Project
Project bundles agents and steps to carry out work. In the Marketplace edition, you place and run agents registered by an administrator (registered agents) on the steps. In a workflow, each run is a case: it holds its settings and artifacts as versions, and a step where a person decides checks them before the work goes on.
The ideas are the same as in the SaaS edition. This section is written with the Marketplace edition's facts so that you can read it through in the order of how it works, quickstarts, guides, and references. Check the differences from the SaaS edition in the SaaS Edition Mapping Reference.
Run something small
Place a registered agent and take your first case through.
→Use registered agents
What can be placed, the step settings, and what the agent receives.
→Look up the differences from SaaS
How to read each page of the SaaS edition.
→Understand how it works
Get the ideas behind steps, reviews and records first.
→Main differences from the SaaS edition
| SaaS edition | Marketplace edition | |
|---|---|---|
| Agents placed on steps | Users create them in the project (goal (instructions), guardrails, playbook, skills) | Container agents an administrator registered in the admin console. They are not created in the project, and their contents are not changed there |
| What it takes to place one in a workflow | It has a goal (instructions) | An administrator has registered a contract and it is certified |
| What you change per step | (You fix the agent) | The step settings (parameters, connectors, input bindings) / environment variables (cycles) |
| Hand-over between steps | The output of the previous step passes to the next step | It passes only when you bind the files |
| Running a workflow | “Run now” | “Start case”. Settings and artifacts are held as versions |
| Shape of a workflow | It can divide into lanes and run them at the same time | Serial. There are no parallel lanes and no “Run at the same time”. With a Branch step, the lane to go to can be chosen by the previous step's result (there is no “question” to check) |
| Review method | Stop and wait for a decision / Notify and proceed after the deadline | Stop and wait for a decision / External wait (a GitLab MR being merged). The deadline does not decide it |
| Ways to start | Manual, time, external API, email | Manual, time, external API (no email) |
| Creating with AI, consulting on improvements | Available | Not available |
| Project memory | Available | Not available |
| Execution rules | The basic rules and forbidden operations act on the run | The basic rules decide whether it can start (workflows). Outbound traffic is restricted with NetworkPolicy and “Banned URL” in the admin console |
How a project is built
A project has steps, and you place registered agents on those steps. What a registered agent does is settled by its container image (and, in a workflow, by the contract an administrator registered). On a step where a person decides, no agent runs: a reviewer looks at the case's artifacts and settings and decides.
| Term | Meaning |
|---|---|
| Registered agent | An agent an administrator registered under “Marketplace AI Agents” in the admin console. It runs as a container image built with the SDK |
| Contract | The agreement on the parameters, files, artifacts and connections a registered agent receives, its effect on external systems and its execution limit. Only agents used in workflows have one |
| Certification | The contract has, all in place, the SDK version, adapter version, image digest, test results and supported execution rules confirmed by testing. Only certified agents can be placed in a workflow |
| Step settings | The parameters, connectors and input bindings set for each placement in a workflow, within the range of the contract |
| Case | One run of a workflow with registered agents placed. It holds its settings and artifacts as versions |
| External wait | A review method that moves on to the next step according to the state of an external service (a GitLab MR being merged) |
The other terms (step, placement, review step, run record, execution rules, ledger) are the same as in the SaaS edition (How a project is built).
The two types
You choose the type when you create the project. The default in the Marketplace edition is workflow.
| Cycle | Workflow | |
|---|---|---|
| How it starts | You set a period for each registered agent placed, and it runs on that period. It can also be run by webhook | Started manually (Start a case). It can also be started at a set time or from the external API |
| How it proceeds | Registered agents do not wait for one another; each runs on its own period | One execution (a case) goes through the steps in order. The next step starts after the previous one finishes. A Branch step chooses the lane to pass through |
| How it ends | It does not end. It keeps running until you stop it | Each item ends (completed, rejected, failed, or cancelled) |
| What can be placed on steps | Registered agents used in chat (no contract or certification needed). A review step cannot be placed | Certified registered agents. Review steps and Branch steps can be placed |
| Example of suitable work | Check a state at fixed intervals and notify if something is wrong | Receive one document, process it, and finish it through a reviewer's check |
How you use it
Register the agent
Register it under Marketplace AI Agents, and add a contract and certification if it is used in workflows.
Allow traffic
If the agent uses external services, allow the destinations.
Place it on steps
Place registered agents and enter the step settings.
Take cases forward
Start a case, and move it on at review steps after looking at the versions.
Look at the record
Choose what to fix from the run records and metrics.
Where to read at each stage.
