Managing bot projects

On the Mercury.ai platform, all bots are organized in projects. Since most professional environments demand team collaboration, publication flows and lifecycle management, projects are a good way to think about all the things needed to create, train, publish and maintain your chatbot.

A project contains tools to build the bot, train its AI components and publish it for your end users. It has a team of collaborators with permissions and settings to control privacy and compliance related aspects of your bot.

Permission management

Whatever kind of bot project you want to implement, it will be embedded in your organization environment. The organization is the entity within which your users are organized. Use the Mercury.ai platform fine-grained permission set, so you can organize your members into different projects. You have a clear structure within your organization so that you can efficiently organize multiple bot projects as separate projects implemented by different teams.

On top of the inner structure of organizations within companies, you also have the opportunity to collaborate with partner organizations such as agencies. Reflecting on the need for separation while simultaneously coming together for a project, the Mercury.ai platform allows you to do just that: Organizations have the option to add their agency to a project. Organize your projects in the way your everyday organization works already. How you do just that and how you can set up and configure your company account on the platform will be described in detail in the section Organization.

While the organization itself is just a container for your bot projects, your users are always the key to structure your organizational pathways. It is key to work with different hierarchies, different teams with different roles within a bot project, so it is essential to manage your users efficiently. Whether you want to decide on which project users may work on or whether a user may have only a certain set of permissions, you can effortlessly configure their role the way you want it. However, you do not have to configure these role sets individually but you can also copy a set of permissions for a new user for your organization. How you can do all this and to learn more about user management, go to users.

Permission management: Mercury.ai offers you a fine-grained permission management system in which you can roles set up different roles according to each team member's position. The project owner has a different set of permission than the service agent who has a specific role in handling service requests or the bot building team that translates user stories into bot configurations. Each requirement can easily be met within the permission management and in permissions you learn everything about every single permission.

Staging and deployment

Once you have built a bot, it will be deployed to the DEV stage of your project. During the deployment process all the parts of the bot are put together and the AI is trained.

After being deployed to a DEV stage, bots can be promoted to the TEST, and ultimately to the LIVE stage. Also bots can be demoted downwards or deleted from a stage. It’s important to understand that bots on TEST and LIVE stages are always exactly the same version of the bot that you initially deployed to DEV.

To make your bot available for users to chat with, stages can be connected to channels.

Testing and troubleshooting

All bot versions that are active on a stage can be tested with the debugging chat feature in the right side bar. Since the debugging chat is no regular channel, the conversations will not show up in your inbox and you will not be listed in the bot's user overview. The test user identity and context will reset 30 minutes after the last interaction.

Bots on the DEV stages contain error message responses that hopefully point you to the solution of the problem.

The inbox of your bot shows every conversation users had with the bot and allows you to monitor the bots performance qualitatively. Users will send sentences that the NLU will not understand. To improve the bots NLU performance you can annotate the misunderstood or unknown messages directly in the inbox.

To perform more systematic tests of your bot, unit tests give you the ability to define complete conversational flows that can be automatically tested.