Install Jentic One Beta

Connect the Lev API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Lev 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%2Flev.com%2Flev" | 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%2Flev.com%2Flev" | 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 Lev API.

Create a financing deal with loan amount, loan type, and transaction type, then move it to a pipeline stage

Search the lender directory by name, headquarters state, or lender type and open a lender's profile

Record a lender placement against a deal and track its status and outreach date

Log a term sheet quote with total rate, initial funding, quote type, and rate type, then mark the winning one

GET STARTED

Start building with Lev API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Lev API for, with concrete tasks.

★ Agent-run deal desk through Jentic

A capital advisor's AI agent can take a new financing request, create the deal in Lev, search the lender directory for matching lenders, and open a placement for each lender company already in the account. Through Jentic the agent finds the deal, lender-directory, company, and placement operations by intent and loads their schemas, so it works the Lev pipeline without the developer wiring each call by hand.

Create a deal titled '123 Main St Acquisition' with a loan_amount of 12000000, search the lender directory with filter[state]=NY, then create a placement using the new deal_id and the matching lender's private_company_id from the companies list.

Term sheet comparison

When several lenders quote on one deal, the Lev API stores each quote as a term sheet tied to a placement, with fields such as total_rate, initial_funding, max_ltv, max_ltc, and term. Listing a deal's term sheets lets an agent or analyst compare quotes side by side and flag the winning one with a partial update.

List the term sheets on a deal, find the one with the lowest total_rate, and patch it with winning set to true.

Deal fact lookup for underwriting

Lev indexes the facts extracted from a deal's documents. An underwriting assistant can search those facts with a natural-language context string, inspect the per-document observations behind a value, and record a user-supplied metric when a figure is missing, using metric ids from the deal's metric definitions.

Search the indexed facts of a deal with the context 'net operating income', then list the observations behind the top result's sot_id.

Market rate snapshot for pricing

Pricing a floating-rate loan needs today's index. The Lev API returns current base rates such as SOFR, CMT, and Prime, plus the asset type definitions it uses, so an agent can quote an all-in rate or populate a deal's base_rate before a term sheet is written.

Fetch the current base rates and report the SOFR value alongside the list of asset types.

Key Endpoints

81 endpoints — the lev api runs commercial real estate debt deals from origination to term sheet: it creates and updates deals, moves them through pipeline stages, and records lender placements and the term sheets lenders quote against them.

METHOD

PATH

DESCRIPTION

POST

/api/external/v2/deals

Create a new deal

GET

/api/external/v2/deals

List deals with filtering and sorting

POST

/api/external/v2/deals/{deal_id}/pipeline

Move a deal to a pipeline stage

GET

/api/external/v2/lenders/directory

Search the lender directory

POST

/api/external/v2/placements

Create a placement against a deal

POST

/api/external/v2/deals/{deal_id}/term-sheets

Create a term sheet against a placement

POST

/api/external/v2/deals/{deal_id}/index/search

Search indexed deal facts

GET

/api/external/v2/market/base-rates

Get current base rates

POST

/api/external/v2/deals

Create a new deal

GET

/api/external/v2/deals

List deals with filtering and sorting

POST

/api/external/v2/deals/{deal_id}/pipeline

Move a deal to a pipeline stage

GET

/api/external/v2/lenders/directory

Search the lender directory

POST

/api/external/v2/placements

Create a placement against a deal

POST

/api/external/v2/deals/{deal_id}/term-sheets

Create a term sheet against a placement

POST

/api/external/v2/deals/{deal_id}/index/search

Search indexed deal facts

GET

/api/external/v2/market/base-rates

Why Jentic?

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

Setup

Wiring Lev by hand means sending its bearer token on the right operations, threading deal, placement, and term sheet ids between calls, and paging with cursors. Through Jentic you install once, import Lev from the API Directory, store the token once, and your agent calls it.

Permission scoping

Lev puts the deal id in the URL path (/api/external/v2/deals/{deal_id}/...), so a rule can pin your agent to one deal and the operations you pick on it. You choose the operations it may call, so destructive ones like archiving a deal or revoking an API key are not included unless you add them.

Credential isolation

Your Lev 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 'search the lender directory' or 'log a term sheet', and Jentic returns the matching Lev operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Lev API through Jentic.

What authentication does the Lev API use?

The Lev API uses HTTP bearer authentication per its OpenAPI spec: you send an API key or JWT in the Authorization header as a bearer token. Two operations are open without a token, the health check and the API key validation call, which accepts a key and returns its authentication details. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at request time.

Is there a Lev API MCP server?

You don't need an MCP server to give your agent the Lev API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it, discovering deal, lender, and term sheet operations on demand instead of loading a full set of tool definitions into its context.

Can I search for lenders with the Lev API?

Yes. The lender directory operation searches by lender name with partial and close-spelling matches, and filters by headquarters state as an uppercase two-letter code such as NY and by lender type, with comma-separated values to match several. Each result's org_id opens the lender's full directory profile.

What are the rate limits for the Lev API?

The OpenAPI spec does not specify rate limits. Check the Lev developer documentation at https://www.lev.com/docs for current limits on your account.

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

Yes. For example, write a rule that allows the term sheet list and read operations and the term sheet update under /api/external/v2/deals/123/, so the agent can compare quotes and mark a winner on that one deal while deal archiving, note deletion, and API key creation stay outside its reach. Every call it makes is logged.

How do I move a deal through the pipeline with the Lev API through Jentic?

Search Jentic for 'move a deal to a pipeline stage', load the operation, and pass the deal_id in the path with the pipeline_id and pipeline_status_id in the body; the pipelines list returns the available ids and statuses. Jentic injects your bearer token at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Does unlocking a lender contact cost credits?

Yes. The unlock action on a contact reveals an AI-recommended lender contact, charges credits, and requires the ai:actions scope. You can check the active account's remaining credits with the billing credit balance operation before calling it.

Lev API

AI ReadinessNon-Ready (C)56/100

See full scorecard

Official vendor OpenAPI document · agent-readyCRMDeal Pipelinebearer81 EndpointsREST

For Agents

Create and advance commercial real estate financing deals, search the lender directory, log placements and term sheets, and query a deal's documents, memos, and indexed facts.

Use for: I need to create a new bridge loan deal for a multifamily acquisition, Find all lenders headquartered in NY that match a lender type, Move this deal to the next stage in our pipeline, Log a term sheet a lender just quoted on this deal

Not supported: Does not originate or fund loans, process payments, or e-sign closing documents. Use for managing commercial real estate debt deals, lender placements, and term sheets only.

The Lev API runs commercial real estate debt deals from origination to term sheet: it creates and updates deals, moves them through pipeline stages, and records lender placements and the term sheets lenders quote against them. It also searches a lender directory by name, headquarters state, and lender type, returns current base rates such as SOFR, CMT, and Prime, and exposes each deal's documents, checklists, generated memos, and indexed financial facts. Companies, contacts, and notes on deals, placements, and checklist tasks round out the relationship record.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: FSignals: 4

38%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

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

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: B-Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

52%

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: C-Signals: 4

49%

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.

58%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: ASignals: 1

89%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

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).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: B+Signals: 1

67%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Lev API to your agent

Capabilities

Start building with Lev API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Lev API

Jentic AI Readiness Score

Lev 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