1 Open the AI Assist tab

Step 1 · Open the editor

Either edit an existing system, or click Create New System

The AI Assist tab is part of the System Definition Editor — it's available on every system, including brand-new ones. From the Systems list at /systems:

  • To create from scratch with AI: click + Create New System. The editor opens at /system-editor/new. Skip to the AI Assist tab without filling anything else.
  • To edit an existing system: click any system in the list. The editor opens with that system loaded.

Across the top of the editor you'll see a horizontal row of tabs. AI Assist is the new one, marked with a lightning-bolt icon.

System Editor — tab strip
System Details
Connection
OAuth
Automation
Designer
YAML Editor
MCP Tools
Fulfillment
API Docs
⚡ AI Assist NEW
Why it lives in the editor

Every system has its own AI Assist tab and its own chat history. Switching to another system gives you that system's chats — they don't bleed across.

2 Pick the agent

Step 2 · Agent picker

System Definition Assistant is auto-selected

At the top of the AI Assist panel you'll see two pickers — an Agent and a Chat history picker. The platform auto-selects the right agent for systems work; you almost never need to change it.

AI Assist — header
System Definition Assistant
Currently editing: helpdesk-api · gpt-4o · 12 tools
Agent: System Definition Assistant ▾ — Start new chat — ▾
PickerWhat it controls
AgentWhich AI agent answers. The platform picks System Definition Assistant automatically; admins can publish other systems-aware agents and they appear here.
Chat historyPrevious conversations with this system. — Start new chat — starts a fresh session. Older sessions are listed by their first prompt as a title.
Refresh / DeleteRefresh reloads the agent list. Delete next to the chat picker removes the currently selected chat from history.

3 Describe what you want

Step 3 · Composer

Type a description, hit Send

The bottom of the panel has a single-line composer labelled "Describe the system you want…". The agent works for both create (no system loaded yet) and edit (an existing system is open) modes — it figures out which from context.

Good prompts include:

  • The connector type if you know it: REST, SCIM, LDAP, ServiceNow, Azure, ODBC, "internal".
  • The object types you want — users, groups, tickets, contacts.
  • The auth model — OAuth client credentials, basic, API key, bearer.
  • Any specific scopes / permissions the API needs.
Empty state — example prompts
👋 Describe the system you want and I'll draft the YAML.
"Create an Entra ID user provisioning system with user and group object_types using OAuth2 client credentials and Group.ReadWrite.All scope."
"Build a ServiceNow incident management system with create / update / list / close commands."
"Generate an internal stub for our HR onboarding service with employees and contracts."
"Add a search_users command to this system that takes a query string and returns the first 50 matches."
💡
Be specific about scope

The more concrete the prompt, the less back-and-forth. Naming the connector type and the operations you need usually produces a usable draft on the first try.

4 Watch the live stream

Step 4 · Streaming

Tool cards, rationale, and a streaming reply

The agent doesn't just write YAML — it calls a set of system-authoring tools as it works. You'll see each tool invocation surface in the chat as a small card: when the tool is called, what arguments it received, and whether it succeeded.

Live stream from the agent
create an Entra ID user provisioning system with user and group object_types and OAuth2 client credentials
I'll draft an Azure AD / Entra ID system with two object types (user, group) and OAuth2 client credentials authentication.
tool · systems.list_connector_types — completed (38 ms)
tool · systems.get_reference — { system_name: "azure_ad" } (62 ms)
tool · systems.validate — completed (12 ms)
model: gpt-4o · tier: L1 · 4 chunks · 2.1s

Common tool calls you'll see:

ToolWhat the agent is doing
systems.list_connector_typesLooking up which connector types are available in your tenant.
systems.get_referenceFetching a reference example for a known system (e.g. azure_ad, salesforce) to use as a template.
systems.suggest_schemaGenerating a draft schema for an object type based on the connector.
systems.validateRunning the draft through the schema validator before returning. Catches missing required fields, malformed paths, etc.
systems.compare(Edit mode) showing what's changed between current and proposed YAML.
⏸️
Cancel anytime

If the stream is going somewhere unhelpful, click Cancel to abort. You can also Retry the last prompt — useful if the model got distracted by an irrelevant tool call.

5 Review the system card

Step 5 · System card

The structured preview at the bottom of the reply

When the agent finishes, the assistant message ends with a system card — a structured summary of the YAML it generated. The card is your read of what's about to land in the editor.

System card preview

📦 entraid_user_provisioning

connector: scim · auth: oauth2_client_credentials · 12 commands
user group ✓ validated
▸ Preview YAML (412 lines)
Auto-applied to editor

What to check on the card:

  • Name matches what you asked for and follows your tenant's slug conventions.
  • Connector type is the one you wanted (REST vs SCIM vs Internal).
  • Object types chips list every object the agent included. Missing one? Just ask in chat.
  • Validated chip — green ✓ validated means the agent ran systems.validate before returning. If it's missing or red, the YAML may have schema issues.
  • Preview YAML — click to expand the full text inline before you commit to loading it.

