canonical: https://jentic.com/apis/boundary-ai.com/boundary-ai

# BoundaryAI API

The BoundaryAI API builds customer surveys, collects their responses, and turns the results into analysis, flags, and reports for a feedback and market-research platform. You can author a survey by hand or generate one from a short description, serve it through embedded and shareable survey flows, then read back responses and run analysis that drafts replies and raises flags. Survey series track the same study over time with evolution buckets and monitors, and reports can be scheduled and distributed to named recipients.

## For AI agents

Create and AI-generate surveys, collect responses, and analyze feedback for a BoundaryAI organization, then build and distribute reports. Authenticates with a bearer API key in the Authorization header.

## Scope

Does not handle CRM contact management, email marketing campaigns, or web traffic analytics. Use for creating surveys, collecting responses, and analyzing feedback only.

## Capabilities

- Create customer surveys by hand or generate them from a short prompt with AI
- Collect survey responses through embedded, shareable, and partial-save flows
- Analyze responses to raise flags, summarize themes, and draft replies
- Build, schedule, and distribute reports to named recipients
- Track a survey series over time with evolution buckets and monitors
- Manage API keys, organizations, and native data connectors

## Use cases

### Agent-Driven Survey Operations

An AI agent connected through Jentic creates a survey for a BoundaryAI organization, publishes it, and then reads back the collected responses so a feedback program runs without a person operating the dashboard. Because the analysis operations return structured flags and summaries, the agent can act on the findings rather than reading raw responses one by one.

Example prompt: Create a post-purchase survey for my store, publish it, and summarize the first batch of responses

### AI-Generated Survey Design

A product team turns a short brief into a ready survey by calling the AI survey generation operation, which drafts questions from a description, then refines the draft with the standard editing operations. This shortens the gap between deciding to measure something and fielding a usable questionnaire.

Example prompt: Generate a five-question customer satisfaction survey from the brief 'measure delivery speed and support quality'

### Automated Response Analysis

An analyst pipeline collects survey responses and runs the analysis operations to raise flags on concerning answers and draft replies, so a human reviews conclusions instead of combing through every response. Flags can feed monitors on a survey series to watch a metric over successive waves.

Example prompt: Analyze the latest survey wave, raise flags on negative delivery feedback, and draft a reply for each flagged response

### Scheduled Report Distribution

An operations team schedules a report on a survey series and distributes it to a recipient list, so stakeholders receive results on a cadence without anyone exporting data manually. Report subscriptions add an approval step before a run is sent.

Example prompt: Schedule a weekly report for this survey series and add two recipients to its distribution list

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/surveys` | List surveys |
| POST | `/surveys` | Create a survey |
| POST | `/surveys/ai-generate` | Generate a survey from a prompt with AI |
| GET | `/surveyseries/{org_id}` | List survey series for an organization |
| POST | `/chat/{org_id}/ask` | Ask the analytics assistant a question |
| GET | `/api/keys` | List API keys |
| POST | `/api/keys` | Create an API key |

## Key resources

- **Surveys** — Create, generate, edit, and publish surveys, and read the responses they collect
- **Analysis** — Run analysis over responses to raise flags, summarize themes, and draft replies
- **Survey Series** — Track a study over time with evolution buckets and monitors across waves
- **Reports** — Build, schedule, and distribute reports to recipients, with subscription approvals
- **API Keys** — Create, inspect, and revoke scoped API keys for an organization

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 51 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 46 / 100
  - Developer Experience & Jentic Compatibility: 60 / 100
  - AI-Readiness & Agent Experience: 50 / 100
  - Agent Usability: 43 / 100
  - Security: 59 / 100
  - AI Discoverability: 67 / 100
- **View full report:** https://jentic.com/apis/boundary-ai.com/boundary-ai/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring the BoundaryAI API by hand means managing its bearer API key auth, picking the survey, analysis, and reporting routes you need out of a large surface, and handling pagination yourself. Through Jentic you install once, import BoundaryAI from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** BoundaryAI puts the organization id in the URL path for many routes, such as its survey-series and chat routes, so a rule can pin your agent to one organization's data. You choose which operations it may call, so write actions like deleting surveys or rotating API keys are not included unless you add them.
- **Credential handling:** Your BoundaryAI API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'create a customer survey' or 'summarize survey responses', and Jentic returns the matching BoundaryAI operation with its input schema so the agent calls the right endpoint without reading the reference docs.

## Related APIs

- **Typeform API** — Conversational form and survey builder with response collection and webhooks
- **SurveyMonkey API** — Established survey platform for creating questionnaires and collecting responses
- **Qualtrics API** — Experience management platform for surveys and advanced research analysis

## FAQ

### Is there a BoundaryAI MCP server?

You don't need an MCP server to give your agent the BoundaryAI API. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent can create surveys and read responses straight away, with no extra server to run and no tool definitions loaded into the agent's context.

### Can I limit what my agent is allowed to do with the BoundaryAI API?

Yes. Write a rule that allows only the survey-read and response-read operations for one organization, so the agent can pull survey results and nothing else, and every call it makes is logged. If you later want it to create surveys as well, you add that one operation to the rule.

### What authentication does the BoundaryAI API use?

The BoundaryAI API authenticates with a bearer API key passed in the Authorization header per its OpenAPI spec, while the dashboard web app signs in with a Clerk-issued session token. Through Jentic the key is stored encrypted by your own instance and added to each request at call time, so it never appears in the agent's prompt or logs.

### Can I generate a survey with AI using the BoundaryAI API?

Yes. The API includes an AI survey generation operation that drafts a questionnaire from a short description, alongside the standard create-survey operation, so an agent can turn a prompt like 'a five-question post-purchase survey' into a ready draft it can then edit.

### What are the rate limits for the BoundaryAI API?

Each BoundaryAI API key carries its own per-minute rate limit set on the key, as described in the OpenAPI spec; the spec does not publish a single fixed number for every account. For the limit that applies to your key, check the key's settings in the BoundaryAI dashboard under Integrations Hub.

### How do I create a survey with the BoundaryAI API through Jentic?

Import the BoundaryAI API from the Jentic API Directory, then have your agent issue a request such as 'create a post-purchase survey for my store'. Jentic matches the intent to the create-survey operation and returns its input schema so the agent builds a valid request, with your stored API key injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.