> ## Documentation Index > Fetch the complete documentation index at: https://agents.concierca.ch/llms.txt > Use this file to discover all available pages before exploring further. # Agents > Creating and configuring agents: briefing, skills, tools, data access, triggers, and the hierarchy. Agents are your autonomous AI team. Each agent has an identity (role, department, briefing), a set of granted tools and data, one or more triggers that wake it up, and delivery channels for its results. Everything an agent does is logged and auditable. **Where:** Sidebar › Agents › **Agents**. Related entries in the same section: [Hierarchy](/guide/agent-hierarchy) (the org chart), and the activity views [Runs](/guide/agent-runs), [Agent Decision Log](/guide/agent-decision-log), [Agent Inbox](/guide/agent-inbox), [Analytics](/guide/agent-analytics), and [Cost](/guide/agent-cost). ## The Agents list * **Stat cards:** Total Agents, Active, Departments, Total Runs. * **Toolbar:** search (*"Search name, ID, dept, role..."*), department filter, status filter (Active / Paused / Draft), **Group** by department, and a table/grid view toggle. * **Table columns:** Name, ID, Department, Role, Model, Schedule ("Manual" when none), Status. Columns are sortable and **drag-resizable** (widths are saved per user). * **Row actions** (on hover): ▶ **Run now** (active agents only) and a ⋯ menu with **Edit**, **Duplicate**, and **Delete**. *Careful: Delete removes the agent immediately, without a confirmation dialog.* * **Banners** warn about failed runs in the last 24 hours and a low AI-provider balance. **Who sees which agents:** Company Admins see all agents in the company. Members see agents they own plus agents shared with their active department. ## Creating an agent Three ways: | Method | How | | ------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Create with AI** | A chat dialog: pick who may see the agent (Just me / Department / Organization), then describe the agent in plain English. The AI designs and creates it, then opens it. | | **New Agent** | Creates a draft and opens the full editor directly. | | **Setup form** (`/agents/new`) | A single scrolling form with a live preview: Agent Type (Autonomous / Workflow), Department, Visibility, Identity (name, display name, role, reports-to, system prompt), Configuration (model, reasoning effort, budget, billing policy), Invocations (manual, Telegram, schedule, webhook confirmation), Theme, and Memory Push to Telegram. | ## The agent page The agent page has the editor on the left and a **Run Agent** panel on the right. **Header controls:** * **Execution type** — **Autonomous** (the model decides on its own, using the briefing and tools; best for open-ended tasks) or **Workflow** (deterministic steps that run in order; best for structured pipelines). * **Quick model switch**, **Configure with AI** (describe a change in plain English; you review a before/after diff and click **Apply**), and **Save Changes**. Tabs: **Overview · Briefing · Skills & Tools** (labeled **Workflow Steps** in Workflow mode) **· Triggers · Output · Runs & Cost · Telegram · History**. ### Overview Stat cards (Total Runs, Success Rate, Avg Response, Cost/30d) plus: * **Agent Avatar & Icon** — pick a face, icon, and color theme. * **Agent Details:** | Field | Notes | | -------------------------------- | ------------------------------------------------------------------------------------------ | | Display Name | The agent's shown name | | ID Name (slug) | Read-only technical name | | Role | CEO (Master AI) / Supervisor / Worker | | Main Department / Sub-Department | Where the agent belongs | | Reports To Agent | Its supervisor in the hierarchy (a CEO has no parent) | | Owner *(admin only)* | Who the agent runs as and who receives its replies | | Mandate | A short authority statement — what the agent owns, what it may do alone, when it escalates | | Status | Active / Paused / Draft | | Visibility | **Just me** or **Department** (everyone in the department can see and use it) | * **Decision Bounds** — the agent's personal guardrails: *"Ask me before the agent… spends more than \$X"* and *"…does something irreversible (delete, mass-send, pay out)"*. Both default to on. Otherwise the agent decides on its own. *(Enforcement on autonomous tool calls is still rolling out.)