What is the AI Reply Agent?
The AI Reply Agent is the first AI Agent we launched. It is an automated assistant that manages your inbox by reading incoming emails, replying to leads, handling objections, sending follow-ups, sharing calendar links, and updating CRM status, all without constant oversight. Watch the walkthrough video HERE.
When sending thousands of emails daily, you’re likely getting hundreds of replies:
Some leads want more information
Some are ready to book a call
Others raise concerns or objections
Speed to Lead is Critical. Manually managing all responses is slow and time-consuming. The faster you respond to a prospect, the higher your conversion rate. Delayed responses = lost opportunities.
The AI Reply Agent ensures replies go out instantly (under 5 minutes), 24/7, keeping leads warm, answering questions, and booking calls while intent is still high—without requiring your team to be constantly available.
Cost: 5 Instantly Credits per reply once generated, regardless of whether you send, edit, or use the suggested reply.
How to Set Up the AI Reply Agent
Step 1: Create Your Agent
Navigate to AI Agents from the left sidebar
Click "Add New"
Name your agent
Select AI Reply Agent
Step 2: Choose Your Mode
Select how hands-on you want the agent to be:
Human-In-The-Loop (HITL) Mode
You approve replies before they're sent
Review and edit drafts
Full control over every response
Best for: New users or teams still fine-tuning workflows
Autopilot Mode
Agent replies to everything instantly
No approval needed
Fully automated responses
Best for: Experienced teams with refined workflows and high volume
Recommendation: Start with HITL to fine-tune tone and responses, then switch to Autopilot once comfortable.
Step 3: Configure Agent Settings
Basic Settings
Decide what the AI reply agent should handle:
Handle follow-ups: Automatically send follow-up emails to leads if they do not reply
Respond to automatic and out-of-office replies: Automatically send an email to the lead on the day they return to office after being out-of-office
Handle objections or negative responses
Advanced Options
1. Label-Based Filtering (Include/Exclude)
Under Advanced Options, you can now optionally control which interest labels the AI reply agent responds to.
Use "Only trigger for" to limit the agent to specific labels. We recommend leaving this option off so your AI agent can respond to all relevant replies and provide maximum value. Restricting to specific labels may cause the agent to miss important conversations.
Use "Don't trigger for" to exclude labels. The AI reply agent will respond to all replies except those from leads tagged with the selected labels.
2. Monthly Credit Budget
Set a maximum number of Instantly credits an AI reply agent can use per calendar month. When the budget is exceeded, the AI reply agent stops generating automatic replies and follow-ups.
3. Business Days Only
When enabled, the AI reply agent will only send follow-up emails Monday through Friday. Replies to incoming emails are not affected — this only controls outbound follow-ups.
No-Show Recovery
When enabled, the AI reply agent will automatically follow up with leads that are assigned the "No Show" label, helping you recover missed meetings.
If your Calendly account is connected, it will automatically propose alternate times and schedule meetings based on the back-and-forth communication. You can control the following settings for No-Show Recovery:
How many follow-ups to send: The first follow-up is sent immediately when a lead is marked as "No Show". If they don't book a meeting or reply, additional follow-ups are sent after 24 hours, then 48 hours, and so on.
Fallback Sending Accounts(Optional): Fallback email accounts for no-show follow-ups - only needed when a lead has no existing Instantly conversation. By default, the email account associated with the lead's conversation thread will be used.
You can check AI reply agent analytics to see the revenue impact and the number of 'no-show' leads recovered.
Step 4: Assign Campaigns and Inboxes
Choose which campaign the AI reply agent should monitor: Simply assign specific tags to monitor certain campaigns and accounts
Step 5: Train Your Agent
Provide context to help the agent understand your tone, product, and goals. This is the most crucial step. The more context you provide, the more accurate and useful the replies will be.
Optimize Your Guidance: Click "Optimize" to get AI-powered suggestions for improving your guidance by checking for common issues and recommending enhancements.
Example Guidance:
Your goal is to qualify and convert interested replies into booked calls.
When someone shows interest or asks for more info:
- Acknowledge their interest clearly and politely.
- Ask a simple qualifying question if needed (e.g., "Are you targeting outbound for your own business or running it for clients?")
- Suggest a call to go deeper and explain what they'll get from it.
Booking Prompt Example:
“Sounds like this could be a good fit. Let’s do a quick call to see how we can help. Here’s the link to book a time: [Calendly Link]”
If they ask specific questions (e.g., pricing, deliverability, how it works):
- Answer clearly and briefly.
- Still suggest a call for full context.
Always keep replies:
- Direct and friendly
- Focused on value and next step (call)
- Avoid fluff, no salesy phrases
Example Style:
“Yes, we include lead sourcing and full campaign setup. Most clients see results within 3–4 weeks. Let’s hop on a quick call so I can walk you through the setup: [Calendly Link]”
Don’t:
❌ Use exaggerated claims (“insane results,” “game-changing”)
❌ Write like a robot (“Thank you for your message. I am happy to assist you.”)
