Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the RFP.ai REST 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%2Frfp.ai%2Frfp" | 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%2Frfp.ai%2Frfp" | 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 RFP.ai REST API.
Draft a source-backed answer to one RFP question with a wordLimit and inline or no citations via POST /ask
Answer many questions against the same project in one call via POST /ask-batch, with optional autoSave
Create an RFP project with a name and deadline, and list or read projects in the organization
List the files attached to a project, such as the source questionnaire
GET STARTED
Export a project's responses as a DOCX or PDF document
Fill the source XLSX questionnaire template with the project's answers via POST /export/xlsx-filled
Patterns agents use RFP.ai REST API for, with concrete tasks.
★ Agent-drafted RFP answers with a scoped token
A developer wants their agent to take a questionnaire, draft every answer from the company's knowledge base, and hand back a filled file for a human to review. Through Jentic the agent searches by intent, gets the generateAnswersBatch operation with its input schema, and calls it with the bearer token injected at execution time. It can then export the result, while project creation stays outside the operations the developer allowed.
Call POST /ask-batch with projectId 'proj_123', a questions array of the questionnaire items, citationMode 'inline', and autoSave true, then call POST /export/xlsx-filled with projectId 'proj_123' to produce the filled questionnaire
Single-question drafting inside a sales workflow
Sales engineers often get one-off questions from a prospect in email or chat. POST /ask takes a projectId and a question, drafts an answer grounded in that project's knowledge base, and returns citations and trust signals when evidence is available. Setting wordLimit keeps the draft short enough to paste into a reply, and citationMode 'none' drops inline citations.
Call POST /ask with projectId 'proj_123', question 'Do you encrypt customer data at rest?', wordLimit 120, and citationMode 'inline', then return the draft with its citations
Project setup and export for each bid
Each new bid starts as an RFP.ai project. POST /projects creates one with a required name and an optional deadline, GET /projects/{projectId}/files lists the uploaded questionnaire files, and once answers are done POST /export/docx or POST /export/pdf produces a document to submit. POST /export/xlsx-filled writes answers back into the original spreadsheet when the buyer requires their own template.
Create a project via POST /projects with name 'Acme Corp RFP' and deadline '2026-12-01', list its files via GET /projects/{projectId}/files, and export answers via POST /export/pdf with the new projectId
10 endpoints — the rfp.
METHOD
PATH
DESCRIPTION
/ask
Generate an answer
/ask-batch
Generate answers for multiple questions
/projects
Create a project
/projects
List projects
/projects/{projectId}/files
List project files
/export/xlsx-filled
Fill the source XLSX template with answers
/export/pdf
Export responses as PDF
/ask
Generate an answer
/ask-batch
Generate answers for multiple questions
/projects
Create a project
/projects
List projects
/projects/{projectId}/files
List project files
/export/xlsx-filled
Fill the source XLSX template with answers
/export/pdf
Export responses as PDF
What agents get from Jentic-routed access to this vendor.
Setup
Wiring RFP.ai by hand means creating a bearer token on a paid plan, passing projectId into every answer and export call, and handling HTTP 207 partial results from batch answering. Through Jentic you install once, import RFP.ai from the API Directory, store the token once, and your agent calls it.
Permission scoping
RFP.ai carries the projectId in the request body for answering and exporting, so rules bound which operations your agent may call, not which project. Limit it to the operations it needs, such as drafting answers and exporting the filled XLSX, so project creation is not included unless you add it.
Credential isolation
Your RFP.ai 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 'draft an answer to an RFP question' or 'export the RFP responses as PDF', and Jentic returns the matching RFP.ai operation with its input schema so the agent sends the right projectId and fields.
Alternatives and complements available in the Jentic catalogue.
Specific to using RFP.ai REST API through Jentic.
What authentication does the RFP.ai REST API use?
The RFP.ai REST API authenticates with an HTTP bearer API token per its OpenAPI spec, created in Settings on a paid plan. Tokens carry scopes such as read, projects.write, qa.write, qa.approve, and kb.write, but the spec notes the REST endpoints accept any valid token regardless of scope. Through Jentic the token is held by your own Jentic One instance and attached at call time.
Can I answer a whole questionnaire in one call with the RFP.ai REST API?
Yes. POST /ask-batch takes a projectId and a questions array, both required, plus optional wordLimit, citationMode, and autoSave. It processes the questions against the same project and may return HTTP 207 when some answers succeed and others fail, so check each result.
What are the rate limits for the RFP.ai REST API?
The OpenAPI spec does not specify rate limits. Check the RFP.ai documentation at https://rfp.ai for current limits before sending large batches.
Is there an RFP.ai MCP server?
Yes - RFP.ai offers its own MCP JSON-RPC endpoint driven by the same bearer tokens. You can also connect the RFP.ai REST API directly through Jentic: your agent gets the full 10-endpoint surface from the spec without loading another server's tool definitions into its context, your token is injected at call time by your self-hosted instance instead of living in an MCP config, and your rules decide which operations the agent may call.
How do I draft an RFP answer through Jentic?
Search Jentic for 'draft an answer to an RFP question', load the generateAnswer operation, and execute POST /ask with your projectId and the question text. The response includes the draft plus citations when evidence is available. 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 RFP.ai REST API?
Yes. For a drafting assistant, write a rule that allows POST /ask, POST /ask-batch, and POST /export/xlsx-filled. The agent can draft answers and fill the questionnaire, but it cannot create projects, and every call it makes is logged. This matters here because the REST endpoints do not enforce token scopes themselves.
For Agents
Create RFP.ai projects, draft citation-backed answers to RFP questions singly or in batches, list project files, and export responses as DOCX, PDF, or a filled XLSX.
Use for: Draft an answer to this security questionnaire question with citations, I need to answer all fifty questions in this RFP in one batch, Create a new RFP project for the Acme bid due next Friday, List all RFP projects in my organization
Not supported: Does not upload knowledge base content, sign contracts, or send proposals to buyers. Use for creating RFP projects, drafting answers, and exporting responses only.
The RFP.ai REST API drafts source-backed answers to RFP and security questionnaire questions from a project's knowledge base, one question at a time or in batches, with optional inline citations and a word limit. It creates and lists RFP projects with a name and deadline, lists the files attached to a project, and exports the response work as DOCX, PDF, or a filled copy of the source XLSX template. It is aimed at paid-plan customers whose response teams want to move first drafts and exports out of the web app and into their own tooling.
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>