How Credits Work
Before you start: credits are consumed in two places during a campaign.
Generating a lead — 1 credit per lead. This creates the personalized sequence for that lead.
Deep research on a lead — 1 credit per lead. This runs expanded research and is a separate action from generating.
Re-generating the same lead's sequence within the same campaign — free. Iterate as much as you want once a lead is enriched.
Generating the same lead in a different campaign counts as a new credit.
1. Add Your Leads
Start by adding the leads you want to reach out to. Twain gives you three options:
Upload CSV — upload a custom lead list from LinkedIn Sales Navigator, Apollo, or another source
Integrations — connect directly via your sales tools (e.g., Clay, HubSpot)
Add manually — paste LinkedIn URLs one by one
When uploading a CSV, map these fields:
Work Email — required for delivery
LinkedIn Profile — used for research-based personalization
Company Name, Title, First Name — optional, but the more context you give, the better the personalization
💡 If you have a large list, consider splitting it in half. It makes A/B testing easier later without extra setup.
💡 Clean, well-mapped data ensures Twain personalizes correctly and prevents errors during export.
2. Set Up Your Agent
Agents are the brain behind your campaign. They research your leads, apply your personas and rules, and write personalized sequences. Once created, an agent can be reused across multiple campaigns — you don't need to rebuild it every time.
If it's your first campaign, click Create Agent. You'll fill in three sections:
General — Base knowledge and context
Enter your company website and add a short description of the agent's purpose and audience. You can also upload files (e.g., a one-pager or brochure) for additional context. Twain uses all of this to understand your product and value proposition.
The General tab also contains:
Signals — specific data points or triggers you want the agent to look for when researching leads. Twain already researches key lead data by default; signals let you go deeper.
Warnings — disqualifiers or red flags that should stop a lead from being contacted. Twain flags common issues by default; add your own on top.
Personas — Audience and value prop
Twain suggests buyer personas based on your General setup. Each persona has detailed fields: Company/product name, Pain points, Cost of inaction, Solutions, Objections, Competitive advantages, and Social proof. Review the suggestions, edit what doesn't fit, and add new ones if needed.
Personas help the agent tailor messaging to different audience types within the same campaign.
Rules — Research and warnings
A summary view of your Signals and Warnings before you finalize the agent. Once you're happy, click Create Agent.
💡 If you've already built an agent for a previous campaign, select it from the list instead of creating a new one. A well-configured agent improves over time — the more you use and refine it, the better it represents your brand.
Fine-tuning your agent after campaign creation
Once your campaign is live, you can access extended agent settings via the ⚙️ icon next to "Agent" in the campaign view. This opens three tabs: General, Personas, and a new tab that isn't available during initial setup:
Writing style
Control how the agent writes across all campaigns it's used in:
Tone — three sliders: Formality (Casual to Official), Creativity (Direct to Imaginative), Firmness (Humble to Assertive). Use Auto-detect to let Twain infer your style, or Preview to test it.
Blocklist — words or phrases that should never appear in generated copy. Twain already blocks common spam words by default; add your own on top.
Terms — company-specific vocabulary, acronyms, or product names with exact spelling and context instructions.
💡 It's worth setting up Writing style after your first campaign — it applies to all future campaigns using the same agent.
3. Define Your Campaign Idea
Describe why you're reaching out to this specific list. Be specific — the more context you give, the more relevant Twain's research and messaging will be.
Use the helper buttons to structure your idea:
+ Context — describe the shared signal or trigger across your leads (e.g., "All leads have recently expanded their sales team, which typically means they're scaling outbound")
+ Research — tell Twain what to specifically look for per lead (e.g., "Search if they've publicly spoken about outbound challenges or AI adoption")
+ Rules — add targeting constraints (e.g., "Only reach out to companies headquartered in the EU with 50–200 employees")
+ Intent — describe your outreach goal (e.g., "We'd like to invite them to a free trial" or "We want to offer them a free audit")
You can also click Suggest to let Twain generate an idea based on your agent setup, or use History to pull in a campaign idea from before.
💡 Keep your wording consistent throughout. If you call your targets "leads," use "leads" everywhere. Mixing terminology can affect the quality of Twain's output.
💡 You can edit the campaign idea at any time after creation by clicking the pencil icon next to "Idea" in the campaign view.
