Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Conturs Scoring 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%2Fconturs.com%2Fconturs-scoring-api" | shStep 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%2Fconturs.com%2Fconturs-scoring-api" | 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.
What an agent can do with Conturs Scoring API.
Score a single lead against the configured ICP model via POST /leads
Receive a 0-100 fit score with factor-level breakdown for sales qualification
Probe API liveness with the GET /health endpoint before bulk scoring runs
Embed scoring directly inline in a CRM enrichment workflow without webhooks
Authenticate per-call by sending the api_key in the request body alongside lead data
GET STARTED
Patterns agents use Conturs Scoring API for, with concrete tasks.
★ Inbound Lead Qualification
Score every form submission, demo request, or trial signup against the company's ICP model before routing to sales. POST /leads returns a 0-100 score and factor breakdown so reps see exactly why a lead matched. Suited to revenue teams handling between dozens and thousands of inbound leads per week who need consistent, ICP-aligned prioritisation.
Submit a lead with email jane@acme.com, company Acme Inc, and title VP Engineering to POST /leads and return the fit score
CRM Enrichment Workflow
Plug Conturs scoring into the moment a contact is created in the CRM so the score lands on the record without manual review. The single POST /leads call slots into a Zapier or workflow step, returning a numeric score and factor list that can be written back to custom fields. Useful for ops teams that want lead grading visible directly on contact records.
When a new HubSpot contact is created, call Conturs POST /leads with the contact's email and company and write the returned score to the lead_score field
Batch Lead Backfill
Score historical leads stored in a CSV or warehouse against the current ICP model to find latent pipeline. Iterate through the dataset, call POST /leads per record, and write back the score and factor breakdown for sales follow-up. Fits one-off backfills of ten thousand leads or recurring weekly re-scoring as the ICP evolves.
Iterate through last quarter's 5,000 leads, call POST /leads for each, and write a new csv with the score and top factor
Agent-Driven Lead Triage via Jentic
Let an AI agent triage inbound leads through Jentic without hard-coding the Conturs URL. The agent searches Jentic for 'score a lead', loads the schema, and calls POST /leads with values pulled from the inbound payload. Through Jentic the API key sits in the vault, so the agent can run scoring loops without ever holding the secret in context.
Search Jentic for 'score a lead', load the Conturs schema, then score the latest inbound demo request and post the score to Slack
2 endpoints — jentic publishes the only available openapi specification for conturs scoring api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/leads
Score a lead against the configured ICP model
/health
Health check endpoint
/leads
Score a lead against the configured ICP model
/health
Health check endpoint
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Conturs Scoring API by hand means passing your api_key as a query parameter and handling the lead scoring request yourself. Through Jentic you install once, import the Conturs Scoring API from the API Directory, store the api_key once, and your agent calls it.
Permission scoping
The Conturs Scoring API identifies its lead in the request body rather than the URL path, so you limit the agent to the operations it needs, such as scoring a lead or checking service health, and it can call nothing outside that set. Leaving an operation out of the allowed set keeps it unavailable to the agent.
Credential isolation
Your Conturs 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.
Intent-based discovery
Agents search Jentic by intent such as 'score a lead against our ICP', and Jentic returns the matching Conturs operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Conturs Scoring API through Jentic.
Why is there no official OpenAPI spec for Conturs Scoring API?
Conturs does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Conturs Scoring 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 Conturs Scoring API use?
The API uses an API key passed in the request body as the api_key field on each POST /leads call. There is no header-based or OAuth flow. Through Jentic the api_key is held in the vault and injected at execution time so it never appears in the agent's prompt context.
Can I score multiple leads in a single Conturs API call?
POST /leads is documented as the lead scoring endpoint in the spec. For multiple leads, iterate and call /leads per lead - the API surface is intentionally small (two endpoints total) and there is no documented batch operation.
What does the Conturs lead score actually return?
POST /leads returns a 0-100 fit score against your configured ICP model along with a factor breakdown explaining which lead attributes drove the score. Use the factor list to surface qualification reasoning to reps rather than a black-box number.
What are the rate limits for the Conturs Scoring API?
Rate limits are not declared in the OpenAPI spec. Treat the scoring endpoint as soft-limited per API key and respect HTTP 429 responses by backing off. Contact Conturs directly for documented limits on your plan.
How do I score a lead through Jentic?
Run jentic search for 'score a lead', load the returned Conturs POST /leads operation, then execute it with the lead's email, company, and title. Jentic injects the api_key from the vault and returns the score and factors as a structured result.
Can I limit what my agent is allowed to do with the Conturs Scoring API?
Yes. Because you run Jentic One yourself, your own rules decide which Conturs operations and credentials the agent can use. This API has only two operations, scoring a lead via POST /leads and checking service health via GET /health, so you can allow just the ones the agent needs and leave the rest out. Any operation you do not add to the allowed set stays unavailable to the agent, and the api_key is injected only for the calls you permit.
Know of an official OpenAPI document? Contribute it →
For Agents
Submit a lead profile to Conturs and receive a 0-100 ICP fit score with factor-level reasoning. Agents call POST /leads with the API key and lead attributes.
Use for: Score this inbound demo request against our ICP, Get a fit score for a lead with the email jane@acme.com, Check whether the Conturs API is healthy before running a batch, Retrieve the factor breakdown for a low-scoring lead
Not supported: Does not enrich missing contact data, send outbound emails, or manage CRM records - use for ICP-based lead scoring only.
Jentic publishes the only available OpenAPI specification for Conturs Scoring API, keeping it validated and agent-ready. Conturs scores inbound leads against a customer's personalised Ideal Customer Profile model and returns a 0-100 fit score with factor breakdowns. The API exposes two endpoints - a health probe and a POST /leads scoring call - so integration is small and predictable. Authentication is an API key passed in the request body alongside the lead payload.