❌ Be vague (“It depends,” “We’ll see what works”)
❌ Sound promotional (“This is the best solution out there!”)
Step 6: Connect Integrations (Optional)
Get real-time alerts when leads need attention
Receive notifications for escalations
Let the agent send booking links automatically
Agent can autonomously book meetings when prospects confirm availability
If someone replies "I'm free at 3 pm," the agent schedules the meeting directly (not just sends the link)
AI Agent Details/Analytics
You can track all AI Agent replies and interactions in the Activity Feed, which gives you a real-time view of every conversation. It shows when an email was sent, when a reply needs review, or when the AI requested more info.
Each item is time-stamped and color-coded by action, making it easy to spot what’s been handled and what still needs attention. From here, you can also take action, like reviewing drafts, marking conversations as done, or digging into specific lead replies.
Each reply generated by the AI reply agent costs 5 Instantly credits, regardless of whether you send, edit, or use the suggested reply. You can check the total number of replies that have been generated in the AI reply agent analytics.
Key Performance Metrics
1. Involvement Rate
The Involvement Rate shows how often your AI reply agent participates in email conversations. It measures the percentage of email threads where the AI agent was actively involved in helping craft responses.
The AI is considered "involved" whenever it generates a draft reply, regardless of whether you send it as-is, modify it, or even decide not to send it at all.
As long as the AI generated a suggestion for you to review, it counts as involvement.
This includes both cases where you send the AI's draft unchanged and cases where you edit the draft before sending.
The only time the AI is NOT considered involved is when you completely skip its suggestion and write an entirely manual response from scratch.
Why it matters: A high involvement rate indicates that your AI agent is successfully identifying and responding to conversations that need attention, saving you time by providing draft responses.
2. Resolution Rate
The Resolution Rate measures how often the AI reply agent handles email responses completely hands-free, meaning you can send the AI's draft without any edits or intervention.
This metric only counts emails that were actually sent (not pending drafts).
A "hands-free resolution" occurs when you send the AI's draft exactly as generated, without making any changes.
If you edit the draft in any way before sending, it doesn't count toward the resolution rate.
If you skip the AI's suggestion entirely and write your own response, this also doesn't count as a hands-free resolution.
Why it matters: A high resolution rate means the AI is accurately understanding and responding to emails in a way that matches your communication style and needs, requiring less manual intervention from you. This directly translates to more time saved.
Both metrics work together to show you how effectively your AI agent is helping manage your inbox - the Involvement Rate shows how often it's helping, while the Resolution Rate shows how accurately it's helping.
Frequently Asked Questions
What does the Calendly integration do exactly?
What does the Calendly integration do exactly?
The Calendly integration has two capabilities:
Send booking links – The agent includes your Calendly link in replies when leads express interest
Autonomously book meetings – When prospects confirm availability (e.g., "I'm free at 3 pm"), the agent schedules the meeting directly in Calendly (not just sends the link)
When the 'No-Show Recovery' feature is enabled, the AI reply agent will automatically follow up with leads that are assigned the "No Show" label, helping you recover missed meetings.
How does routing work when handover or escalation is triggered?
How does routing work when handover or escalation is triggered?
When the AI Agent decides a conversation needs human attention, it notifies you in three ways:
Slack notification – Real-time alert
Activity section – Lead appears with the message for review, response, or marking as done
Unibox – Conversation visible alongside all other replies for full context and follow-up
This ensures no escalated lead gets missed.
Will the Autopilot AI Agent always send replies automatically without needing my approval?
Will the Autopilot AI Agent always send replies automatically without needing my approval?
Yes, Autopilot is designed to send replies automatically, but only when the agent is confident in its response. However, it pauses and requests review when:
Missing product information
Unclear context
Uncertain about the appropriate response
To see why a reply wasn't sent automatically:
Open the agent
Go to the Activity Feed section
Find the specific lead
Click to review the message details—it will show the reason
This ensures quality while maintaining automation.
How can I check the credits consumed by the AI reply agent?
How can I check the credits consumed by the AI reply agent?
You can check AI reply agent credit usage in two ways:
1. Check total replies generated
Open your AI reply agent
Look at the Total replies generated metric in the AI agent details section
2. View detailed credit usage history
Go to Billing page
Navigate to the Instantly Credits section
Click Usage to see credit history
Click All history to filter by usage type
Look for entries labeled "Credit used -> AI Reply Agent" which show exactly how many credits were consumed
Each AI reply costs 5 credits once generated, regardless of whether you send, edit, or use the suggested reply.
If you have sub-workspaces on a Hyper Credits plan, remember that credits can also be used by those workspaces.