For Agents
Publish and revise HTML reports with full revision history: fetch and diff revisions, leave and resolve anchored comments, manage password-protected share links, attach assets, run reviewer agents, and schedule regeneration.
Use for: Publish this HTML as a new report, Update a report in place with revised content, Show the line-level diff between two revisions of a report, List the comment threads on a report
Not supported: Does not handle spreadsheets, BI dashboards, or email campaigns. Use for publishing, revising, reviewing, and sharing HTML reports only.
The Comma API publishes HTML reports and edits them in place while keeping a full revision history. It lists and fetches individual revisions, produces a line-level diff between any two, and lets collaborators leave anchored comment threads that can be resolved or reopened. Reports can be published or unpublished with a password-protected share link, have assets attached, and be checked by reviewer agents against the head revision. Routines, skills, and connectors schedule regeneration so a report stays current without manual edits.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Comma 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%2Fcommareports.com%2Fcommareports" | 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%2Fcommareports.com%2Fcommareports" | 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 Comma API.
Publish an HTML report and update it in place
Track a full revision history and diff two revisions line by line
Leave anchored comment threads on a report and resolve or reopen them
Publish, unpublish, and password-protect a report's share link
Attach and remove assets on a report
Run reviewer agents against a report's head revision
Schedule regeneration with routines, skills, and connectors
Patterns agents use Comma API for, with concrete tasks.
★ Agent Report Publishing
An AI agent connected through Jentic publishes a generated report and keeps it current: it creates the report from HTML, updates it in place as inputs change, and relies on Comma's revision history to diff what changed between versions. Because every edit is a revision, the agent can always show a line-level diff rather than overwriting silently.
Create a report from HTML, update it in place with new content, then return the line-level diff between the two revisions
Review and Comment Loop
A team reviews a published report by leaving anchored comment threads, resolving them as they are addressed, and running reviewer agents against the head revision for an automated pass. The Comma API exposes the comment threads, replies, and reviewer runs, so an agent can gather open feedback and trigger a fresh review in one flow.
List a report's open comment threads, run the reviewer agents against the head revision, and report what each surfaced
Scheduled Regeneration
A report that must stay current is wired to a routine that regenerates it on a schedule, drawing on skills and connectors for its data. Comma's routines, skills, and connectors operations let an agent set up the schedule, test a connector's credentials, and run the routine immediately to verify output before leaving it on a cadence.
Create a routine for a report, test its connector, and run the routine once to confirm the regenerated output
53 endpoints — the comma api publishes html reports and edits them in place while keeping a full revision history.
METHOD
PATH
DESCRIPTION
/reports
Create a report
/reports/{id}
Fetch a report
/reports/{id}
Update a report in place
/reports/{id}/revisions
List a report's revisions
/reports/{id}/diff
Diff two revisions line by line
/reports/search
Full-text search reports
/reports/{id}/comments
Leave a comment
/reports/{id}/review
Run reviewer agents against the head revision
/reports
Create a report
/reports/{id}
Fetch a report
/reports/{id}
Update a report in place
/reports/{id}/revisions
List a report's revisions
/reports/{id}/diff
Diff two revisions line by line
/reports/search
Full-text search reports
/reports/{id}/comments
Leave a comment
/reports/{id}/review
Run reviewer agents against the head revision
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 the Comma API by hand means managing a scoped bearer token, handling the revision and diff model, and running the reviewer and routine flows yourself. Through Jentic you install once, import the Comma API from the API Directory, store the token once, and your agent calls it.
Permission scoping
Comma puts the report id in the URL path (/reports/{id}), so a rule can pin your agent to one report: it can read, revise, and comment on that report and nothing else. You choose the operations it may call, so destructive ones like deleting a reviewer or clearing a share password are not included unless you add them.
Credential isolation
Your Comma API 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 'publish an HTML report' or 'diff two revisions', and Jentic returns the matching Comma 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 Comma API through Jentic.
What authentication does the Comma API use?
The Comma API authenticates with a bearer personal API token in the Authorization header, per its OpenAPI spec, and the token carries granular scopes such as reports read and write. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's prompt, logs, or context.
Can I diff two revisions of a report with the Comma API?
Yes. Every edit is stored as a revision, so you can list a report's revisions, fetch any single one, and request a line-level diff between two of them. That lets an agent show exactly what changed between versions rather than overwriting content silently.
What are the rate limits for the Comma API?
The OpenAPI spec meters AI-heavy work through plan caps and routine usage rather than a fixed request-per-second limit, and exposes a usage endpoint for the current month. Check https://commareports.com for the specific limits on your plan.
Is there a Comma MCP server?
You don't need an MCP server to give your agent the Comma API. Jentic connects it directly from the API Directory: import it, store your token once, and your agent calls it. Operations are discovered on demand, so your agent's context stays lean instead of loading a separate server's tool definitions.
Can I limit what my agent is allowed to do with the Comma API?
Yes. Write a rule that allows only the read and comment operations on reports, such as fetching a report, listing its revisions, and leaving comments, so the agent can review and annotate but cannot publish share links, delete reviewers, or change connectors. Every call it makes is logged.
How do I publish a report through Jentic?
Import the Comma API from the Jentic API Directory, store your API token once, and have your agent search Jentic for 'publish an HTML report'. Jentic returns the create-report operation with its input schema so the agent sends the content and reads back the published report. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED