> ## 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. # Missions > Multi-step agent workflows: blueprints, runs, artifacts, approvals, and budgets. A **mission** is a repeatable, multi-step workflow carried out by your agents — for example "summarize weekly sales and send the summary to my inbox". A mission has a flow of steps (agent steps, human approvals, waits, checks), runs on demand or on a schedule, and keeps a full history of every run, cost, and decision. **Where:** Sidebar › **Missions**. The badge on the entry shows how many approvals are waiting for you. ## The Missions list * **Lifecycle tabs:** All / Active / Paused. * **Stat cards:** Total missions, Active, Needs attention, Avg success rate. * **Filters:** sort (Last active / Success rate / Avg cost / Name), operational state toggles (Running / Waiting / Paused / Failed), and a department dropdown. * **Toolbar:** search, **Group** (Department / Status / No grouping), time range (All time / 7 / 30 / 90 days), view switcher (**List / Compact / Board**), **Columns** (toggle Description, Owner & steps, Trend & metrics), and **Export CSV**. * An **attention banner** highlights missions with a pending approval or a failed last run; an **incident banner** appears when agent runs failed in the last 24 hours. * Each row shows status, title, description, creator, step count, a success-rate sparkline, the latest run status, and live progress ("Step 2 of 5") while a run is in flight. If you are a Company Admin viewing a mission you don't own or belong to, a **"via admin access"** badge marks that. ## Creating a mission Click **New mission** and choose: | Option | What happens | | ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Create with AI** | Describe your goal in plain words (e.g. *"Summarize weekly sales and send the summary to my inbox"*). The planner drafts the mission using **your existing agents**; tasks with no fitting agent become human steps. | | **New Empty Mission** | Enter a Name and Goal and build the flow yourself. | | **Start from Template** | *Not yet available.* | | **Import Blueprint** | *Not yet available.* | ## The mission page The mission page opens with a hero — progress ring, status, goal, creator — and these actions: * **Run** — start a run now (mission must be active and you must have write access). * **Pause / Resume** — pause stops new runs. * **Mission Cockpit** (✨) — a read-only chat about this mission: *"What is the current status?"*, *"Why did the last run fail?"*, *"How many credits did the last runs consume?"*. * **⋯ menu** — **Duplicate Mission** (live) and **View Capability Manifest**; blueprint export/publish are *not yet available*. Tabs: **Overview · Flow · Runs · Approvals · Insights · Build · Settings**. ### Overview * **Mission health** — a 0–100 health score with a headline, plus Current step, Last completed, Next action, Pending approval, and Next scheduled. Buttons: **Retry from failed step** and **Increase budget** (add credits and continue a budget-parked run). * **Live KPIs** — total runs, success rate, avg duration, credits, avg approval wait, retry rate. * **Mission value** — configured business value across runs, with a link to Economics. * **Mission Identity** — the Passport (domain, use case, industry) and Genome (structural fingerprint of the flow) at a glance. ### Flow The flow is shown as a horizontal chain: **Trigger → steps → Complete**, plus an editable step list (**drag to reorder**, pencil to edit, trash to delete, **Add step** at the bottom). Step types: | Type | Purpose | | ------------------ | ------------------------------ | | **Agent** | Run an AI agent | | **Human approval** | Wait for a person to decide | | **Wait (time)** | Pause for a duration (seconds) | | **Wait (poll)** | Poll until a condition is met | | **Verify** | Check a condition | | **Notify** | Send a message | An **Agent step** is configured with: the agent, a **Handoff prompt** (context passed into the step), **On failure** behavior (Retry once then stop / Stop immediately / Continue to next step), an optional **Step key** (to reference this step's output in later steps as `{{steps..output.X}}`), and an **Output contract** — typed fields (string / number / boolean / json, required or not) that the step's output is validated against on every run. Click **Inspect** on a step to open the step inspector: the agent's mandate, tools & apps, data access, knowledge, memory, permissions, budget, typed inputs/outputs, and per-mission performance — with a link to the agent's own page. ### Runs * **Live** — a real-time view of the current run: which step is running or waiting for a human, steps done, a credit budget bar, and controls **Stop after current step** (graceful) and **Cancel now** (immediate; side effects of the running step may already exist). * **History** — every past run. Select one to see: **Summary** (goal, result, duration, cost, tokens, agent/mission version), **Trace** (per-step prompt and answer, attempts, cost), **Prompt** (the exact assembled system prompt per agent step), **Input**, **Tool calls**, **Logs** (decisions recorded during this run), **Evaluation** (execution status + business verdict), and **Cost** (per-step cost table, including credits wasted on failures). * **Logs** — the mission-wide decision log with search and level filters (all / info / warn / error). * **Artifacts** — files and reports produced by runs, grouped by run. ### Approvals The mission's own approval inbox. Each pending approval shows the instruction, a **risk level**, the kind — **Mission approval** ("may the process advance?") or **Tool approval** ("may the agent execute this side effect?") — and a response deadline. Decisions available: **Approve**, **Approve with conditions** (conditions text is required), **Reject**, **Request changes → step** (send the run back to an earlier step with a note), and **Delegate** (hand the decision to another member). Every decision lands in the **Discussion** thread and the **Audit trail** timeline. Who may decide: the step's designated approver, the mission owner, or a lead. ### Insights * **Analytics** — success rate over time, cost over time, and credits by agent, plus quality metrics (avg loop count, tool error rate, human correction rate). Some panels are marked *coming soon*. * **Economics** — business value tracking (gross savings, time saved, total cost, net value, ROI). Savings are **configured estimates** you provide, not automatically derived. *This area is still being rolled out.* **What the badges mean.** Some mission panels carry a small colored badge: **emerald ("ready")** means the panel is freshly wired to your live data; **amber ("soon")** means the panel is a preview showing **sample data**, not your own. Currently on sample data: **Analytics** (the quality-metrics panels), **Cost intelligence**, **Economics**, and the CI / changed-files / artifact details of output contracts. Everything else on the mission page — runs, traces, logs, artifacts, approvals, budgets — is live. ### Build | Section | What it does | | ------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Variables & contracts** | Mission variables (`{{vars.key}}`) — static values or connection references (secrets stay hidden), with "used by" step tracking; plus each step's output contract. | | **Versions** | Version history of the mission's configuration. **Create draft from live config**, then **Publish** or **Discard**; publishing is blocked if the live config changed since the draft was cut (unless forced). Each version shows a step-level diff and can be **restored**. | | **Test** | **Run pre-flight** — a read-only readiness check (agents, approver, webhook, credits) with a % ready score. No side effects, no agent runs. | | **SOP** | An auto-generated Standard Operating Procedure document derived from the current flow (purpose, scope, responsibilities, process, approvals, audit rules). | | **Passport** | Business identity of the mission — Domain, Use Case, Industry, Business Outcome, Risk, Sharing. Editable. | | **Genome** | An automatically generated structural fingerprint of the mission's steps. | | **Capability manifest** | Everything the mission needs to run: required agent roles, systems, connections, data views, permissions, human responsibilities, inputs/outputs, plus cost and duration per run over the last 30 days. | | **Blueprint** | The portable, secret-free package describing the mission. **Preview Package** and **Export JSON** work today; publishing/installing blueprints is *not yet available*. | ### Settings | Section | What it does | | ------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **General** | Name, description; **Danger zone**: **Archive mission** (stops runs, schedule, and webhook — history stays auditable; no hard delete) and **Unarchive (to paused)**. | | **Members** | Add teammates as **member** or **lead**; remove members. | | **Triggers** | **Schedule** (off / hourly / daily / weekdays / custom cron) and a **webhook trigger** with a secret URL (show/copy, **Rotate secret**, enable/disable), plus a duplicate-subject policy (reject duplicates for idempotency, or allow). | | **Permissions** | The role matrix: viewing is for owner/members/admin; run control for owner, lead, admin; step & settings editing for owner, lead, admin; approvals for owner, lead, or the step's approver; member management for owner and admin. | | **Budgets** | **Credit budget per run** — the max credits one run may consume before it parks for approval. Leave empty for no cap. | | **Guardrails** | Require tool-call receipts, a no-work stop token, and the human-approval-gate status derived from the flow. | | **Connections / Notifications** | Visible but *not yet functional* — connection references and notification rules are still being wired up. | ## Who sees a mission Missions are **member-scoped**: only the owner, the people added under Members, and Company Admins can see a mission. Department is a label on a mission, not an access boundary. Everyone can open the Missions page and create their first mission. ## Typical workflows 1. **Automate a weekly report:** Create with AI → review the generated steps in Flow → set a weekly schedule in Settings › Triggers → Run once manually to verify → let it run. 2. **Put a human in the loop:** add a **Human approval** step before any risky step; the responsible person gets it in their Approvals and Inbox. 3. **Control spend:** set a per-run credit budget; a run that hits the cap parks and asks for a budget increase in Overview. 4. **Evolve safely:** cut a draft in Build › Versions, publish when ready, restore an older version if needed.