Cold email and prospect research
Cold email
Cold Email Outreach That Earns Replies
- Cold Email Outreach That Gets Replies
- What a Routing Table Costs When You Get It Wrong
- A Cold Email Sequence That Adjusts to the Reply
- A Fallback Ladder for Routing Failures
- Keeping Model Spend Flat as Reply Volume Grows
- Logging Personalized Drafts to Explain a Drop in Reply Rate
- Reading a p95 Latency without Lying to Yourself
- Retry Budgets for Agent Calls: Backoff, Jitter and a Cost Ceiling
- All of Cold email
Cold email openers
Crafting Cold Email Openers That Earn Replies
- A Prompt Library for Cold Email Variants
- A Review Rubric for Model-Written First Touch Copy
- Openers From a Sparse Prospect Row: Rules for the Model
- Using an LLM to Personalize Cold Email at Scale
- Writing the First Two Sentences of a Cold Email
- A Grounded Prompt Template for Any Data Row, Not Just Email
- A Regression Set of Sparse Rows to Test Your Opener Rules
- Caching and Routing to Keep Personalization Token Spend Flat
- All of Cold email openers
Prospect list building
Prospect List Building for Outreach Campaigns
- A Fallback Ladder That Ends at a Human When Extraction Fails
- A Verification Prompt That Checks Enriched Fields
- Building a Prospect List from Public Sources
- How Many Empty-Input Cases Your Regression Set Needs
- Using an AI Agent to Enrich a Prospect Row with Public Data
- When a Model Should Refuse to Edit a Row Instead of Guessing
- When the Ad Schema Comes Back Empty: A Prompt That Skips a Row
- A Regression Set of Failed Extractions to Test the Ladder
- All of Prospect list building
Prospect and lead scoring
Judging Prospect Fit with a Rubric and Model
- Batch Size and Parallelism: Latency and Cost
- Calibrating a Model Judge Against Human Labels
- Calibrating a Model Scorer Against a Human Judge
- Keeping a Scoring Prompt in Sync Across Two Models
- When to Audit the Human Judge: Checking the Reference Standard
- A Drift Monitor for Model Scorers: Logging Scores and Rechecks
- A Fallback Ladder for Classifier Failures
- A Reference Set That Survives a Taxonomy Change
- All of Prospect and lead scoring
Cold email privacy
Personalized Cold Email Within Privacy Rules
- A Permission Ledger for Agent Tools: Scope, Owner and Expiry
- Keeping Personalized Cold Email Within Privacy Rules
- Keeping Public-Data Prospecting Inside Privacy Rules
- Stripping Instructions from Text Before It Enters Context
- Wrapping Untrusted Appeal Text in Tags the Model Cannot Close
- Writing a Source Map for Every Inferred Field
- Writing a Source Policy for AI Research Agents
Cold email compliance