Reference guides for the forms apps an AI agent can work with: every endpoint, the permission each one needs, and how to give agents safe, governed access.
The Formstack API is how an app or AI agent works with a Formstack account: listing forms and their fields, reading and creating the submissions a form collects, organizing forms into folders, and registering webhooks that fire when a form is submitted.
The Google Forms API is how an app or AI agent works with a Google form: creating a form, adding and editing its questions in a single batch, reading the answers people submit, and setting whether the form is published.
The Jotform API is how an app or AI agent works with a Jotform account: listing forms, reading the submissions a form has collected, creating or cloning a form, and adding a webhook so new submissions are pushed out.
The SurveyMonkey API is how an app or AI agent works with a SurveyMonkey account: building a survey and its questions, sending it out through a collector, reading the responses that come back, and managing the contacts it goes to.
The Tally API is how an app or AI agent works with a Tally account: creating a form, updating its questions, reading the submissions people send in, or managing workspaces and webhooks.
The Typeform API is how an app or AI agent works with a Typeform account: building a form from a definition, reading the responses a form has collected, registering a webhook to receive new submissions, and managing images, themes, and workspaces.
A forms API is how an app or AI agent reads form and survey responses, or manages the forms themselves. The tools here, including Typeform, Google Forms, Jotform, and SurveyMonkey, collect submissions from people, and their APIs let an agent pull responses, react when one arrives, or create and edit a form.
Responses often contain personal information people typed in, so reading them is the main access an agent holds, and a write permission can change a live form. Access runs on an access token scoped to particular forms or actions. A governed layer lets an agent that summarises new responses read submissions without being able to alter the form or reach unrelated ones.
Bollard AI sits between a team's AI agents and the apps it runs on. Grant each agent exactly the access it needs, read or write, app by app, and every call is checked and logged.