The agent listing
When you open Agent Foundry you land on a grid of every agent your departments can see, grouped into sections by what each one is currently doing.| Control / Button | What it does |
|---|---|
| Search agents | Filters the grid by agent name |
| Departments filter | Narrows the grid to selected departments |
| Statuses filter | Narrows by state: Running, Evolving, Paused, Idle, Error |
| New Agent button | Opens the agent creation wizard (or press “n”) |
| Running section | Agents actively working or evolving |
| Paused section | Agents you have stopped |
| Idle section | Agents set up but not currently doing anything |
| Errored section | Agents that hit a problem on their last run |
| Agent card | Click to open Overview; shows status, description, quick stats |
| Card ”…” menu — Open | Goes to the agent’s Overview |
| Card ”…” menu — Pause / Resume | Stops or restarts automatic activity |
| Card ”…” menu — Restart | Restarts the agent |
| Card ”…” menu — Edit | Opens the agent for editing |
| Card ”…” menu — Delete | Moves to Trash; confirms first |
The agent creation wizard
Eight steps. Nothing is created until you press Create agent on the final step.Step 1 — Identity
| Control / Field | What it does |
|---|---|
| Name (required) | The agent’s display name |
| Description | A short summary |
| Departments (required) | The teams that can see and use this agent |
| Owner | Who controls sharing, deletion, transfer; defaults to you |
Step 2 — Model & modes
| Control / Field | What it does |
|---|---|
| ReAct toggle | Chat with tools (on by default) |
| Quick toggle | Sub-2-second answers with no tools |
| Deep toggle | Multi-agent teamwork for research |
| Graph toggle | Branching, parallel, human-in-the-loop |
| Persistent toggle | Long-running background agent |
| Model selector (per enabled mode) | Picks the AI model; only org-approved models appear |
| Initial system prompt | Optional standing instructions |
Step 3 — Tools
| Control / Field | What it does |
|---|---|
| Tool tree | Tick the individual tools the agent may use |
| Selected count | Shows how many tools you picked |
Step 4 — Data sources
| Control / Field | What it does |
|---|---|
| Data source checkbox | Grants the agent access |
| Access level | Read only, or Read & write |
| Daily query limit | Caps queries per day (0 = unlimited) |
Step 5 — Triggers
| Control / Field | What it does |
|---|---|
| Add trigger menu | Adds a new trigger |
| Schedule (cron) | Recurring timetable in a timezone |
| Data change (CDC) | Runs when chosen sources/tables change |
| Webhook | Outside system triggers the agent; IP restrictions allowed |
| Manual | A person fires the agent on demand |
| Enabled switch | Turns a trigger on or off |
| Remove | Deletes a trigger |
Step 6 — Security
| Control / Field | What it does |
|---|---|
| Role name | Label for the access role |
| Permission level | Read-only SELECT, Read & write, or Admin |
| PII access | Masked, Hashed, or Clear |
| PII mask fields | Specific field names to mask |
| Row limit per query | Caps rows per query |
| Rate limit | Caps queries per hour |
| Cost guardrail | Daily spend ceiling |
| Approval threshold | Actions costing more require an approver |
| Flag-confidence threshold | Outputs below this confidence are flagged |
| Data retention | How long generated artefacts are kept |
| Query validation | Pre-checks every generated query |
Step 7 — Notifications
| Control / Field | What it does |
|---|---|
| Add binding | New notification connection |
| Channel | In-app, Email, Slack, or PagerDuty |
| Destination | Target for that channel |
| Credential reference | Required for Slack/PagerDuty |
| Events | Which events trigger a message |
| Enabled switch | Turns binding on or off |
| Remove | Deletes the binding |
Step 8 — Review
Read-only summary. Press Create agent to save everything in one atomic commit.Who can use it
- Organization members can create agents.
- The departments you select determine who can see and use the finished agent.
- Approved tools and models are decided upstream by your Org Admin in Settings → AI Capabilities.