Your first 24 hours with Mercury

Pick your deployment, choose Mercury Credits or BYOK, connect your first channel, and get to your first real workflow fast. No fluff. Just the shortest path from checkout to a useful operator.

Cloud usually goes live in 10–15 minutes
10–15 min
Typical Cloud Go-Live
3 Steps
From Checkout to First Win
30 days
Included Post-Launch Support

What happens after you buy

1. We provision or prep your environment

Cloud spins up automatically. On-Site and Ship-In move into scheduling and hardware handoff.

2. You choose how Mercury thinks

Use Mercury Credits for the fastest start, or connect your own provider keys if you want direct model control.

3. You connect channels and run the first workflow

Telegram, Discord, WhatsApp, Signal, Slack, or iMessage — then give Mercury a job that matters today.

Choose your deployment path

Cloud: fastest path to live

Best for founders, operators, and teams who want a private always-on agent without touching infra.

  • Complete checkout
  • Watch for your deployment confirmation
  • Open your setup email
  • Connect your first messaging channel
  • Pick Mercury Credits or add your API keys
  • Run your first workflow

Typical time to first live session: 10–15 minutes after payment.

On-Site: for local-control environments

Best for offices or teams with stricter hardware, network, or data-handling requirements.

  • Complete your intake
  • Confirm hardware and network access
  • Schedule the install window
  • Confirm approved messaging channels
  • Review go-live checklist with your team

Best when local environment control matters more than instant deployment speed.

Ship-In: your hardware, preconfigured

Best when you want Mercury running on your own box without doing the install yourself.

  • Confirm supported hardware
  • Ship the device
  • Approve install scope
  • Receive configured hardware back
  • Plug in, connect network, and test channel access

Best when you want ownership of the machine but not the setup headache.

Your first 24 hours checklist

If you do only these seven things, Mercury will stop feeling like AI infrastructure and start feeling useful.

  1. Name the agent and define its job. Example: “Mercury handles inbound lead triage, follow-up drafts, and research requests.”
  2. Connect one primary messaging channel. Start with the channel you already live in most.
  3. Decide Credits vs BYOK. Credits = fastest. BYOK = maximum control.
  4. Add one repeating workflow. Good first wins: lead follow-up, daily summary, inbox triage, research brief, or ops reminders.
  5. Set one permission boundary. Decide what Mercury should never do without you.
  6. Run 3 real prompts from your actual business. Don’t test with toy prompts. Use today’s real work.
  7. Save one result you’d want again tomorrow. That becomes the seed of a real operator workflow.

Mercury Credits or BYOK?

Both work. The right answer is speed vs control.

Mercury Credits

Best for people who want one bill, no provider-account juggling, and the fastest setup path.

  • Fastest activation
  • No separate model billing dashboards
  • Simplest for non-technical buyers

Tradeoff: less direct provider-level control.

Bring Your Own Keys

Best for customers who already use Anthropic, OpenAI, Google, or other providers and want direct billing control.

  • Direct provider ownership
  • Flexible model switching
  • Easy to align with existing AI spend

Tradeoff: a few more setup steps up front.

What you actually need

Telegram or another supported channel is the only real must-have. API keys are only required if you choose BYOK.

  • Required: one messaging channel
  • Optional: AI provider key if using BYOK
  • Optional: Nylas, Brave Search, or ElevenLabs for extra workflows

Most customers should start simple, then add integrations after the first real win.

Fast path setup notes

If you choose BYOK, Mercury never locks you to one provider. Claude is strong for polished writing and strategy, GPT is flexible, Gemini is cost-effective for lightweight checks, and Kimi often gives excellent value.

Getting your API key fast

  1. Go to your chosen provider website (Anthropic, OpenAI, Google AI Studio, or Moonshot).
  2. Create an account and add billing details if required.
  3. Open the API or Developer section and generate a new key.
  4. Copy the key and store it in a password manager — never post it publicly.