* ### Briefing The agent's **System Prompt** — loaded on **every** run; it defines who the agent is, what it has, and how it behaves. Use the **Auto-Generate / Improve** button to draft or refine it with AI (review, then **Append** or **Replace**). For one-off tasks use the Per-Run Input in the run panel instead. In Workflow mode the system prompt is not used and the field is disabled. ### Skills & Tools Everything the agent is allowed to use. Grants save automatically, and **ungranted tools are blocked server-side** — even if the model tries. Sections: | Section | What you grant | | ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Connected Tools** | Per-action grants for each connected app (Gmail, Slack, …) — enable exactly the actions this agent may perform. Manage the connections themselves under Connections. | | **Skills** | Attach reusable skills from your skill library (searchable picker, grouped by category). | | **Memory & Knowledge** | **Pinned Knowledge** and **Pinned Memory** — specific entries the agent always reads at run time; optional write toggles (*Save Knowledge* / *Save Memory*) let it create entries. An **Advanced** panel sets the default access scope — *Just me / My department / Everything (admin only)* — plus category and topic filters, with a live "Matches N entries" preview. | | **Data Sources** | Read access to your catalog tables — see "The data ceiling" below. | | **Orchestration & Advanced** | Spawn sub-agents, raw HTTP calls, and any extra capabilities via a searchable picker. | | **Model** | Model override (or inherit the company default), temperature, max output tokens, max budget per run, sub-agent model, and conversation history length. | | **MCP Servers** | Grant all tools of an MCP server your company added under Connections. | | **API Credentials** | Which vault credentials the agent may use — values stay masked and are never shown to the model; they are decrypted only at tool-execution time. | #### The data ceiling For each granted table you can open a per-source preferences editor *(editable by admins; members see it read-only)*: * **Columns this agent may read** — unpicked columns cannot be requested by the agent at all, even if it asks. * **Default filters** — always applied; the agent cannot opt out. * **Row limit cap** — max rows per query (up to 50). Combined with the access scope (*Just me / My department / Everything*), this is a hard ceiling: an agent can never read more than its owner could. Write access per table (insert/update) is a separate, **admin-only** toggle — audited and limited to registered columns. ### Workflow Steps (Workflow mode) Instead of thinking autonomously, a Workflow agent runs a deterministic pipeline, top to bottom. You can **drag to reorder**, edit, or delete steps, and each step declares its input/output variables. 15 step types are available: **Tool, Extract, Filter, Pick, Map, Split, Format, LLM, Approval, Loop, Skill, User Choice, User Form, Inbox, Knowledge**. * The **Extract** step bridges raw tool output to the next step in plain English — no JSON wrangling needed; an inline *"Insert Extract step"* button appears where one would help. * The **Approval** step pauses the workflow and sends a Telegram approval request; it continues only if approved. * **Generate with AI** builds or modifies the whole workflow from a description; **Test Run** executes real tool *reads* (no delivery) and shows per-step input/output with timings. * **Version History** tracks each saved workflow version with one-click **Restore**. ### Triggers Enable one or more triggers — the agent wakes on every active one: | Trigger | What it does | | ------------------------ | --------------------------------------------------------------------------------------------------------------------------------------- | | **Alive Mode** | The agent stays in a stateful loop and processes events as they arrive (shows heartbeat, session cost, and a Stop button). | | **Schedule** | Off / Hourly / Daily / Weekdays / Custom cron, with a time picker, weekday buttons, and a preview of the next 3 execution times. | | **Telegram** | Configured on the Telegram tab (see below). | | **Slack** | Channel + mode (Passive / Mention / Always). *Requires Slack app setup — not fully available yet.