Research and personalization compete for the same hours you need for conversations. An account brief is useful when it gives you a defensible reason to contact someone. A polished paragraph about their company is much less useful. Start by deciding what the research must help you do.
This page brings the outbound work together: account research, prospect lists, cold email, sequence review, and call preparation. The prompts name the assistants they support. Full playbooks show the complete tool stack, and skills name their intended runtime. Choose a task first, then follow the instructions for the tools your team uses.
From one account to one reviewed email
Research the account
Use a company URL, your ICP, and a target role to build a short brief. Check the cited facts and mark any assumptions.
Open the account-brief prompt →Draft the first touch
Use one verified observation and your real value proposition. Review the connection between the account detail and the problem you solve.
Open the cold-email prompt →Check the sequence
Check follow-up logic, merge fields, and campaign settings before importing or sending. The QA workflow names its required tools.
Review the campaign QA workflow →
Carry the evidence from research into outreach
Before drafting, assemble the company URL, the role you want to reach, your ICP, and the problem your offer solves. Ask for a short account brief with sources and separate confirmed facts from guesses. A hiring page can support a claim that a team is growing. It cannot prove that the team has your particular problem.
Carry the useful evidence into the first email. Name the observation, explain why it might matter, and make one clear ask. Keep the brief beside the draft when you review it. If a line has no source and no basis in your own knowledge, remove it or turn it into a question.
Before loading a sequence, review the whole conversation: the opening, the follow-ups, and what happens if someone replies. Repeating the same claim in three different phrasings adds volume without adding a reason to answer. The campaign QA playbook helps check the files and campaign structure before a send.
Prove the message on one account
Start with an account you know well enough to judge. Compare the generated brief with what you already know, open the sources, and look for details attached to the wrong company. Similar names and outdated job titles are easy ways to produce confident nonsense.
Read the proposed email aloud. Keep your actual offer, a specific reason for contacting this person, and a reply they can give without doing homework. Ask a teammate to identify the evidence behind each personalized line. Fix the brief if the message needs a fact that is missing.
Only expand the workflow after the result is worth sending. Record which inputs and instructions produced it, keep a review step, and watch replies for signs that the research or targeting is off. A larger list makes a weak assumption more expensive.
Use cases for SDR / BDR
Complete workflows with their implementation tools listed below. Follow each playbook's setup and review steps.
Account Research: Turn Any Company URL Into a First-Call Brief
Run the account research for a first call from a single company URL: a structured, cited, talking-point-ready brief before every first call, in minutes instead of an hour.
Tools: Claude web search, Claude, HubSpot / SheetsThe Ideal Customer Profile (ICP) Template, AI-Scored in Clay
Turn an ideal customer profile template into a live scoring rubric: pull a target account list, enrich it with the signals an AI can read, then score every account against your ICP with a reason and a risk you can audit.
Tools: Clay, Apollo.io, Claude, HubSpotHow to Identify Website Visitors and Trigger Same-Day Outreach
Identify the anonymous website visitors on your site, filter to ICP fits, and trigger a personalized touch the same day, while the intent is still warm.
Tools: RB2B, Clay, Slack, SmartleadCold Email Personalization at Scale, From Real Research
Cold email personalization at volume: research each prospect automatically and generate one genuinely personalized email per person, then send at scale without sounding like a mail merge.
Tools: Clay, Apollo.io, Claude, SmartleadVideo Prospecting at Scale Without Capping at 20 a Day
Scale video prospecting past the 20-a-day ceiling: record one base video and have AI personalize the opening and on-screen details per prospect, so each recipient gets a video that feels made for them.
Tools: Sendspark, HeyGen, Clay, SmartleadSales Follow-Up Email Templates, Auto-Drafted From Every Call
The sales follow-up email is the highest-return touch in the cycle and the one reps most reliably botch, written three hours late from fading memory. Steal the templates below, then let a Claude agent draft each one from the actual call transcript in the rep's voice and write clean CRM notes to HubSpot over MCP. A human still reads every send. Same-day follow-ups, and RevOps finally gets comparable deal data across the team.
Tools: Gong / Fathom, Claude Code, HubSpot (via MCP)AI Sales Coaching from Every Call: A Weekly Claude Agent That Scores Reps Against Your Rubric
Most sales coaching happens on the two calls a manager had time to listen to, and the rep picked both. This play puts a Claude agent on every call instead: each week it reads the transcripts over MCP, scores each call against a rubric you own, with the quote that earned each score, and writes every rep a one-page note with a pattern across their calls and one thing to practice. The manager gets a team view that shows where the whole team is weak. Coaching stops being a lottery of which calls got heard.
Tools: Gong or Fireflies (via MCP), HubSpot or Salesforce (via MCP), The rubric file, Claude Code, Slack (via MCP)Account Planning Template + a Claude Agent That Builds Every Rep's Territory Plan
Territory planning is a ritual most teams run once a quarter and abandon by week two: a template goes out, the reps fill in the top of it, the plans go in a folder, and the quarter is worked from the inbox. This play makes the plan build itself and stay alive. At the start of the quarter a Claude agent reads each rep's territory from the CRM, enriches the missing fit fields, tiers every account by fit, signal, and history against a rubric you wrote, drafts a one-page plan for each tier-A account with why now, who to reach, the play, and the risk, cited to sources, and writes the manager a territory summary. The rep edits and commits. A monthly refresh re-tiers on new signals and checks the plan against what actually happened.
Tools: HubSpot or Salesforce (via MCP), Clay, Apollo, or ZoomInfo, Claude web research, Claude Code, The CRM + SlackHow I’d take a cold email draft through QA to a Smartlead import
A finished email draft still needs evidence review, suppression checks and a reliable handoff. I built a small offline workflow for that last mile, with a fictional batch you can reproduce before using your own prospects.
