Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the bicycle.guide guide registry 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%2Faiengineerprofessional.com%2Faiengineerprofessional" | 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%2Faiengineerprofessional.com%2Faiengineerprofessional" | 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 bicycle.guide guide registry API.
Look up a single guide's decorated registry row by its slug
Search the guide registry for a guide
Read cross-book disagreements for a guide with names and provenance
Browse the guide program's taxonomy as structured data
Trace the capability spine that joins books, guides, KSAO elements, and jobs
GET STARTED
Read organizational conditions including identity, label, corroboration, and causal roles
Patterns agents use bicycle.guide guide registry API for, with concrete tasks.
★ Agent Lookups Against the Guide Registry
An AI agent connecting through Jentic can resolve a guide and its context in a few reads: it searches the registry, reads a guide's decorated row by slug, and pulls the taxonomy to place it. Jentic injects the shared secret at call time, so the agent queries the read-only registry without ever holding the credential in its prompt.
Search the registry for a guide, then read that guide's decorated row by its slug and return its taxonomy placement
Taxonomy and Capability Spine
Work with the guide program's vocabulary and its competency mapping as data. The Bicycle.guide API serves the taxonomy as structured values and returns the capability spine that joins books, guides, KSAO elements, and jobs, so an agent can map a job to the guides and competencies that cover it rather than parsing prose documentation.
Read the capability spine and the taxonomy, then map a given job to the guides and KSAO elements that cover it
Guide Search and Disagreements
Find the right guide and understand where sources differ. The Bicycle.guide API searches guides or refuses with the nearest owned match, and reports cross-book disagreements for a guide with names and provenance, so an agent assembling an answer can cite the guide it drew from and flag where books disagree.
Search guides for a topic, then read the chosen guide's cross-book disagreements to flag where sources differ
8 endpoints — the bicycle.
METHOD
PATH
DESCRIPTION
/api/v1/guides
Read the guide registry
/api/v1/guides/{slug}
Read a single guide's decorated row
/api/v1/guides/search
Search guides
/api/v1/guides/{slug}/disagreements
Read cross-book disagreements for a guide
/api/v1/taxonomy
Read the guide program's taxonomy
/api/v1/capabilities
Read the capability spine
/api/v1/conditions
Read organizational conditions
/api/v1/guides
Read the guide registry
/api/v1/guides/{slug}
Read a single guide's decorated row
/api/v1/guides/search
Search guides
/api/v1/guides/{slug}/disagreements
Read cross-book disagreements for a guide
/api/v1/taxonomy
Read the guide program's taxonomy
/api/v1/capabilities
Read the capability spine
/api/v1/conditions
Read organizational conditions
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Bicycle.guide API by hand means sending a shared secret in the x-bicycle-guide-secret header on each read and parsing the registry, taxonomy, and capability spine yourself. Through Jentic you install once, import Bicycle.guide from the API Directory, store the secret once, and your agent calls it.
Permission scoping
Because the whole Bicycle.guide surface is read-only, a rule can allow guide lookups, search, and taxonomy reads without exposing any destructive action. Guide slugs travel in the URL path (/api/v1/guides/{slug}), so a rule can also pin the agent to one guide.
Credential isolation
Your Bicycle.guide shared secret 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 guide registry' or 'read the taxonomy', and Jentic returns the matching Bicycle.guide 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 bicycle.guide guide registry API through Jentic.
What authentication does the Bicycle.guide API use?
The Bicycle.guide API authenticates with a shared secret sent in the `x-bicycle-guide-secret` header per its OpenAPI spec, and every route is protected. Through Jentic the secret is injected at call time rather than living in the agent's prompt or logs.
Can I search the guide registry with the Bicycle.guide API?
Yes. The search operation looks for a guide across the registry or refuses with the nearest owned match, and you can read any guide's decorated row by its slug. The taxonomy and capability spine endpoints let you place a guide within the program's vocabulary and competency mapping.
What are the rate limits for the Bicycle.guide API?
The OpenAPI spec does not specify rate limits. Check the Bicycle.guide documentation at https://bicycle.guide/docs for current limits before running a high volume of registry or search reads.
How do I look up a guide with the Bicycle.guide API through Jentic?
Search Jentic for 'search the guide registry' and it returns the search and guide-read operations with their input schema. Your agent searches the registry, then reads a guide's decorated row by its slug. 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 Bicycle.guide API?
Yes. Because the whole surface is read-only, a rule can allow guide lookups, search, and taxonomy reads without exposing any destructive action, and every action it takes is logged. Guide slugs travel in the URL path, so a rule can also pin the agent to one guide.
Is there a Bicycle.guide MCP server?
You don't need an MCP server to give your agent the Bicycle.guide API. Jentic connects it directly from the API Directory: import it, store your shared secret once, and your agent calls the guide, taxonomy, and capability operations on demand without loading another server's tool definitions into its context.
For Agents
Search and read a registry of published guides, their taxonomy, cross-book disagreements, and the capability spine joining books, guides, KSAO elements, and jobs.
Use for: Search the guide registry for a topic, Look up a guide by its slug, Browse the guide taxonomy, Find cross-book disagreements for a guide
Not supported: Does not author or edit content, enroll learners, or deliver courses. Use for reading and searching the published-guide registry, its taxonomy, and capability mappings only.
The Bicycle.guide API is a read-only registry of published guides, their taxonomy, and the capability spine that joins books, guides, KSAO elements, and jobs. It returns the full guide registry and a single guide's decorated row by slug, searches guides, and reports cross-book disagreements for a guide with names and provenance. The taxonomy, capability spine, and organizational conditions are all served as structured data for cooperating repos and agents. Every route is protected by a shared-secret header.
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>