For Agents
Commission a pre-meeting research dossier on a named person, resolve which profile is meant, poll until it completes, and read the briefing as Markdown or a Google Doc or Word link.
Use for: Prepare a briefing on the person I am meeting tomorrow, Check whether my dossier on Jane Smith is ready, Get the Markdown briefing for a completed dossier, List all dossiers I have created this month
Not supported: Does not schedule meetings, send emails, or return bulk contact lists. Use for generating research dossiers on individual people only.
The RunDossier API generates executive pre-meeting dossiers on a named person, researched in the background and returned as a finished briefing. A client creates a dossier with a subject_name and optional context, which deducts one credit and returns a pending job to poll. When the subject is ambiguous the dossier waits in an awaiting_selection state with candidate profiles until the client picks one or cancels for a refund. Completed dossiers carry the briefing as Markdown plus Google Doc and Word download links.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the RunDossier 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%2Frundossier.com%2Frundossier" | 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%2Frundossier.com%2Frundossier" | 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 RunDossier API.
Commission a pre-meeting dossier on a person from a subject_name and optional context
Poll a dossier through pending, processing, awaiting_selection, complete, and error states
Resolve an ambiguous subject by choosing a candidate profile url, or cancel with null to refund the credit
Read the finished briefing as result_markdown, or open it through google_doc_url or a short-lived word_doc_url
List past dossiers newest first with cursor pagination
Check the monthly and top-up credit balance before commissioning new dossiers
Patterns agents use RunDossier API for, with concrete tasks.
★ AI assistant preparing for a meeting
An AI calendar assistant preparing a user for tomorrow's meetings commissions a briefing on each external attendee. Through Jentic the agent searches for 'create a pre-meeting dossier', loads the createDossier operation with its input schema, and calls it with the bearer key injected at execution time. It polls the dossier until the status is complete, then reads result_markdown and adds a short summary to the calendar event.
Call POST /dossiers with subject_name Jane Smith and context VP Sales at Acme, poll GET /dossiers/{id} until status is complete, then return the result_markdown summary
Disambiguating a common name
Research on a common name can match several people, and a briefing on the wrong one is worse than none. When RunDossier cannot tell which person is meant, the dossier enters awaiting_selection and lists candidate_profiles. The caller posts the chosen candidate's url as selected_url to continue, or sends null to cancel and get the credit refunded.
When GET /dossiers/{id} returns status awaiting_selection, pick the candidate whose company matches the meeting context and send its url to POST /dossiers/{id}/select as selected_url
Sales team briefing library
A sales team keeps briefings on prospects in a shared workspace. GET /dossiers lists the caller's dossiers newest first with a next_before cursor, and each completed dossier exposes a google_doc_url for sharing. GET /credits reports monthly and top-up balances so a batch job can stop before credits run out.
Call GET /credits, and if total is above zero, page through GET /dossiers with the before cursor and collect the google_doc_url of each complete dossier
5 endpoints — the rundossier api generates executive pre-meeting dossiers on a named person, researched in the background and returned as a finished briefing.
METHOD
PATH
DESCRIPTION
/dossiers
Create a dossier
/dossiers/{id}
Retrieve a dossier and its status
/dossiers/{id}/select
Resolve a disambiguation
/dossiers
List dossiers
/credits
Get credit balance
/dossiers
Create a dossier
/dossiers/{id}
Retrieve a dossier and its status
/dossiers/{id}/select
Resolve a disambiguation
/dossiers
List dossiers
/credits
Get credit balance
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.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
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>What agents get from Jentic-routed access to this vendor.
Setup
Wiring RunDossier by hand means attaching the dsk_live_ bearer key, polling an asynchronous job, handling the awaiting_selection branch, and catching 402 when credits run out. Through Jentic you install once, import RunDossier from the API Directory, store the key once, and your agent calls it.
Permission scoping
RunDossier puts the dossier id in the URL path (/dossiers/{id}), and creation, selection, listing, and credits each have their own route, so a rule can bound your agent to reading dossiers or to the full research loop. You choose the operations it may call, so credit-spending creation is not included unless you add it.
Credential isolation
Your RunDossier 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 'create a pre-meeting dossier' or 'check my dossier credits', and Jentic returns the matching RunDossier operation with its input schema so the agent sends subject_name and context correctly.
Alternatives and complements available in the Jentic catalogue.
Specific to using RunDossier API through Jentic.
What authentication does the RunDossier API use?
Per its OpenAPI spec, the RunDossier API uses HTTP bearer authentication with a personal API key in the dsk_live_ format, created in Settings under API Keys and sent in the Authorization header on all five operations. Through Jentic the key is held by your own Jentic One instance and attached at call time.
How long does a dossier take, and how do I know it is done?
POST /dossiers returns immediately with status pending, and generation runs in the background. Poll GET /dossiers/{id} until status is complete or error; the response includes a status_message for progress and a duration_ms value once finished. Fetch word_doc_url promptly, as the spec says that signed link is valid for 5 minutes.
What are the rate limits for the RunDossier API?
The OpenAPI spec does not specify numeric rate limits, though every operation can return HTTP 429 when you exceed them. Check https://rundossier.com/docs/api for current limits. Separately, each new dossier deducts one credit and the API returns 402 when none remain.
Is there a RunDossier MCP server?
You do not need an MCP server to give your agent RunDossier. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls the create, poll, select, and credits operations on demand without extra tool definitions in its context.
How do I create a dossier through Jentic?
Search Jentic for 'create a pre-meeting dossier', load the POST /dossiers operation, and execute it with subject_name and an optional context string such as the person's company. Keep the returned id and poll GET /dossiers/{id} for the briefing. 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 RunDossier API?
Yes. For an agent that should only read existing briefings, write a rule that allows GET /dossiers and GET /dossiers/{id}, so it can list and read dossiers but cannot spend credits by creating new ones. Add POST /dossiers when it should commission research, and every call it makes is logged.
GET STARTED