Official vendor OpenAPI document · agent-readyData EnrichmentCompany Databearer14 EndpointsREST
For Agents
Search companies, list their professionals, and generate sales assets through Databook AI. Run account reasoning, start account chats, and submit batch jobs to enrich lists of target accounts.
Use for: Search for companies by name, Find the professionals who work at a target account, Generate a sales asset for an upcoming meeting, Run deep reasoning on an account to prepare talking points
Not supported: Does not handle CRM record storage, email sequencing, or deal-stage tracking. Use for account intelligence and sales asset generation only.
The Databook AI API retrieves account intelligence for B2B sales teams, searching companies by name and listing the professionals associated with each one. It generates sales assets from the asset studio, runs deep reasoning over a target account, and answers account questions through a chat endpoint. Batch jobs enrich lists of accounts asynchronously, returning results you can poll for once the job completes.
Install Jentic One Beta
Connect the Databook AI to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Databook AI, 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.
1
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%2Fdatabook.com%2Fdatabook" | sh2
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%2Fdatabook.com%2Fdatabook" | sh
jentic register # connects your agent to your Jentic One instanceJentic 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 Databook AI API.
Search for companies by name and pull the professionals associated with each account
Generate sales assets from the asset studio library for a target account
Run deep reasoning over an account to surface strategy and talking points
Submit batch jobs to enrich a list of accounts and retrieve the results when ready
Start a chat session to ask questions about an account in natural language
List the account insights available for a target company
Use Cases
Patterns agents use Databook AI API for, with concrete tasks.
★ Account Research Agent
An AI agent researches a target account end to end: it searches Databook for the company, lists the professionals attached to it, pulls the available insights, and runs deep reasoning to assemble strategy notes. The agent discovers each Databook operation through Jentic by intent, so it calls company search, the professionals lookup, and reasoning in sequence without hardcoding endpoint paths.
Search Databook for a company by name, list its professionals, then run deep reasoning on the account and return the strategy summary
Pre-Meeting Sales Prep
A seller preparing for a meeting needs a briefing on the account. The agent searches the company, generates a sales asset from the asset studio, and lists the insights on file, producing a ready-to-read brief. Databook handles the asset generation server-side, so the agent only submits the request and reads the generated asset back.
Search for the target company, generate a sales asset for it, and return the generated asset along with the available account insights
Bulk Account Enrichment
A revenue team wants intelligence on a long list of accounts rather than one at a time. The agent downloads the batch input CSV template, submits a batch job, polls for completion, and retrieves the per-account results. Databook processes the list asynchronously, so the agent fires the job once and collects results when the job finishes.
Submit a batch job for a CSV list of accounts, poll the job by its id until it completes, and retrieve the results
Key Endpoints
14 endpoints — the databook ai api retrieves account intelligence for b2b sales teams, searching companies by name and listing the professionals associated with each one.
METHOD
PATH
DESCRIPTION
GET
/v1/asset/companies
Search companies by name
GET
/v1/asset/companies/{company_id}/professionals
List professionals at a company
POST
/v1/reasoning
Run deep reasoning over an account
POST
/v1/chat
Create a chat session about an account
GET
/v1/insights
List available account insights
POST
/v1/batch/job
Create a batch enrichment job
GET
/v1/batch/job/{job_id}
Get a batch job by id
GET
/v1/batch/job/{job_id}/result
Retrieve batch job results
GET
/v1/asset/companies
Search companies by name
GET
/v1/asset/companies/{company_id}/professionals
List professionals at a company
POST
/v1/reasoning
Run deep reasoning over an account
POST
/v1/chat
Create a chat session about an account
GET
/v1/insights
List available account insights
POST
/v1/batch/job
Create a batch enrichment job
GET
/v1/batch/job/{job_id}
Get a batch job by id
GET
/v1/batch/job/{job_id}/result
Retrieve batch job results
Jentic AI Readiness Score
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.
D
DatabookAI REST API
- Foundational (C+)59/100
93
Foundational Compliance69
Developer Experience & Jentic Compatibility44
AI-Readiness & Agent Experience94
Agent Usability60
Security32
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
93
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A+Signals: 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).
75%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
69
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B+Signals: 4
1%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
75%
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.
44
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: DSignals: 4
24%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
54%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
60
Security
Trust, risk posture, and security compliance.
Grade: B-Signals: 1
60%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
32
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: FSignals: 1
32%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Databook by hand means managing its bearer token and sending the right user and tenant identity headers on every call. Through Jentic you install once, import Databook from the API Directory, store the token once, and your agent calls it.
Permission scoping
You choose which Databook operations your agent may call, so you can allow company search and insight reads while leaving asset generation and batch job creation out unless you add them. Databook carries account and job identifiers in the request body and URL path, so rules bound which operations run.
Credential isolation
Your Databook token 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 find professionals at a company or run account reasoning, and Jentic returns the matching Databook operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Databook AI API through Jentic.
What authentication does the Databook AI API use?
The Databook API authenticates with a bearer token in the Authorization header, per its OpenAPI spec, and requests also carry identity headers that resolve the calling user and tenant. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it never lands in the agent's prompt or logs.
Can I generate sales assets with the Databook AI API?
Yes. The asset studio operations let your agent browse the asset library, generate an asset for a target company, and read the generated asset back by its generation id. Pair it with the company search operation to resolve the account first.
What are the rate limits for the Databook AI API?
The OpenAPI spec does not publish rate limits for the Databook API. Check Databook's own API documentation for the current limits that apply to your account, since access is provisioned per tenant.
Can I limit what my agent is allowed to do with the Databook AI API?
Yes. Write a rule that allows only the read operations such as company search, the professionals lookup, and insight listing, so the agent can research accounts but cannot generate assets or create batch jobs unless you add those operations. Every call it makes is logged.
How do I run account reasoning with the Databook AI API through Jentic?
Search Jentic for an intent like research a target account, store your Databook token once, and your agent calls the reasoning operation with the account it resolved from company search. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a Databook AI MCP server?
You don't need an MCP server to give your agent the Databook API. Jentic connects it directly from the API Directory: import it, store your token once, and your agent calls the operations it needs on demand.
GET STARTED