For Agents
Run and manage Manifestly recurring-process checklists — workflows, runs, steps, hooks, and users — through an API-key REST API.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Manifestly Checklists 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://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | 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 Manifestly Checklists API.
Start a new run of a published checklist with assignees and a due date
List active and archived checklists in the workspace
Mark a step on a running checklist as complete
GET STARTED
Use for: Start a new client onboarding checklist run, List all archived checklists in the workspace, Mark step 3 on the current run as complete, Add a new step to the customer-onboarding checklist template
Not supported: Does not handle ad-hoc project tasks, document storage, or chat — use for recurring-process checklists, runs, steps, and hooks only.
Manifestly is a recurring-process checklist platform used by ops, customer success, and IT teams to run repeatable workflows reliably. The API exposes the platform's core objects — checklists (workflow templates), runs (instances of a checklist), steps, step data, hooks, users, and memberships — under /api/v1. Authentication is an API key in the Authorization header. The endpoints support template management (create/update checklists and their steps), run lifecycle (start a run, list, complete steps), and webhook-style hooks at workflow and step level for outbound notifications.
Create or update a checklist template with its ordered steps
Register workflow- and step-level hooks for outbound notifications
Manage workspace users and memberships on individual checklists
Patterns agents use Manifestly Checklists API for, with concrete tasks.
★ Trigger an onboarding run from a CRM event
Customer success teams trigger a fresh onboarding checklist whenever a new customer reaches a milestone in the CRM. POST /runs starts a run from a published checklist template with the customer name, owner, and due date, and webhook hooks notify the team channel as steps complete. The recurring process now lives in one place rather than ad-hoc CRM tasks.
On a CRM 'customer signed' webhook, start a Manifestly run of the 'New Customer Onboarding' checklist, assign the CSM, and set a 14-day due date.
Operational compliance reporting
Operations leaders need evidence that recurring processes — closing the books, monthly access reviews — actually ran and were completed on time. GET /runs filtered by checklist and date returns the run history with step completion timestamps, which a reporting job can roll up into a compliance report. The data model is the same one auditors care about.
Pull all runs of the 'Monthly Access Review' checklist for the last quarter and return a table of run id, owner, started_at, completed_at, and overdue flag.
Step-level integration with downstream tools
Teams want certain steps in a checklist to fire actions in other tools — create a Jira issue, post in Slack, send an email. Step hooks registered via /steps/{id}/hooks call out to a webhook receiver when the step is reached or completed, which then bridges to the downstream system. The checklist remains the source of truth for the process.
On the 'Provision laptop' step of the IT onboarding checklist, register a hook that posts to the IT Slack channel when the step is completed.
Agent-driven process kickoff
An AI agent inside an ops tool can spin up the right checklist based on a free-text trigger ('new vendor onboarding for Acme'). Through Jentic, the agent searches by intent, picks the right checklist template, and calls POST /runs to start the run. The Manifestly API key never appears in the agent's prompt — Jentic's vault holds it.
Given the instruction 'kick off vendor onboarding for Acme Corp', find the matching Manifestly checklist and start a run named 'Acme Corp - Vendor Onboarding'.
40 endpoints — manifestly is a recurring-process checklist platform used by ops, customer success, and it teams to run repeatable workflows reliably.
METHOD
PATH
DESCRIPTION
/checklists
List checklist templates
/checklists
Create a checklist template
/checklists/archived
List archived checklist templates
/checklists/{checklist_id}/steps
Add a step to a checklist template
/checklists/{checklist_id}/steps/{step_id}
Update a step in a checklist template
/checklists/{checklist_id}/steps/{step_id}/data_setting
Get a step's data settings
/checklists
List checklist templates
/checklists
Create a checklist template
/checklists/archived
List archived checklist templates
/checklists/{checklist_id}/steps
Add a step to a checklist template
/checklists/{checklist_id}/steps/{step_id}
Update a step in a checklist template
Three things that make agents converge on Jentic-routed access.
Credential isolation
Manifestly API keys are stored encrypted in the Jentic vault and injected into the Authorization header at call time. Agents only receive a scoped session — the raw key never enters their prompt context.
Intent-based discovery
Agents search Jentic by intent (e.g. 'start a manifestly checklist run') and Jentic returns the matching POST /runs operation with its input schema, so the agent can start the run without browsing the Manifestly docs.
Time to first call
Direct Manifestly integration: 1-2 days for auth, hook handling, and run lifecycle plumbing. Through Jentic: under an hour — search, load schema, execute.
Alternatives and complements available in the Jentic catalogue.
Specific to using Manifestly Checklists API through Jentic.
What authentication does the Manifestly Checklists API use?
Manifestly uses an API key passed in the Authorization header (apiKeyHeader). Keys are generated by workspace admins from the Manifestly settings UI. Through Jentic the API key is stored encrypted in the vault and injected at call time, so the raw key never sits in the agent's transcript.
Can I start a checklist run through the Manifestly Checklists API?
Yes. POST /runs starts a new run from a published checklist template. The payload references the checklist_id and accepts a run name, owner, and assignees so the run is set up correctly from the moment it starts. List active runs with GET /runs.
What are the rate limits for the Manifestly Checklists API?
Manifestly's published documentation does not pin a single per-second number; the API throttles per-workspace and returns 429 with a Retry-After header when exceeded. Pace bulk imports of templates or runs and respect the Retry-After value rather than retrying immediately.
How do I add a step to a checklist template through Jentic?
Run pip install jentic, then search Jentic for 'add a step to a manifestly checklist'. Jentic returns the POST /checklists/{checklist_id}/steps operation with its step schema, which you execute with the title, description, and position to add the new step to the template.
Does the Manifestly Checklists API support webhooks?
Yes, at two levels. Workflow hooks fire on workflow-level events (run started, run completed); step hooks fire on step-level events (step started, step completed). Register both through the hooks endpoints under /checklists/{id}/hooks and /steps/{id}/hooks.
Can I capture data inside a checklist run?
Yes. Each step can have data settings configured via the step data setting endpoints, which expose typed fields the assignee fills in during the run. The captured values are returned with the run and can be pulled out by reporting and downstream automations.
/checklists/{checklist_id}/steps/{step_id}/data_setting
Get a step's data settings