Creating Agents
Module:
operations:agents| Role: Any member | Licence: Pro+
Any workspace member can create custom agents via Eve using the create_agent tool.
Required Fields
| Field | Type | Description |
|---|---|---|
agent_id | string | Unique identifier (kebab-case, e.g., grid-planning-assistant) |
name | string | Display name |
description | string | What the agent does (shown in agent list) |
prompt | string | System prompt — defines personality, expertise, and constraints |
Optional Fields
| Field | Default | Description |
|---|---|---|
emoji | "robot" | Display emoji |
tool_groups | ["all"] | Which tool groups the agent can access |
temperature | 0.7 | LLM temperature (0.0-1.0) |
model | inherited | "sonnet", "opus", "haiku", or null (inherit from parent) |
pattern | "bespoke" | LANES pattern — sets default objective/kr if not provided |
objective | "" | What the agent aims to achieve |
kr | "" | Key result — how success is measured |
visibility | "workspace" | "workspace" (all members) or "restricted" |
visible_to | [] | User IDs (only when visibility is "restricted") |
triggers | [] | Autonomous execution triggers |
module_id | null | Module to associate with (enables dispatch tool) |
mcp_connections | [] | External MCP server connections — e.g. ["snowflake"] (workspace must have these integrated; call list_agent_tool_groups() to see what's available) |
External Integrations (MCP)
Agents can call external services at dispatch time by declaring mcp_connections. Credentials are resolved from the workspace's connected integrations — the agent never handles secrets directly.
| Integration | Scope | What it provides |
|---|---|---|
"holistics" | Personal only | Query analytics and dashboards via Holistics MCP (API key per-person). Cannot be used in mcp_connections — it is user-only and would silently fail for other workspace members and scheduled triggers. |
"snowflake" | Workspace | Query Snowflake data via Cortex Agents MCP. |
Use list_agent_tool_groups() to see which integrations are actively connected for the current workspace. Each entry includes a can_be_stored_in_mcp_connections flag — entries where this is false (user-scoped integrations like Holistics) cannot be used in mcp_connections and will be rejected at create/update time. Non-MCP integrations (e.g. Slack) cannot be used as mcp_connections either.
Tool Groups
Agents declare which tool groups they can access:
| Group | Tools | Description |
|---|---|---|
simulation | Scenario creation, analysis, comparison | Energy simulation tools |
simulation_core | Core simulation without location/hosting | Subset for constrained contexts |
utility | format_generic_chart, read_chart_data | Data visualization |
policy | All policy agent tools | Regulatory intelligence |
websearch | Web search | External information retrieval |
all | Everything above | Full access (default) |
Triggers
Add autonomous execution with optional delivery channels:
{
"triggers": [
{
"type": "cron",
"schedule": "every monday at 06:00 UTC",
"task_prompt": "Generate weekly regulatory digest",
"delivery": ["slack_dm", "email"]
}
]
}
The schedule string is human-readable and always UTC. Accepted forms:
daily at HH:MM UTC, every <weekday> at HH:MM UTC,
every weekday at HH:MM UTC. Raw crontab notation ("0 6 * * 1")
is no longer accepted — it was the source of a day-of-week ambiguity
that shifted some agents' fire days by one.
| Trigger Type | Required Fields |
|---|---|
cron | schedule (human-readable UTC string), optional task_prompt |
event | event (event name) |
webhook | webhook_path |
manual | (none — triggered via Eve) |
Delivery Channels
When a triggered agent completes, its output can be pushed to the user who created the trigger (scheduled_by). Configure via the delivery list on any trigger:
| Channel | Behavior |
|---|---|
slack_dm | Sends output as a Slack DM via the workspace's connected Slack bot. Requires the workspace to have an active Slack integration and the user to have a linked Slack account. |
email | Sends output to the user's registered email address via Mailgun. |
Specific targets
Use colon syntax to send somewhere other than the trigger creator:
| Target | Behavior |
|---|---|
slack:@handle | DM a user by their Slack display name or username (e.g. slack:@nick). Fails if two humans share the same first name and neither has a unique display name. |
slack:#channel | Post to a channel by name (e.g. slack:#policy). The Eve bot must be invited to private channels. |
slack:user@email.com | DM a user by their registered email (e.g. slack:nick.woolley@ev.energy). Most reliable option — resolves via Slack's users.lookupByEmail endpoint and survives handle collisions. Bot needs the users:read.email scope. |
email:user@example.com | Send an email to any address. |
Targets can be combined with commas: slack:@nick,#policy.
Both top-level channels can be used together. If a channel fails (e.g., no Slack integration), the other channels still deliver. If no delivery is specified, agent output is logged but not pushed — the user would need to ask Eve for results.
Agent Lifecycle
- Create — Agent registered in workspace, dispatch tool auto-generated if
module_idset - Use — Eve dispatches to agent via auto-generated tool (e.g.,
ask_grid_planning_assistant) - Update — Modify prompt, tools, triggers, visibility (workspace agents only)
- Delete — Remove agent, dispatch tool, and team memberships
Permissions
| Operation | Who Can Do It |
|---|---|
| Create | Any workspace member |
| Read/List | Any member (respecting visibility) |
| Update | Creator only (for workspace agents) |
| Delete | Creator only (for workspace agents) |
| Modify builtin | Nobody (immutable) |
| Promote/Demote | Platform admin only |