Install Jentic One Beta

Connect the ABM.dev API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the ABM.dev API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.

Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.

Step 1: Jentic One Host machine

# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fabm.dev%2Fabm" | sh

Step 2: Agent machine

# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fabm.dev%2Fabm" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.

Capabilities

What an agent can do with ABM.dev API.

Enrich B2B people and company records with every field cited to a source and a confidence score

Find contacts at target companies through people-finder jobs and stream their progress

Run account-based campaigns that surface candidate contacts for review and approval

Preview a CRM writeback diff before pushing enriched fields back to your CRM

Inspect the source breakdown and field-level attribution behind each enriched record

GET STARTED

Start building with ABM.dev API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use ABM.dev API for, with concrete tasks.

★ Agent-driven account research

An AI agent researching a target account can create an enrichment, stream its progress, and read back each field alongside the source and confidence that produced it. Because the ABM.dev API cites every value, the agent can decide whether a contact meets a confidence threshold before acting on it rather than trusting an uncited guess.

Create an enrichment for a company domain, stream progress until it completes, then read the field attribution to keep only values above a confidence threshold

CRM hygiene with reviewed writeback

Keeping a CRM current usually means trusting a bulk sync that can overwrite good data. The ABM.dev API lets a team preview the exact writeback diff first, so a reviewer sees which fields would change and which source each new value came from before approving. Approved changes are then pushed back to the connected CRM.

Preview the writeback diff for an enrichment, approve it, then execute the writeback to the connected CRM

People finding for ABM campaigns

A sales team targeting a set of accounts needs named contacts in specific roles. The ABM.dev API runs people-finder jobs against a company list and campaigns that return candidate contacts with their citations, so the team approves real people rather than scraping and guessing. Jobs stream progress so long-running searches can be polled.

Create a people-finder job for a list of company domains and poll the job until it returns candidate contacts with sources

Key Endpoints

70 endpoints — the abm.

METHOD

PATH

DESCRIPTION

POST

/v1/enrichments

Create an enrichment job

GET

/v1/enrichments

List enrichment jobs

GET

/v1/enrichments/{id}/sources

Get the source breakdown for an enrichment

POST

/v1/people-finder

Create a person finder job

POST

/v1/campaigns/confirm

Confirm and start an account-based campaign

POST

/v1/enrichments/{id}/writeback

Execute the CRM writeback for an enrichment

POST

/v1/enrichments

Create an enrichment job

GET

/v1/enrichments

List enrichment jobs

GET

/v1/enrichments/{id}/sources

Get the source breakdown for an enrichment

POST

/v1/people-finder

Create a person finder job

POST

/v1/campaigns/confirm

Confirm and start an account-based campaign

POST

/v1/enrichments/{id}/writeback

Execute the CRM writeback for an enrichment

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring the ABM.dev API by hand means handling its two credentials (an X-API-Key header for the API and a Clerk JWT bearer for signup), its streamed job progress, and CRM writeback config yourself. Through Jentic you install once, import ABM.dev from the API Directory, store the credential once, and your agent calls it.

Permission scoping

Jobs are addressed by an id in the URL path, but a rule bounds which operations your agent may call rather than which record it touches. You choose the operations it may call, such as creating and reading enrichments, so a CRM writeback execution or an API key revocation is not included unless you add it.

Credential isolation

Your ABM.dev credential 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.

Intent-based discovery

Agents search Jentic by intent such as 'enrich a company with contacts' or 'find people at a target account', and Jentic returns the matching ABM.dev operation with its input schema so the agent calls the right endpoint without reading the reference docs.

FAQs

Specific to using ABM.dev API through Jentic.

What authentication does the ABM.dev API use?

The ABM.dev API authenticates API calls with an API key sent in the X-API-Key header, and uses a Clerk-issued JWT bearer token for the organization signup bootstrap, as declared in its OpenAPI spec. Through Jentic the credential is stored once and injected at call time, so it never appears in your agent's prompt or logs.

Can I see which source supplied each enriched field from the ABM.dev API?

Yes. Every enrichment carries a source breakdown and field-level attribution, so for each value the API returns which source produced it and the confidence score, letting an agent gate on confidence before acting.

What are the rate limits for the ABM.dev API?

The OpenAPI spec does not state numeric rate limits for the ABM.dev API. Check the vendor documentation at https://abm.dev for current limits before running large batch enrichments.

How do I enrich a company through Jentic with the ABM.dev API?

Search Jentic for 'enrich a company with contacts', which returns the POST /v1/enrichments operation with its input schema, then stream progress and read the result. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Can I limit what my agent is allowed to do with the ABM.dev API?

Yes. Write a rule that allows only the enrichment and people-finder read and create operations, so the agent can research and enrich accounts but cannot execute a CRM writeback or revoke an API key, and every call it makes is logged. You decide which operations are in the rule, so nothing destructive runs unless you add it.

ABM.dev API

AI ReadinessAI-Aware (B)64/100

See full scorecard

Official vendor OpenAPI document · agent-readyData EnrichmentContact EnrichmentapiKey, bearer70 EndpointsREST

For Agents

Enrich and source B2B people and company data with every field cited to a source and confidence score, then preview and write the results back to your CRM. Runs enrichment, people-finder, and account-based campaign jobs.

Use for: Enrich a list of companies with decision-maker contacts, Find the head of marketing at a target account, Start a batch enrichment from an uploaded spreadsheet, Preview the CRM writeback diff before pushing changes

Not supported: Does not handle email sending, ad buying, or deal pipeline management. Use for B2B people and company data enrichment only.

The ABM.dev API enriches B2B people and company records and returns every field with a citation to its source and a confidence score. It runs enrichment jobs, people-finder jobs that locate contacts at target accounts, and account-based campaigns that surface candidates for review, with progress streamed as jobs run. Enriched results can be previewed as a diff and written back to a connected CRM.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: ASignals: 4

97%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

30%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: C+Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

35%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: DSignals: 4

31%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

55%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

91%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1

62%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A-Signals: 1

72%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the ABM.dev API to your agent

Capabilities

Start building with ABM.dev API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

ABM.dev API

Jentic AI Readiness Score

ABM.dev API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness