Integration
Connect Azure DevOps and Small Improvements
When Completed Build fires in Azure DevOps, your agent runs Add 1:1 Action Item in Small Improvements, or New Goal in Small Improvements to Add Link to Work Item in Azure DevOps. Describe the whole flow and it is built, tested on every scenario and kept running.
What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.
Build solutions, not workarounds.
What do you want Azure DevOps and Small Improvements to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.
Set it up in your client
Claude Code
Run this in the directory you want to work in.
claude mcp add --transport http -s project apiant-ai https://mcp.apiant.aiStart Claude Code there, approve the server, and sign in in the browser page it opens.
Claude Code guide (opens in a new tab)Claude, web and desktop
Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.
Setup guide (opens in a new tab)Cursor
Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.
Setup guide (opens in a new tab)Zed
Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.
Setup guide (opens in a new tab)Codex and the ChatGPT desktop app
Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.
Setup guide (opens in a new tab)Any other MCP client
Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.
Setup guide (opens in a new tab)Example flows
What Azure DevOps and Small Improvements can do together
From Azure DevOps to Small Improvements
When Completed Build in Azure DevOps
then Add 1:1 Action Item in Small Improvements
When New Work Item in Azure DevOps
then Add 1:1 Talking Point in Small Improvements
From Small Improvements to Azure DevOps
When New Goal in Small Improvements
then Add Link to Work Item in Azure DevOps
When New Meeting Action Item in Small Improvements
then Create Work Item in Azure DevOps
Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.
Everything your agent can do with Azure DevOps and Small Improvements
Triggers and actions 9 triggers · 11 actions
Trigger
Code Push (Git)Triggers when commits are pushed to a Git repository in an Azure DevOps project.
Trigger
Completed BuildTriggers when a build finishes in an Azure DevOps project, with its result (succeeded, failed, partially succeeded or canceled).
Trigger
New Work ItemTriggers when a work item is created in an Azure DevOps project.
Trigger
New Work Item CommentTriggers when someone comments on a work item in an Azure DevOps project.
Trigger
Updated Work ItemTriggers when a work item is updated in an Azure DevOps project, with the work item's current values and the list of fields that changed.
Action
Add Link to Work ItemAdds a link to an Azure DevOps work item: a related, parent, child, predecessor, successor or duplicate link to another work item, or a hyperlink to a web page.
Action
Create Work ItemCreates a new work item (such as a Task, Bug, Issue or User Story) in an Azure DevOps project.
Action
Find Work ItemFinds work items in an Azure DevOps project that match a Work Item Query Language (WIQL) query, returning the matching work item IDs, or the matching links for a link query.
Action
Trigger BuildQueues a new run of an Azure DevOps build pipeline, optionally for a specific branch or commit and with pipeline variables or parameters.
Action
Update Work ItemUpdates an existing Azure DevOps work item: changes its title, description, state, assignee, area, iteration, priority or tags, and can add a discussion comment. Fields left blank are not changed.
Trigger
Anytime FeedbackTriggers when you receive new Anytime Feedback.
Trigger
New GoalTriggers when anyone in the company creates a new public goal.
Trigger
New Meeting Action ItemTriggers when a new action item is created in your meetings.
Trigger
New PraiseTriggers when new praise is given.
Action
Add 1:1 Action ItemAdds an action item to a 1:1 meeting.
Action
Add 1:1 Talking PointAdds a talking point to a 1:1 meeting.
Action
Add Reviewee to Feedback CycleAdds one or more people as reviewees to a feedback cycle by creating their feedback requests.
Action
Find PersonFinds a person by email address.
Action
Find PraiseFinds public praise a person received in a date range.
Action
Find Review ContentReturns a person's performance reviews: cycles, review text and ratings.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from Azure DevOps
Azure DevOps to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Azure DevOps to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Azure DevOps to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Azure DevOps to Google SheetsGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Azure DevOps to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Azure DevOps to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
More into Small Improvements
HubSpot to Small ImprovementsHubSpot is your all-in-one stop for all of your marketing software needs.
Salesforce to Small ImprovementsSalesforce is a leading enterprise customer relationship management (CRM) platform.
Slack to Small ImprovementsSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Google Sheets to Small ImprovementsGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Gmail to Small ImprovementsGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to Small ImprovementsGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Questions
Azure DevOps and Small Improvements, answered
What can start an automation from Azure DevOps?
Any of Azure DevOps's 5 triggers in the catalog, including Completed Build, New Work Item, New Work Item Comment and Updated Work Item. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Small Improvements when something happens in Azure DevOps?
Any of Small Improvements's 6 actions, including Add 1:1 Action Item, Add 1:1 Talking Point, Add Reviewee to Feedback Cycle and Find Person. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Small Improvements to Azure DevOps?
Yes. When something happens in Small Improvements, your agent can act in Azure DevOps too. This page covers both directions: Small Improvements's triggers and Azure DevOps's actions are listed here as well.
Do I have to build a connector for Azure DevOps or Small Improvements?
No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.
Can my AI client use Azure DevOps and Small Improvements without building an automation?
Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.
What happens when something fails?
Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.
Is there a free plan?
Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.