* | | **Email Inbound** | A dedicated inbound email alias for the agent. | | **Inbound Webhook** | Trigger via HTTP POST — copyable URL with an embedded secret, **Rotate** to revoke, an example curl, and a **Send Test** button. | | **Handoff (on success)** | When this agent finishes successfully, the selected agents start immediately with its output (chains up to depth 3; loops are blocked). | Agents in the same reporting chain can also hand work to each other's inbox mid-run — no separate trigger needed. ### Output Where results go **after** a run: * **Target Document** — the agent maintains a *living knowledge document* instead of a new one per run: a single document, or one per user / department / channel / custom key. Attach an existing document or create one on the spot. * **Delivery Channels** — **Inbox (team routing)**: results route automatically up the hierarchy (worker → supervisor → CEO → you). Telegram delivery is configured on the Telegram tab. * **Webhook Delivery** — POST the run result to external URLs (HMAC-signed), per-event: run success, run failed, budget exceeded. * **API Actions** — pre-configured external API calls (method, URL, vault credential fixed) that become callable tools for the agent; each has a **Test** button. * **During-Run Inbox** — allow the agent to hand work to another agent's inbox mid-run. ### Telegram Everything Telegram in one place: connect a bot (bot token lives in Settings › Vault), enter or **Detect** your Chat ID, and use the **Send Test** button to verify the wiring. **Trigger modes** — how incoming chat messages start the agent: | Mode | Behavior | | ----------- | ------------------------------------------------------------------------- | | **Passive** | Chat messages never trigger the agent — use this for delivery-only setups | | **Mention** | The agent runs only when it is mentioned in the chat | | **Always** | Every message in the chat triggers a run | **Voice messages** — with *accept voice* enabled, voice notes are **transcribed automatically** and the transcript becomes the run input; an optional confirmation step asks before the run actually starts. **Talking back** — enable **result delivery to Telegram** to have run results posted to the same chat, and toggle the during-run tools: *Send Telegram Message* (a non-blocking update mid-run), *Ask User (blocking)* — the agent posts a question with **inline choice buttons** and the run pauses until you tap one (or the prompt times out) — and *Request Approval* (non-blocking yes/no). Actions that require your sign-off arrive the same way: a message with inline **approve / reject buttons**, decided with one tap. **One voice.** Only the top-level agent of a run talks to you on Telegram. When it delegates work to sub-agents, they report their results back up the chain, and you receive one coherent answer instead of several bots messaging you at once. Keep blocking prompts in mind for scheduled runs: a run waiting on *Ask User* stays paused until someone taps or the prompt times out. ### Runs & Cost * **Savings** — record how many human minutes and what hourly rate one run saves, to track ROI per run. * **Credit consumption** — the agent's billing policy and an optional max-credits-per-run override. * **Run budget** — a hard USD ceiling per run; the runner stops the agent at the cap. * **Recent Runs** — status, trigger, duration, cost, savings, tokens. Click a run to open the **Run Audit Trail**: trigger input, agent output, base system prompt, injected skills, registered tools, context sources, inbox tasks, user replies, conversation history, unverified claims, and the full assembled prompt — plus **Replay** to run it again. **View All Runs** jumps to the Runs view filtered to this agent; **Reset History** clears the stats. ### History Every briefing, prompt, or configuration change is captured as a version. Expand a row to see what changed, and **Restore** any previous version. ### The Run panel On the right of every agent page: the agent's status, an optional **Per-Run Input** (an ad-hoc prompt for this run only — it does not change the system prompt), the **Run Now** button (or **Run Workflow (N steps)**), recent runs, and quick stats. The agent must be **Active** to run. ## Hierarchy See [Hierarchy](/guide/agent-hierarchy) for the org chart and how delegation works (reports-to chains, handoffs, and delegated runs). ## Permissions summary | Action | Member | Company Admin | | -------------------------------------------------------- | ------------------------- | ------------- | | See agents | Own + active department's | All | | Create/edit/run agents they can see | ✔ | ✔ | | Assign an agent's **Owner** | — | ✔ | | Set memory/data scope to **Everything (whole company)** | — | ✔ | | Grant **write** access to data tables | — | ✔ | | Edit the data ceiling (pinned columns, filters, row cap) | read-only | ✔ | ## Notes & not-yet-available * **Slack trigger** requires additional Slack app setup and is not fully available yet. * **Decision Bounds** enforcement on autonomous tool calls is still rolling out. * **Duplicate** currently opens a blank create form rather than a pre-filled copy. * There is no archive for agents — use **Status: Paused**; Delete is permanent and immediate.