4. Configure Your Sequence
Choose how to structure your messages:
Auto — Twain decides the sequence format for you. Then select your outbound channel: Email, LinkedIn, or both. Hit Create Campaign.
Customize — manually define the number of steps, message types, and structure.
💡 Not sure which to pick? Start with Auto. You can always adjust individual steps via the Framework Editor once the campaign is created.
5. Review Research Before Generating
Once your campaign is created, you can run deep research on individual leads before generating their sequence. Open the Research tab to see what Twain has found:
About — a summary of the lead's role and company focus
Insights — real-time findings with source links (e.g., recent funding rounds, rebrands, product launches)
Discovery questions — suggested conversation starters based on the research
Talking points — value prop angles with examples
Why now — why the timing of your outreach is relevant for this specific lead, backed by recent signals
Why us — why your product is relevant for this lead's current situation and challenges
The right panel also shows a Warning if Twain has flagged something about the lead (e.g., company instability, wrong persona fit) and which Persona has been auto-assigned to that lead.
Use the Research tab to spot data quality issues before spending credits on generating the full list.
💡 For a deeper dive into Twain's research capabilities, see: Using Expanded Research for Manual Prospecting.
6. Generate a Few Leads First
Before generating your entire list, generate one or two leads to see how the messages look. This costs credits but saves you from generating a full list based on a setup that needs adjustment.
Check: Does the opener feel relevant? Is the tone right? Is the CTA what you intended?
💡 Generating a lead costs 1 credit. Re-generating the same lead within the same campaign is free — so iterate as much as you want once a lead is enriched.
7. Refine Your Messages
Once you've seen how the first messages look, refine before generating at scale. You have three ways to adjust:
Framework Editor — click the pencil icon on any step to edit the underlying message structure. Use structured placeholders to redefine the narrative flow (e.g., pain-point > solution > proof, or research > question > CTA). Switch between saved frameworks or create a new one. Apply changes with Update Step. Frameworks can be saved and reused across campaigns.
💡 For a full walkthrough of the Framework Editor, see: Framework Editor – Customize and Test Campaign Structures
Instructions and exact phrases — type directly into the campaign to shape Twain's output:
Instructions guide tone and structure (e.g., "Make this conversational and under 80 words")
Exact phrases ensure specific language always appears (e.g., "Twain injects real-time research into every message")
AI chat panel — use the chat panel (bottom right of the campaign view) to ask Twain to adjust steps directly, e.g., "Make step 2 shorter" or "Change the CTA to a softer ask."
💡 The goal is for the output to sound like you, not like a generic SDR. Invest time here before generating at scale.
8. Generate at Scale
Once you're happy with the setup, generate messages for all leads.
💡 Twain only exports leads with generated content to your sequencer. Leads that haven't been enriched yet won't be included.
9. Set Up A/B Tests
Duplicate the campaign and change one element. Good things to test:
CTA: "Book a 15-min call" vs. "How are you currently handling this?"
Subject line: Offer-based (e.g., "Quick idea for your team") vs. Source-based (e.g., referencing something the lead published)
Opener style: Research-led vs. pain-point-led
Run both campaigns in parallel and compare open rate, reply rate, and positive reply rate.
💡 A/B testing shows what actually resonates with your audience instead of guessing.
10. Export
Export your generated leads:
Google Sheets — for review or manual editing before sending
Instantly, Smartlead, Lemlist, HeyReach, LaGrowthMachine — direct integration, exports leads with personalized copy straight into your sending sequence
11. Best Practices
Don't skip the agent setup: The quality of your agent — especially personas, signals, and writing style — directly determines personalization quality. It's worth the upfront time.
Reuse and refine your agent: A good agent is an asset. Use it across campaigns and update it as you learn what works, rather than building new ones from scratch.
Be specific in your campaign idea: Vague ideas produce generic output. Describe your signal, research intent, and targeting rules as concisely and specifically as you can.
Check the Research tab first: Before generating at scale, spot-check a few leads to make sure the data quality is good. Remember: research and generating are billed separately.
Test before scaling: Generate a few leads, refine the idea, agent, or framework, then generate at scale.
Be opinionated: The AI should sound like you. Use your own vocabulary, CTAs, and point of view.
A/B test early: Even a small list split gives you data to work with for the next campaign.