Explore interface changes in a working prototype
Let product and design staff use an AI coding assistant to try interface changes in the product workspace, then review and keep or revert them.
A FIELD GUIDE TO AI AT WORK
Product & Engineering workflows
Explore practical AI workflows for product & engineering: inputs, implementation steps, human checks and downloadable skills to adapt to your team.
ESSENTIALS / THREE FOUNDATIONS
People. Projects. P&L.
Build the foundations with three practical skills.
Start with what your team does.
Choose your recurring activities to build a starting set.
Build a direct storefront from brand context
Use approved brand and product material to prototype a store with consistent pages and product-selection experiences.
Introduce an AI feature at the moment it becomes useful
Test onboarding that offers a concrete next action when a user provides a relevant artifact, instead of relying only on a feature announcement.
Research a stakeholder request before committing it to the roadmap
Combine official technical documentation with internal product usage to assess a proposed feature and explain feasible alternatives.
Convert product reviews into a weekly action digest
Collect new product reviews and surface recurring problems, valued features, and requests that product owners can investigate.
Keep an agent evaluation set current as the real world changes
Review evolving reference cases and test each agent update against current, verifiable expected behavior.
Exercise native-app releases through repeatable user flows
Use UI automation and change context to inspect a desktop build for regressions before release.
Maintain a connected map of product knowledge
Connect code, documentation, support issues, and feature context so changes can be understood across the product.
Check delivery updates against task and code evidence
Compare reported work with the original task and implementation artifacts to surface missing or inconsistent evidence.
Make a technical contractor handover searchable
Connect repositories, project documentation, and permitted discussion history to help the receiving team understand an inherited system.
Improve a prompt against a defined evaluation set
Iterate on a production task’s prompt using labeled examples and an explicit quality metric instead of judging each rewrite by intuition.
Build and test a product prototype with a coding assistant
Use a coding assistant to explore a product extension before committing a full development team.
Compare model outputs before changing a workflow
Run the same task across candidate models to check whether a model change alters a business-critical evaluation.
Run a supervised search for a better churn model
Let a coding assistant explore candidate prediction models against an agreed evaluation objective. Collect the experiment results and hand the selected model to engineers for validation and deployment review.
Prepare engineering requests across time zones
Use an assistant to collect work requests that arrive while an engineer is offline, identify bounded tasks it can prepare, and present proposed changes for review at the start of the next workday.
Evaluate sales and support agent conversations in batches
A product team used an external workflow to inspect historical conversations while core development continued. Separate evaluation stages made it easier to change criteria and rerun the analysis.
Check research-agent changes against a fixed evaluation checklist
A practitioner compared research workflows using a known example and explicit completion criteria before keeping changes to prompts or connected tools.
No workflows here yet.
Try a broader search or save a workflow from the library.
The library could not load.
Please check your connection and try again.
18–34 of 38 workflows