Integration
Connect CrewForm to Softwium
When AI Agent Task Failed fires in CrewForm, your agent runs Add book in Softwium. 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 CrewForm and Softwium 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 CrewForm can start in Softwium
When AI Agent Task Failed in CrewForm
then Add book in Softwium
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 CrewForm and Softwium
Triggers and actions 1 trigger · 30 actions
- AI Agent Task Failed
Triggers when a CrewForm AI agent task fails.
- Add agent
Creates a new AI agent in your CrewForm workspace with the model, instructions and settings you choose.
- Delete agent
Deletes an AI agent from your CrewForm workspace.
- Delete task
Deletes a task from your CrewForm workspace.
- Get agent
Returns a single CrewForm agent by its id, including its model, prompt and settings.
- Get task
Returns a single CrewForm task by its id, including its title, status, priority, assigned agent and results.
- List agents
Returns all AI agents in your CrewForm workspace, with each agent's name, model, prompt and settings.
- List tasks
Returns the tasks in your CrewForm workspace, newest first, optionally only those with a given status.
- Send Task to AI Agent
Creates a task in CrewForm assigned to an AI agent, which dispatches it to that agent to work on right away. Returns the created task.
- Update agent
Updates an existing CrewForm agent's name, model, prompt, temperature, tools, status or configuration. Only the fields you fill in are changed.
- Update task
Updates an existing CrewForm task's title, description, priority, status, assigned agent or team, or metadata.
- Add book
creates a new fake book, returns HTTP 201. Note: the vendor does not actually persist writes (test/mock API).
- Add currency
creates a new fake currency, returns HTTP 201. Note: the vendor does not actually persist writes (test/mock API).
- Add people
creates a new fake person record, returns HTTP 201. Note: the vendor does not actually persist writes (test/mock API).
- Add pokemon
creates a new fake pokemon, returns HTTP 201. Note: the vendor does not actually persist writes (test/mock API).
- Delete book
deletes the fake book with the given ID. Note: the vendor does not actually persist writes (test/mock API).
- Delete currency
deletes the fake currency with the given ID. Note: the vendor does not actually persist writes (test/mock API).
- Delete people
deletes the fake person record with the given ID. Note: the vendor does not actually persist writes (test/mock API).
- Delete pokemon
deletes the fake pokemon with the given ID. Note: the vendor does not actually persist writes (test/mock API).
- Get book
returns the fake book with the given ID, or HTTP 404 if not found.
- Get currency
returns the fake currency with the given ID, or HTTP 404 if not found.
- Get people
returns the fake person record with the given ID, or HTTP 404 if not found.
- Get pokemon
returns the fake pokemon with the given ID, or HTTP 404 if not found.
- List books
returns all fake books (optional ?limit=N query param to cap the count). Read-only test data, no auth.
- List currencies
returns all fake currencies (optional ?limit=N query param to cap the count). Read-only test data, no auth.
- List peoples
returns all fake people records (optional ?limit=N query param to cap the count). Read-only test data, no auth.
- List pokemons
returns all fake pokemon records (optional ?limit=N query param to cap the count). Read-only test data, no auth.
- Update book
partially updates the fake book with the given ID. Note: the vendor does not actually persist writes (test/mock API).
- Update currency
partially updates the fake currency with the given ID. Note: the vendor does not actually persist writes (test/mock API).
- Update people
partially updates the fake person record with the given ID. Note: the vendor does not actually persist writes (test/mock API).
- Update pokemon
partially updates the fake pokemon with the given ID. Note: the vendor does not actually persist writes (test/mock API).
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 CrewForm
CrewForm to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
CrewForm to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
CrewForm to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
CrewForm to Google SheetsGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
CrewForm to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
CrewForm to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
More into Softwium
Questions
CrewForm and Softwium, answered
What can start an automation from CrewForm?
Any of CrewForm's 1 trigger in the catalog, including AI Agent Task Failed. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Softwium when something happens in CrewForm?
Any of Softwium's 20 actions, including Update book, Update currency, Update people and Update pokemon. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Softwium to CrewForm?
Softwium has no triggers in the catalog today, so automations start in CrewForm. If you need the other direction, ask: your agent reads Softwium's API documentation and adds it.
Do I have to build a connector for CrewForm or Softwium?
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 CrewForm and Softwium 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.