For Agents
Submit, list, and vote on ideas in the innos innovation management platform.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the innos 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%2Finnos.io%2Finnos" | 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%2Finnos.io%2Finnos" | 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 innos API.
List all ideas currently in the innos workspace via GET /ideas
Submit a new idea on behalf of a user via POST /ideas
Cast a vote on an existing idea via POST /ideas/{id}/vote
Pull innos ideas into reporting tools or dashboards for innovation tracking
GET STARTED
Use for: I want to submit a new idea to innos, List all current ideas in the innos workspace, Vote on an existing idea by ID, Find the most-voted ideas in innos this month
Not supported: Does not handle product roadmapping, customer-facing feedback portals, or task execution - use for innos idea submission, listing, and voting only.
Jentic publishes the only available OpenAPI specification for innos API, keeping it validated and agent-ready. innos is an innovation and idea-management platform where employees submit ideas, vote on each other's submissions, and managers triage promising ones into action. The 3-endpoint API exposes the core flow needed for external integrations: list ideas, submit a new idea, and vote on an existing idea. Authentication is an API key in the Authorization header.
Push ideas captured in chat, email, or external intake forms into innos automatically
Patterns agents use innos API for, with concrete tasks.
★ Idea Intake from External Channels
Capture ideas wherever they originate - Slack, email, an internal form - and submit them to innos without requiring the contributor to log into another tool. POST /ideas accepts the idea fields and returns the new idea ID. Lowers the friction of contribution and increases the volume of ideas captured by innovation programmes.
POST /ideas with title 'Switch lobby lighting to motion-sensor LEDs' and description from a Slack message thread.
Innovation Programme Reporting
Read ideas out of innos into a central reporting layer to track submission volume, vote distribution, and triage progress over time. GET /ideas returns the current list. Useful for innovation programme leads who need to demonstrate engagement and outcomes to executive sponsors.
Call GET /ideas, group results by submission month, and summarise total ideas and vote counts.
Voting Automation
Cast votes on behalf of users when promising ideas surface - for example, an executive sponsor automatically endorsing the top idea in a quarterly review, or a Slack reaction translating into an innos vote. POST /ideas/{id}/vote registers the vote against the supplied idea.
POST /ideas/{id}/vote on the idea ID 'idea-456' to register an endorsement from the authenticated user.
AI Agent for Innovation Coordination
An LLM agent acts as an innovation programme assistant - collecting ideas from conversations, deduplicating against existing submissions returned by GET /ideas, and posting new ones via POST /ideas. Through Jentic, the agent searches by intent and executes without holding the raw API key.
Compare a new idea draft against the list returned by GET /ideas; if no near-duplicate exists, POST /ideas to submit it.
3 endpoints — jentic publishes the only available openapi specification for innos api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/ideas
List all ideas
/ideas
Submit a new idea
/ideas/{id}/vote
Vote on an existing idea
/ideas
List all ideas
/ideas
Submit a new idea
/ideas/{id}/vote
Vote on an existing idea
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the innos API by hand means passing your key in the Authorization header on every call and mapping its idea and vote endpoints yourself. Through Jentic you install once, import the innos API from the API Directory, store the key once, and your agent calls it.
Permission scoping
innos puts the idea id in the URL path (/ideas/{id}/vote), so a rule can pin your agent to voting on ideas. You choose the operations it may call, so submitting new ideas is not included unless you add it.
Credential isolation
Your innos 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 'submit an idea' or 'vote on an idea', and Jentic returns the matching innos 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 innos API through Jentic.
Why is there no official OpenAPI spec for innos API?
innos does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call innos 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 innos API use?
The innos API uses an API key passed in the 'Authorization' header on every request. Through Jentic, the key is stored encrypted in your Jentic One instance and injected at runtime so the agent never sees the raw value.
Can I submit an idea to innos through the API?
Yes. POST /ideas accepts the idea fields (title, description) and returns the new idea ID. The same endpoint is used whether the submission originates from a chatbot, an intake form, or an internal automation.
What are the rate limits for the innos API?
Rate limits are not encoded in the spec; they are enforced per API key on the innos side. Contact innos support via innos.io for the current limits applied to your account.
How do I cast a vote on an idea through Jentic?
Search Jentic for 'vote on an innos idea' to find POST /ideas/{id}/vote. Load the schema, supply the idea ID, and execute. The vote is recorded against the authenticated API key's user. Get started with Jentic One, the self-hosted execution layer.
Can I retrieve a single idea by ID?
The current spec exposes GET /ideas (list), POST /ideas (submit), and POST /ideas/{id}/vote (vote). Retrieving a single idea is done by listing and filtering on the client side, or by inspecting the response of POST /ideas at submission time.
Can I limit what my agent is allowed to do with the innos API?
Yes. Because you run Jentic One yourself, your own rules decide which innos operations the agent may call and which credentials it may use. You can allow it to list ideas with GET /ideas and vote via POST /ideas/{id}/vote while withholding POST /ideas, so it cannot submit new ideas unless you grant that operation. Since the idea id sits in the URL path, a rule can pin the agent to voting on ideas and nothing more.