Tools: Python, SmartleadSkills for SDR / BDR
Reusable procedures for the tool or runtime named on each card. Check the setup before adding one to your workflow.
Account Brief and Account Plan Template for First Calls
Turns a single company URL into a tight, source-grounded first-call account brief a rep can read in two minutes before dialing, and gives you an account plan template to expand it into a plan for your named accounts.
B2B Cold Email Templates in Your Brand Voice
Writes short, relevance-first B2B cold emails in your voice and gives you the cold email templates to start from. Opens with a real observation, not a generic compliment, and refuses to invent personalization.
Sales Call Summary Template, Filled From the Transcript by a Claude Skill
Turns a call transcript or raw notes into a sales call summary template filled with only what the buyer actually said, plus a CRM-ready field block (stage, next step, close date, framework fields, each tagged Confirmed or Inferred) and a to-do list ranked by deadline.
Lead Routing Rules That Explain Themselves: A Claude Skill That Assigns the Owner
Turns a written lead routing rules table into a router that shows its work: for every lead it names the owner, the segment, the SLA, the rule that fired, the out-of-office backup, and the fields it could not see, and it flags catch-all leads so the table gets better every week.
Cold email campaign QA: the skill I’d run before importing leads
I want to know exactly why a prospect and a message are ready before either reaches a sender. This skill produces a review queue, ties decisions to the final copy, and exports approved records to a Smartlead import CSV.
Prompts for SDR / BDR
Individual tasks with required inputs and example outputs. Each prompt lists the assistants it supports.
Turn a Company URL Into a First-Call Brief
Turn a company URL into a sourced, opinionated first-call brief that maps your offer to your buyer's real pressures and earns the next meeting.
Works with: Claude, ChatGPT, Gemini, PerplexityWrite a Cold Email That Earns a Reply
Produce a tight, relevance-first cold email with one clear ask, built around the prospect's trigger not your pitch, sub-90 words, no fluff, no fabrication.
Works with: Claude, ChatGPT, GeminiCold Email Sequence Template (Multi-Touch)
A cold email sequence template as a prompt: generate a value-led, multi-touch cadence where each touch adds a new angle, not a nag, with personalization tags and a test plan baked in.
Works with: Claude, ChatGPT, GeminiSales Discovery Questions, Tailored to the Deal
Build deal-specific, open-ended sales discovery questions mapped to pain, quantified impact, process, and competition, with the must-answer for each.
Works with: Claude, ChatGPT, GeminiObjection Handling Script for Tough Objections
Turn a specific objection into an objection handling script: the clarifying question to ask first, the likely root causes, and three honest, non-defensive responses that advance the deal.
Works with: Claude, ChatGPT, GeminiReply Fast to an Inbound Lead
Draft a fast, intent-matched reply to an inbound lead that keeps momentum, qualifies with one smart question, and makes the next step one click.
Works with: Claude, ChatGPT, GeminiGuides for your chosen assistant
Follow the guide for the tool you use. A shared workflow directory does not change the setup requirements of an individual playbook.
Claude
- Prompting Claude: what actually moves the needle →The things that reliably improve Claude's output are mostly structural: paste the real source material instead of describing it, state the goal, audience, constraints, and exact output format, show an example of the shape you want, and put long context first with the instruction last.
- Getting started with Claude: your first hour, done right →Sign up free at claude.ai (or install the desktop and mobile apps), then spend your first hour on a real task instead of a toy question.
- Claude Projects: persistent, context-rich workspaces →A Claude Project is a workspace that holds custom instructions and a set of knowledge files, so every chat you start inside it opens already knowing your business, your ICP, your voice, your rules, instead of you re-explaining all of it every time.
- Web search in Claude: answers beyond the cutoff →Web search lets Claude pull current information from the live web and cite the sources it used, instead of relying only on what it learned in training.
- The best AI for cold email: the model writes, the sender sends →The best AI for cold email is two tools, because cold email is two jobs.
- The best AI for sales research: the model reasons, the data provider verifies →The best AI for sales research is two tools, because account research produces two kinds of facts.
- Claude vs AI SDR tools: build the agent or rent the rep →Buy an AI SDR tool (11x, Artisan, AiSDR) when you have no builder on staff and need outbound volume running in weeks: you get data, writing, sending, deliverability, and reply handling behind one login and one invoice, at a price that starts around $900 a month for the cheapest published plan and climbs fast.
ChatGPT & Codex
- ChatGPT search and deep research: from sources to a decision →Use search for focused current questions and deep research for an investigation across sources.
- ChatGPT custom instructions and prompting: brief the work clearly →Use custom instructions for stable preferences and task prompts for the specific outcome, sources and checks.
- Writing with ChatGPT: drafts, documents and focused revisions →Use Chat for a short drafting conversation and Work when you need a finished document, presentation or PDF.
Frequently asked questions
What should an SDR try first?
An account brief for a company you already understand. You can judge whether the research is useful, whether the sources support it, and whether it gives you a better opening for a conversation.
Can I use these prompts in ChatGPT or Claude?
Check the tool list beside each prompt. The shared prompt library includes both ChatGPT and Claude. A full playbook or skill may require a particular product, connector, or sending system; follow its own setup instructions.
How do I keep outbound from sounding generic?
Supply real account evidence, your actual offer, and examples of the voice you want. Edit the draft for a specific reader. Extra adjectives and a compliment about the company do not make an email personal.
Should I automate the send too?
Treat sending as a separate decision. First prove that the targeting, evidence, and message are right. Keep campaign review and ownership explicit when you connect drafting to a sending tool.