Build an autonomous AI SDR
Give Jason a goal, knowledge, and guardrails: then supervise instead of operate.
Outcome: A self-optimizing outbound system - the AI SDR finds prospects, writes and sends outreach, handles replies, and books meetings, while your agent supervises through approval gates and performance data.
Availability: runnable today; all 8 steps are callable now.
The highest-altitude recipe: an agent configuring an agent. Instead of composing individual sends, your agent programs Jason (Reply’s AI SDR) and keeps a supervisory loop through approval gates and analytics. The whole loop is callable today, from the knowledge/offer/playbook layer through autopilot and the approval queue; only the feedback signal that tunes future drafts is still coming soon.
Step-by-step guide: docs.reply.io: the canonical per-surface instructions (MCP, CLI, Skills, API) for this workflow.
Steps
- Define the sales goal agent logic
The user states the objective; the agent translates it into an offer, a target market, and success metrics.
- Build the knowledge base
Create a knowledge base and upload product docs, links, reply handlers, and re-engagement cards; the facts Jason sells from. Uses AI SDR API (Jason) .
- Define offers and playbooks
Create the offer (what's being sold, to whom) and the playbook (tone, structure, channels, style). Uses AI SDR API (Jason) .
- Point it at prospects
Use intent signals and Live Data search to define who the autopilot pursues. Uses Prospect Search API .
- Enable autopilot with approval gates
Create an AI SDR sequence, connect the knowledge base and playbook, set approval mode, and enable autopilot. Uses AI SDR API (Jason) .
- Supervise the queue
Review pending approvals: approve, regenerate, or reject drafts. Submitting feedback that tunes future generations is coming soon. Uses AI SDR API (Jason) .
- Watch the conversations
Replies flow into the unified inbox with AI categorization; escalate to a human when intent is high. Uses Conversations & Inbox API .
- Optimize on outcomes
Read performance reports and the meetings ledger; refine the offer, playbook, and targeting based on what converts. Uses Analytics API .