Need help instead of guessing?

Support is included for the first 30 days. Use support@mercuryinstall.com for setup help, /support for support-hour options, or /contact if your deployment needs a human handoff.

🚀 Your First 30 Minutes

These five steps turn your agent from "installed" into genuinely useful. Copy the prompts directly into Telegram to accelerate setup.

Step 1: Say Hello (2 minutes)

Start with a clean intro so the assistant understands context and tone right away.

Hey! I'm [name]. Introduce yourself and tell me what you can do for me day-to-day.

Step 2: Set Up Preferences (5 minutes)

Personalization creates better answers, better drafts, and better reminders.

Let's set up my preferences. Ask me one question at a time about my role, goals, communication style, timezone, and the 3 things I want automated first. Save each answer to memory.

Step 3: Run Your First Task (5 minutes)

Prove value immediately with a real task you can verify in seconds.

Check the weather for [city] and give me a simple 3-day forecast with high/low temps and rain chance.

Step 4: Set Up Morning Briefing (3 minutes)

This is the highest-impact workflow for most users.

Set up a daily morning briefing at [time]. Include weather, today's calendar events, top important emails, and key reminders. Keep it under 200 words.

Step 5: Learn Memory Commands (2 minutes)

Use /compact before changing topics, "Remember that…" for permanent context, and natural-language reminders like "remind me Friday at 4 PM to send invoices."

🧠 Model Routing Made Simple

Think in roles: your Brain handles complex conversations and writing; your Muscles handle repetitive checks cheaply and fast.

RoleBest FitTypical CostUse Cases
BrainClaude Opus or Kimi K2.5$6–$50/moPlanning, strategy, polished writing, complex analysis
MusclesClaude Haiku or Gemini Flash$0–$3/moHeartbeat checks, reminders, routine summaries, lightweight monitoring

🧠 Brain

Best fitClaude Opus or Kimi K2.5
Cost$6–$50/mo
Use casesPlanning, strategy, writing, analysis

💪 Muscles

Best fitClaude Haiku or Gemini Flash
Cost$0–$3/mo
Use casesHeartbeats, reminders, summaries, monitoring

Pro tip: Start with one solid model setup, then add routing once you see your usage patterns.

⚙️ Workflow Templates (Week 1)

☀️ Morning Brief

Receive one clean daily snapshot so you can act fast without opening five apps.

Send me a morning brief every day at 7:00 AM with weather, calendar, urgent emails, and my top 3 priorities.

📧 Email Scanner

Filter noise and only surface messages that need your attention.

Check my inbox every 2 hours, ignore promotions, flag urgent emails from key contacts, and draft replies for approval.

📅 Task Manager

Track commitments and deadlines using simple natural language commands.

When I say 'add task', save it by priority and due date. Send me a 6 PM daily summary of open tasks and tomorrow's deadlines.

🔎 Web Research

Get concise research summaries with links instead of reading dozens of pages.

Twice a week, monitor [industry/topic] and send me a 5-bullet summary with links and one actionable insight.

✍️ Content Creation

Turn rough notes into polished drafts for emails, social posts, and client updates.

Use my preferred tone (professional and concise). When I paste notes, produce a ready-to-send draft first, then a shorter version.

🔒 Security Best Practices

1) Keep Keys Private

Treat API keys like passwords. Store in a secure password manager and never share in chats or screenshots.

2) Set Spend Limits

Configure hard budget caps at your model providers to prevent surprise bills as automation grows.

3) Rotate Credentials

Rotate core keys every 6-12 months and immediately after any suspected exposure.

4) Review Access Monthly

Audit which integrations are connected and remove anything unused to reduce risk surface.

5) Backup What Matters

Ask your agent for a weekly "memory digest" of important preferences, workflows, and commitments so you always have a portable backup.

Ready to Get Started?

Launch your AI agent today and build your first high-leverage workflow in under 30 minutes.

Buy Now