Reference: Outbound SDR Research + Drafting Agent
referencesales-sdr-outbound
framework
Agent Framework
memory
Memory
retrieval
Retrieval / Vector Store
browser
Browser Automation
observability
Observability / Tracing
prompt_management
Prompt Management
deployment
Deployment Target
mcp_servers
MCP Servers
Architectural notes
Reference architecture for an outbound SDR agent: researches a prospect, drafts a personalized email, logs activity to CRM. Why these picks: - Gemini for the research subagent because of long context (consume many pages of prospect content at once). - Stagehand for browser-based prospect research where the public web isn't available via API. - Zep's temporal knowledge graph for tracking how prospect signals evolve over time. - Fly.io because the agent runs long sessions that don't fit serverless timeouts cleanly. Common gotchas: - LinkedIn anti-bot defeats most naive scraping; budget for failures. - Personalization quality drops fast if research input is shallow.
Embed this stack
Show off your stack on your engineering blog or company page.
<iframe src="http://testserver/embed/stacks/sales-sdr-outbound" width="100%" height="380" frameborder="0" style="border: 1px solid #334155; border-radius: 8px;"></iframe>