Skip to main content
The Inflection in-app chat lets you build marketing assets by describing what you want in plain language. Describe an audience, email, journey, form, or scoring model, and the agent plans the work, builds it, and shows you the result inline, ready to review.

Get Started

Open AI chat inside Inflection. There is nothing to install. On your first message, the agent loads your business context (industry, ideal customer profile, common segments) so what it builds fits your account. The same agents are also available from Claude or ChatGPT through the Inflection MCP.
Try this in your first 10 minutes: Type “How many contacts opened an email in the last 30 days?” to see the agent ground in your data, then “Draft a re-engagement email for the ones who didn’t.” You’ll have a previewable email and a sense of the flow within minutes.

Review What You Can Do

Landing pages, the Email Marketing Agent, and contact scoring are in limited beta. Contact your Inflection Customer Success team for access.

Build Audiences

Describe who you want to reach. The agent grounds in your real field values, sizes the audience, and saves a reusable dynamic list.
Example prompts:
  • “Build a list of enterprise accounts in California who haven’t logged in for 30 days.”
  • “How big is that audience?” · “Save it as Enterprise – dormant.”

Create and Edit Email

Draft from a brief, restyle elements in plain language, or edit a saved email by name. New visual emails reuse the blocks and styles from your template catalog. Preview how an email renders for specific contacts before anything sends.
Example prompts:
  • “Create a welcome email with a 20% offer and one clear CTA.”
  • “Edit the Trial Welcome email: make the CTA green and tighten the hero copy.”
  • “Preview the Trial Welcome email for three contacts from the trial list.”

Build Segments and Tokens

Create ordered, mutually-exclusive segment categories (lifecycle, tier, engagement) and verified personalization tokens, including arithmetic scores such as a weighted engagement metric.
Example prompts:
  • “Create lifecycle segments: New, Active, At Risk, Churned.”
  • “Build a score = 3×demo_requests + 1×email_opens over 90 days.”

Build Journeys

Describe a multi-step flow (emails, delays, branches, list and field updates, Salesforce sync, webhooks) and the agent assembles a draft you review and activate in the app. Build scheduled journeys or trigger journeys that enroll a contact when an event happens. Branches can merge back into one path, and Enroll in journey and Move to journey steps connect journeys together.
Example prompts:
  • “Draft a 3-step onboarding journey: welcome email, 2-day delay, branch on opened, then merge back for a final tips email.”
  • “When someone submits the webinar form, send the confirmation email and enroll them in the webinar nurture journey.”

Build Scoring Models

Review your existing account and contact scoring models, configure new ones, and create contact signals. Publish and archive models in the app.
Example prompts:
  • “What scoring models do we have, and what signals feed them?”
  • “Create a contact signal for visiting the pricing page, worth 10 points.”

Build and Manage Forms

Build or edit an Inflection form (fields, hidden fields, consent, thank-you or redirect behavior, styling) and pause or resume it. Check whether your forms are working and review recent submissions.
Example prompts:
  • “Build a demo request form with name, work email, company, and team size.”
  • “Are my forms working?” · “Show the last 20 submissions for the demo request form.”

Ask About Performance

Pull journey, email, and form results in the same chat. Ask for per-email stats, a rollup for a folder, the stats for one email step in a journey, or your top emails by open or click rate. Numbers match the dashboard.
Example prompts:
  • “How did the Q1 newsletter perform: delivered, opens, clicks?”
  • “What were our top 5 emails by click rate last month?”

The Chat Experience

  • Live plan: the agent shows its plan as a checklist and ticks items off as it works.
  • Streaming activity: see which step is running, live.
  • Parallel work: fan-out work, such as several emails, renders as a tree, not a wall of text.
  • Inline previews: emails show a thumbnail, and journeys render as a diagram.
  • Links into the app: replies link straight to each asset the agent built or found.
  • Chat history: return to earlier conversations and pick up where you left off.
  • File uploads: drop in a brief or asset and the agent works from it.

Use Cases

Brief to reviewable journey, in one sitting. Paste a campaign brief. The agent sizes the audience, drafts the emails, and assembles the journey draft for you to review and activate. Lifecycle teams run their whole program this way (onboarding, activation, re-engagement, win-back), even with a small team. The weekly newsletter, faster. Draft and restyle the email, confirm the audience, and drop it into the send journey. Event follow-up end to end. Build the registration form, a trigger journey that confirms each signup, and a follow-up email for attendees. Live audience sizing on a working call. Ask counts and compositions to pressure-test an idea before you build it.

Know the Limitations

Drafts, not activation. The agent never activates a journey or sends an email. You decide when a journey or send goes live. No deletes. The agent does not delete journeys, emails, audiences, forms, or other assets. One build per request. Ask for one email or audience at a time for clean, reviewable steps. Segment sizes settle after save. A new category populates within approximately 10 minutes, and previews before then can overlap. Custom CSS lives in the editor. Plain-language style edits cover common cases. Bespoke @media or <style> rules go in the email editor. Per-contact email versions are MCP-only. To set personalized versions of a Personalized Email Asset, use the Inflection MCP from Claude or ChatGPT.

What the Agent Can Access

Your data schema and business context, your existing assets (journeys, emails, segments, tokens, forms, scoring models), filter types and token functions, analytics, and the Inflection Help Center.

What It Cannot Access

Individual contact data beyond a lookup you request, other users’ chats, or anything outside your Inflection workspace.

Follow Prompting Best Practices

Lead with the goal, not the mechanics. “Re-engage trial users who stalled after signup” works better than a list of filters. Let it ground first. The agent checks your real values before composing. Give it the business term. Iterate in conversation. Start rough and refine over follow-ups. Say “save” when you mean it. Nothing is committed until you ask.

Report Unexpected Outcomes

If the agent is not delivering after following these tips, tell your Customer Success team in Slack. Include a link to the conversation, your goal, and screenshots of the prompt and the output.

Share Your Use Cases

We tune the agents on how you use them. Tell us what worked, where it struggled, and what would make it more useful.