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

# Autobound API

Jentic publishes the only available OpenAPI specification for Autobound API, keeping it validated and agent-ready. Autobound generates personalised cold-outbound emails and openers using a single content-generation endpoint that takes seller context and prospect details and returns a ready-to-send message. The API consolidates prospect research, news triggers, and seller positioning into one POST call, removing the need for sales reps to write every email by hand. It is purpose-built for outbound sequencers and AI SDR agents that need a fresh, personalised hook for every prospect.

## For AI agents

Generate a personalised cold outbound email or opener for a specific prospect, given seller context and prospect details. Returns a single ready-to-send message in one POST call.

## Scope

Does not handle email delivery, prospect database lookups, or engagement tracking - use for generating personalised email and opener copy only.

## Capabilities

- Generate a personalised cold-outbound email body for a named prospect with POST `/generate-content/v2.0`
- Produce a short opener line that can be dropped into an existing email template
- Tailor the message to the seller's product, value proposition, and target persona
- Incorporate prospect-side signals (company, role, industry) into the generated copy
- Support multiple content types in a single endpoint by varying the request payload

## Use cases

### AI SDR agent outbound generation

Drive an AI SDR that pulls a prospect from a CRM, calls Autobound to generate a personalised email body, and queues the message for review or auto-send. The single POST `/generate-content/v2.0` call returns the full email, so the agent does not need to chain multiple research steps. Throughput is limited only by the agent's CRM ingestion rate and Autobound's per-plan quota.

Example prompt: POST `/generate-content/v2.0` with prospect.name, prospect.company, seller.value_proposition, and content_type=email to receive a ready-to-send body

### Opener-only injection into existing sequences

Keep an existing outbound sequencer (Outreach, Salesloft) but personalise just the opening line of each email. Set content_type=opener in the request and Autobound returns a single sentence keyed to the prospect, which the sequencer merges as the first line of a template. This avoids rewriting the full sequence while still defeating spam filters that flag fully-templated emails.

Example prompt: Call `/generate-content/v2.0` with content_type=opener and the prospect's LinkedIn or company URL to produce a one-line hook

### Account-based marketing campaign

Run an ABM campaign where every contact at a target account receives a uniquely worded message tied to that account's recent news or hiring signals. Loop the contact list, call `/generate-content/v2.0` per contact with consistent seller context but varying prospect detail, and store the results for review. Because the API takes seller positioning as input, the campaign voice stays consistent across hundreds of generated messages.

Example prompt: For each contact in a target account, POST `/generate-content/v2.0` with the same seller block and contact-specific prospect block, then store the returned email

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/generate-content/v2.0` | Generate a personalised cold outbound email or opener |

## Key resources

- **Content Generation** — Single endpoint for generating personalised emails and openers

## Why Jentic

- **Setup:** Wiring the Autobound API by hand means managing the X-API-KEY header and assembling the prospect, seller, and content-type request body for its single generation endpoint yourself. Through Jentic you install once, import the Autobound API from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** Autobound exposes one operation, content generation, with inputs carried in the request body rather than as resource ids in the URL path, so scope your agent to just that operation. Because you choose the allowed operations, nothing beyond generating email and opener copy is included unless you add it.
- **Credential handling:** Your Autobound X-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 'generate a personalised sales email', and Jentic returns the matching Autobound operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Outreach API** — Outreach is a sales sequencer that can deliver Autobound-generated emails at scale
- **Salesloft API** — Salesloft is a cadence and dialer platform that consumes Autobound's generated copy
- **Apollo API** — Apollo combines a B2B contact database with built-in AI email writing

## FAQ

### Why is there no official OpenAPI spec for Autobound API?

Autobound publishes documentation on ReadMe but does not host a downloadable OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Autobound API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.

### What authentication does the Autobound API use?

Autobound uses an API key sent in the X-API-KEY header on every request. The key is issued in the Autobound dashboard. Through Jentic the key is stored in the credential vault and injected per call so the agent never sees the raw value.

### What does the Autobound API return?

POST `/generate-content/v2.0` returns a generated message tailored to the prospect and seller context provided in the request. The exact shape depends on the content_type - an 'email' returns subject and body fields, while an 'opener' returns a single hook sentence.

### How do I generate a cold outbound email through Jentic?

Search Jentic for 'generate a personalized sales email', load the POST `/generate-content/v2.0` operation, and execute it with prospect details and your seller value proposition. Jentic injects the X-API-KEY header. Get started with Jentic One, the self-hosted execution layer.

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

Autobound enforces per-plan request quotas in the dashboard rather than the OpenAPI spec. The `/generate-content/v2.0` endpoint is LLM-backed, so latency is several seconds per call; if you receive a 429, back off and consider parallelising across users rather than per-account.

### Can I generate just an opener instead of a full email?

Yes. Set content_type to 'opener' in the request body and Autobound returns a single personalised sentence that can be merged into the first line of an existing template, leaving the rest of the email untouched.

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

Yes. Because Jentic One is self-hosted, your own rules decide which operations and credentials the agent may use. The Autobound API exposes a single operation, content generation at POST `/generate-content/v2.0`, so you scope the agent to just that call and nothing else runs unless you add it. Its inputs (prospect details, seller value proposition, and content_type) are carried in the request body rather than as resource IDs in the path, and your X-API-KEY is injected at execution time without ever entering the agent's prompt or context.