FlowManner
Chat
Sign InGet Started
Flowmanner
Menu
  • Chat
  • Agents
  • Pricing
  • Docs
  • About
Products
  • Workflows
  • Templates
  • Changelog
  • Missions
Resources
  • Blog
  • API Reference
More
  • Careers
  • Contact
  • Security
  • Start
    • Quickstart
    • Your First Mission
    • Your First Eval
  • How-to
    • Connect Your Own Keys (BYOK)
    • Switch Models Per Task
    • Publish a Template
    • Run Evaluations
    • Chat with Artifacts & Previews
    • Automate via the API
    • Webhooks & Triggers
  • Concepts
    • Glossary
    • Execution Model
    • Models & Routing
    • Sandboxes & Previews
    • Memory & Privacy
    • Trust Model
  • Reference
    • Reference · API
      • Authentication
      • Missions & Runs
      • Chat & Sandboxes
      • Blueprints, Graphs & Templates
      • Evaluations & Feedback
      • Marketplace & Community
      • Files & Exports
      • Integrations & Webhooks
      • Agents & Orchestration
      • Auth, Workspaces & Billing
      • Memory & Knowledge
      • Notifications
      • Platform Services
    • Errors
    • Models
    • Limits

Your First Mission

Create, execute, track, and cost-out a solo mission end to end.

What you'll build

One mission with a template-assigned agent, executed and inspected — the complete loop you'll repeat for real work.

Steps

  1. Pick the work. Missions are units like "summarize this document" or "draft outreach from this CRM row". Choose one small enough to judge by eye.
  2. Choose or assign an agent. Agents carry a system prompt, tools, and model parameters (Glossary). A template comes with one pre-assigned; you can override the assigned model per mission (Switch Models).
  3. Fill inputs and execute. Required inputs are validated before launch; execution consumes rate-limit budget (20 executes/min, Limits).
  4. Track it. The mission page shows state transitions live. Retries (default budget: 3) appear as self-correction attempts, not hidden magic.
  5. Inspect costs. LLM calls accrue cost attributed to the mission — open the cost view to see planning vs execution spend.

Where people stumble

  • Bare model names against strict upstreams → use qualified ids (Models).
  • Pausing for over a week auto-fails the mission (Limits).

Next: prove quality with evaluations before scaling up.

Last updated 2026-08-25 (git-derived)

  • What you'll build
  • Steps
  • Where people stumble