- Register the agent — Settings Guide (administrators), Workflow Guide (agent developers)
- Allow traffic — Execution Rules and Traffic Guide
- Place it on steps — Agent Guide; how to divide the work is in the Design Guide
- Take cases forward — Case Guide, Review Guide, Trigger Guide
- Look at the record — Record Guide
Where things are in the UI
The project screen shows a row of tabs. Because “Workflow history” exists only for workflows, a workflow shows five tabs and a cycle shows four (a person who opens it only with an organization operations role does not see the Settings tab). The editing screen opens with the “Edit” button at the top, not a tab (shown to owners only). There is no “Library” tab.
| Tab | What you see |
|---|---|
| Overview | From the top: “Project overview” (a description written by AI from the purpose, steps and Agent settings, or the project description; not shown when there is neither), “Results of this work” for the period you choose (a sentence on the results and the indicators), a diagram of how the registered agents placed in the steps relate (its right-hand column switches between “Basic info”, “Metrics” and “Latest artifacts” for each step; “Latest artifacts” is not shown to people who open the project only through the organization operations role), for a cycle the band of the last 24 hours for each agent, and at the bottom “Project info” (a one-line summary; “Show All” opens all of it). Runs whose completion is not measured (“Run ended (completion not measured)”) appear separately in the legend |
| Execution history | The list of executions. Open one to see its execution record. The record of operations inside the project (Records (audit trail)) is also here |
| Workflow history | The most recent cases, including finished ones. “Case details” opens the case screen |
| Action needed | A list of things that need a person. There are eight kinds: awaiting approval, overdue, waiting on external, failed, awaiting rework, sweep failed, past deadline (run), and stalled (Record Guide) |
| Settings | Basic information, Triggers and notifications, Connectors (MCP, A2A), Members, and Execution rules. A workflow also has “External access (A2A, MCP)” |
In the Marketplace edition, the following differ.
| Where | Difference |
|---|---|
| Top of the project list | There is no “Agents” tab (Home, Projects, Automations, Insights) |
| “Add Agent” in the editor | The list switches to the list of registered agents |
| Top of the project screen | In a workflow with registered agents placed, “Start case” instead of “Run now” |
| Workflow history, run record | “Case details” leads to the case screen (progress, settings, files, records) |
| Settings > Triggers and notifications | There is no starting by email |
| Settings > Connectors | There is an “External-wait webhook secret” (workflows) |
| Settings > External access (A2A, MCP) | In a workflow, once the owner publishes it, external agents (A2A) and MCP clients can start a case with a request, in environments where an administrator has opened the entrance (MCP, A2A) |
Projects can also be used through the external API. It can be called with a service account token (System Integration API Reference) and with the token of a user who signed in from an external tool (User API Reference (Projects)).
Use It from an AI Client
Install the AGENTIC STAR plugin in Claude Code or Codex, and you can work with projects just by asking. For example:
- "Create a workflow that uses the registered agent 'Contract Check' to check incoming contracts and ends after I review them"
- "Find out why recent runs did not go well, and tell me who should fix them"
- "Go through this morning's approval requests for me, checking what each contains"
- "Show me the success rate of each project for the last 30 days"
For how to install the plugin and connect, see AI Client Connection Guide (MCP) — Install the Plugin. The AI can only do what the connected account or service account is allowed to do.
How It Works
This gathers what the screens alone do not make clear. Read it before you start setting up.
- Projects and Steps — A step is where registered agents are placed. The previous step's output is passed only when you connect files
- Cycles and Workflows — A workflow ends as a case; a cycle keeps running placement by placement
- Who Can Decide What — Even an owner cannot decide a review unless named. Only the owner can correct a case's settings
- Human Review — A review step decides whether to move the case on. The deadline does not decide
- How Much to Delegate — Run rules are a check before launch. Operations during a run are not stopped by the platform
- Records and Metrics — An execution record is not a report card. “Completion not measured” is neither success nor failure
Quickstart
Workflow
Place registered agents on steps, start your first case, and take it through review.
→Cycle
Have a registered agent used in chat sweep on a schedule, look at the results, and stop it.
→Guides
- Design Guide — What to decide as a business matter, how to divide it, and what to hand to steps and how far
- Agent Guide — the agents you can place, step settings and environment variables, and what the agent receives
- Case Guide — starting a case, versions of settings and artifacts, and cancelling
- Review Guide — the deadline does not decide, and external waits
- Trigger Guide — how starting differs, cycle sweeps and webhooks, and when it does not go to plan
- Execution Rules and Traffic Guide — where execution rules apply, and how to restrict outbound traffic
- Connection Guide — what to connect to, and where to notify
- Record Guide — action needed, the runtime image, unmeasured results, and why a run could not be launched
References
- SaaS Edition Mapping Reference — how to read each page and section of the SaaS edition
- Settings Reference — the values fixed in the Marketplace edition
- Run Results Reference — what the displayed results mean, and the completion-rate formula
- Records Reference — events added to the records, and what appears in exports
- Glossary — the words that appear only in the Marketplace edition
- Roles Reference — what each role can do