canonical: https://jentic.com/apis/compelling.ai/compelling

# Compelling API

The Compelling API builds research lists of target accounts and contacts inside a workspace and enriches them with AI-generated insight columns. It generates contacts for a list, adds insight columns whose answers are produced on demand, runs multi-step research workflows, and exports the results or pushes them to a connected CRM. Lists, views, accounts, and contacts are each addressed by id so an agent can assemble and refine a target list programmatically. Authentication uses a bearer API key issued from your workspace settings.

## For AI agents

Build workspace research lists of accounts and contacts, generate AI insight columns and their answers, run research workflows, and export results or sync them to a CRM through Compelling.

## Scope

Does not handle email sending, payment processing, or deterministic data verification. Use for building and AI-enriching account and contact research lists only.

## Capabilities

- Build a research list of target accounts inside a workspace
- Generate contacts for a list from Compelling's data
- Add AI insight columns and generate their answers for accounts and contacts
- Run a multi-step research workflow over a list
- Create filtered views of a list for a specific segment
- Export a list or push its records to a connected CRM

## Use cases

### Agent-Built Target List

An AI agent connected through Jentic can assemble a prospecting list end to end: it creates a list in a workspace, adds the target accounts, defines an insight column with a research question, and generates the answers for each account. The agent returns a researched list without a human opening the Compelling app.

Example prompt: Create a list in a workspace, add accounts, add an insight column, and generate its answers for each account

### Account Research at Scale

Compelling's insight columns turn a research question into a generated answer per account, so a team can research hundreds of companies at once. An agent adds an insight column, such as funding stage or recent hiring, and generates answers across the whole list rather than researching each account by hand.

Example prompt: Add an insight column asking for each account's funding stage and generate answers across the list

### Contact Generation

Once the accounts are set, Compelling can populate the people. The contacts generation operation produces contacts for a list of target accounts, so an agent fills in decision-makers to research and later export, keeping the account and contact layers in one workspace.

Example prompt: Generate contacts for a list of target accounts and review the returned people

### CRM Export

Research is only useful once it reaches the team's system of record. Compelling exports a list and pushes its enriched records through a configured integration, so an agent delivers finished research into the connected CRM instead of handing back a raw file.

Example prompt: Export a research list and push the enriched records to the connected CRM

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/workspaces` | Create a workspace |
| POST | `/workspaces/{workspace_id}/lists` | Create a research list |
| POST | `/workspaces/{workspace_id}/lists/{list_id}/accounts` | Add an account to a list |
| POST | `/workspaces/{workspace_id}/lists/{list_id}/accounts/insights` | Add an AI insight column for accounts |
| POST | `/workspaces/{workspace_id}/lists/{list_id}/accounts/insights/{insight_id}/answers` | Generate answers for an insight column |
| POST | `/workspaces/{workspace_id}/lists/{list_id}/contacts` | Generate contacts for a list |
| POST | `/workspaces/{workspace_id}/lists/{list_id}/workflows/{workflow_id}/run` | Run a research workflow |

## Key resources

- **Workspaces and Lists** — Create workspaces and the research lists that hold accounts and contacts
- **Accounts** — Add target accounts to a list and attach insight columns
- **Contacts** — Generate contacts for a list and attach contact insight columns
- **Insights and Workflows** — Add insight columns, generate their answers, and run multi-step research workflows

## 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:** 62 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 73 / 100
  - Developer Experience & Jentic Compatibility: 63 / 100
  - AI-Readiness & Agent Experience: 45 / 100
  - Agent Usability: 91 / 100
  - Security: 60 / 100
  - AI Discoverability: 62 / 100
- **View full report:** https://jentic.com/apis/compelling.ai/compelling/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 Compelling by hand means handling its bearer workspace key, nesting every call under workspace and list ids, and polling long-running insight and workflow jobs. Through Jentic you install once, import Compelling from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** Compelling puts the workspace and list ids in the URL path (`/workspaces/{workspace_id}/lists/{list_id}/...`), so a rule can pin your agent to one list: it can read and enrich that list and nothing else. You choose the operations it may call, so actions like resetting a workspace or deleting a list are not included unless you add them.
- **Credential handling:** Your Compelling workspace 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 'build a target account list' or 'generate research insights', and Jentic returns the matching Compelling operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Apollo.io** — Apollo offers a large prospect database with built-in search and sequencing.
- **Clearbit** — Clearbit returns structured firmographic and technographic attributes for a company.
- **Hunter** — Hunter finds and verifies business email addresses for the contacts a list produces.

## FAQ

### What authentication does the Compelling API use?

The Compelling API authenticates with a bearer API key issued from your workspace settings, passed as an Authorization header per its OpenAPI spec. When you call it through Jentic, that key is stored once by your own Jentic One instance and injected at execution time, so it never reaches the agent's prompt or logs.

### Can I generate AI research insights with the Compelling API?

Yes. You add an insight column to a list of accounts or contacts with a research question, then call the insight answers operation to generate an answer per record. This lets an agent research a whole list, such as each account's funding stage, in one pass rather than one company at a time.

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

The OpenAPI spec does not define numeric rate limits for the Compelling API, and research operations also consume workspace credits. Check the Compelling documentation at https://docs.compelling.ai for the current request limits and credit costs.

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

Yes. Write a rule that allows only the account-add and insight-generate operations on one list, so the agent can build and enrich that list but cannot reset the workspace or delete the list, and every call it makes is logged.

### How do I generate contacts for a list with the Compelling API through Jentic?

Search Jentic with an intent like 'generate contacts for an account list', and Jentic returns the contacts generation operation at `/workspaces/{workspace_id}/lists/{list_id}/contacts` with its input schema so your agent passes the workspace and list ids. To run it on your own infrastructure, install Jentic One from its GitHub repo.

### Is there a Compelling MCP server?

You don't need an MCP server to give your agent Compelling. Jentic connects it directly from the API Directory: import the API, store your workspace key once, and your agent calls the list, account, contact, and insight operations on demand.