6 Load into editor & save

Step 6a · Auto-apply

The first valid system auto-loads to the YAML editor

By default, the moment the agent emits a complete, parseable YAML block, the editor switches to the YAML Editor tab and the new content is dropped in. The form is marked dirty — nothing is persisted yet.

⚠️
Auto-apply does NOT save

It only places the YAML into the editor. The system isn't actually changed in the platform until you press Save System. Closing the tab discards the AI's draft.

Step 6b · Manual reapply

Use Load into editor to re-apply

If you've manually edited the YAML and want to start over from the AI's draft, click 📥 Load into editor on the system card. It reloads the original generated YAML in one click. You can do this any number of times — the chat keeps the draft.

Step 6c · Save

Switch to YAML Editor → review → Save System

The cleanest review workflow:

  1. Stay on YAML Editor after auto-apply.
  2. Read top to bottom. Pay particular attention to connection.base_url, any ${secret://…} placeholders, and command paths.
  3. Replace placeholders with real env-var or Vault references.
  4. Optionally jump to the Connection tab and click Test Connection first.
  5. Press Ctrl+S or click Save System.
🔒
Replace AI-generated secrets

The agent uses ${secret://...} placeholders for credentials, but always double-check there's no plaintext secret hiding in the YAML before you save.

7 Edit an existing system

Step 7 · Edit mode

Ask for changes — the agent receives the current YAML

Open any saved system, switch to AI Assist, and just describe the change you want. Behind the scenes the assistant gets your current YAML embedded in the prompt, so it knows exactly what it's editing.

Examples:

  • "Add a search_tickets command that takes a query string and returns the 50 newest results."
  • "Switch the auth from API key to OAuth2 client credentials with the tickets.read scope."
  • "Add a new object type contract with create / update / list commands."
  • "Change the rate limit to 50 requests per second per user."

The reply includes the complete updated YAML — not a patch. The editor swaps it in wholesale; your existing fields that weren't touched are preserved.

🧪
Iterate freely

If the result isn't quite right, just keep chatting — "make the parameter optional", "use POST instead of GET". Each turn returns a fresh, complete draft.

8 Resume a previous chat

Step 8 · Sessions

Chats are remembered per system

Every chat is saved automatically in your browser, scoped to the system you were editing. Closing the tab, navigating to another system, or refreshing the page won't lose work — the next time you open AI Assist on this same system, the chat picker shows your previous sessions, titled by their first prompt.

  • The chat picker hides itself when there are no prior chats — only one click to start your first conversation.
  • Up to 20 sessions per system are kept; oldest are pruned automatically.
  • Click Delete next to the picker to remove the currently loaded session.
  • Start fresh anytime via — Start new chat — in the picker.
💾
Browser-local only

Sessions are stored in localStorage on the browser you're using. They don't sync across devices and aren't visible to other users — even on the same system. If two admins iterate on the same connector they each have their own chat.

9 Tips, safety, and limits

Step 9 · Best practice

Get the most out of the assistant

TipWhy
Always review the YAML before SaveAuto-apply is convenient, not a commitment. Read at minimum the connection block and any commands that mutate data.
Keep prompts focused"Add one command" beats "make this system better". Smaller asks → smaller, easier-to-review diffs.
Test the connection after big changesThe agent can't actually call your API. Run Test Connection on the Connection tab before relying on the new YAML.
Use Insert Example as a fallbackIf the assistant misunderstands, switch to the YAML Editor's Insert Example dropdown for a known-good template you can edit by hand.
Cancel runaway streamsIf the agent fixates on a tool that isn't producing useful data, hit Cancel and rephrase the prompt.
🛡️
Never paste real secrets into the chat

The conversation goes to the AI service. Use ${secret://path} placeholders or environment variables in your prompt — the agent understands them and will keep them as placeholders.

Limits worth knowing

  • Auto-apply happens once. If you want to re-load the AI's draft after manual edits, use the Load into editor button on the system card.
  • The assistant doesn't auto-save. Every persistence step is an explicit click on Save System.
  • It can't run your API. The agent generates definitions; testing is on you (Connection → Test Connection, or the Test System modal).
  • It works inside the editor only. There's no "Generate from prompt" entry point on the systems list yet — open or create a system first.
🎉
You're set

From now on, "create a connector" can be a one-sentence prompt followed by a YAML review. The grunt work of remembering the schema, command shapes, and auth blocks is the assistant's problem.