeholder alignment

Create custom company templates for standardized document generation.
Seamlessly collaborate with your team and stakeholders on generated artifacts.
Select from a pre-defined prompt library to get started quickly.
Create internal-facing announcements for feature launches with your product knowledge built-in.

Current Limitations

As a beta product, Spark has some current limitations:

File upload: Currently, it's only possible to upload images. If you need to bring in an external PDF or document, take a screenshot of it and upload it to the chat.
Change tracking: Changes made by the AI agent are highlighted in the UI and users can revert them. If no action is taken, changes are accepted automatically. Highlights persist only for the current browser session.
Document privacy: All documents created in Spark are accessible to other users. Chats are always private and not shareable.
Core entities: Spark currently cannot retrieve, create, and update core product entities, such as features, releases, objectives, or initiatives. We're working on more integrated experiences and you can upvote this on our portal.

Frequently Asked Questions

Who can access Spark?

Productboard Spark is currently available to all customers participating in the Spark beta program. You can join the beta here.

Can contributors and viewers use Spark?

In standalone Spark workspaces: No.

If you've spoken to your Productboard representative, you might have special access to a preview build of the integrated Spark workspace. In that case, contributors and viewers can see Spark in the main navigation and use Spark chat, including context management, connectors, and skills.

Contributors and views can ask Spark about existing boards and data they have access to. However, they cannot create new documents or folders with Spark (except in the case of contributors who have been granted document creation permissions in specific teamspaces).

How does Spark differ from other AI tools like ChatGPT or Claude?

Unlike generic AI tools that start from scratch, Spark is context-native intelligence that understands your product's continuity and amplifies your existing strategic thinking. This makes it more effective for hitting the bullseye rather than throwing spaghetti at the wall.

Basically, it's already familiar with what you're working on. The others aren't.

What data does Spark use?

Spark uses any documents and information you provide in your workspace. Your data won't be used to train the AI models for the purpose of other Productboard Customers. We do not permit our third-party Subprocessors of Productboard AI to use your data to train their Al models.

Can I customize Spark's outputs?

Yes, you can define templates and provide specific context to guide Spark's outputs.

Is my data secure?

Yes, Spark follows Productboard's standard security and privacy practices. Your data remains within your workspace and is not used to train external AI models.