Ditto for Content Marketing

Generate research-backed blog articles, infographics, social threads, and more from a single Ditto study — at a pace of 20-40 articles per month. Directly from the terminal.

Full documentation: https://askditto.io/claude-code-guide

What Ditto Does

Ditto maintains 300,000+ AI-powered synthetic personas calibrated to census data across USA, UK, Germany, and Canada. You ask them open-ended questions and get qualitative responses with the specificity of real interviews.

• 92% overlap with traditional focus groups (EY Americas validation)
• Every study produces 70 data points (10 personas x 7 questions)
• One study → 7 content formats in ~60 minutes
• Traditional research-backed content: 2-4 articles/month, $2,000-10,000 each

The Content Quality Test

If you could write the article without the study data and it would read the same, it is NOT research-backed.

Every paragraph must contain a finding, quote, or data point from the specific study. Generic commentary with a study link appended is not content marketing — it is filler.

Quick Start (Free Tier)

Get a free API key — no credit card, no sales call:

curl -sL https://app.askditto.io/scripts/free-tier-auth.sh | bash

Free keys (rk_free_): ~12 shared personas, no demographic filtering. Paid keys (rk_live_): custom groups, demographic filtering, unlimited studies.

API Essentials

Base URL: https://app.askditto.io Auth header: Authorization: Bearer YOUR_API_KEY Content-Type: application/json

One Study, Seven Content Formats

One 10-Persona Study (~12 min)
    ├─ 1. Research Blog Article (1,000-2,500 words, SEO/GEO optimised)
    ├─ 2. Infographic (key findings visualised)
    ├─ 3. Social Media Thread (3-5 posts)
    ├─ 4. Email Outreach (personalised per recipient)
    ├─ 5. Executive Summary (1-page, PDF-ready)
    ├─ 6. Sales Leave-Behind (for prospect sharing)
    └─ 7. Press Release (if newsworthy)

Total: ~60 min from zero to complete content kit
Traditional: 2-4 weeks, $5,000-15,000

The Content Marketing Workflow (6 Steps)

Step 1: Recruit Your Audience Panel

Match the panel to the content's target reader:

curl -s -X POST "https://app.askditto.io/v1/research-groups/recruit" \
  -H "Authorization: Bearer $DITTO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "US Coffee Consumers 25-55",
    "group_size": 10,
    "filters": {
      "country": "USA",
      "age_min": 25,
      "age_max": 55
    }
  }'

Save the uuid. Use group_size (not size), group uuid (not id).

Step 2: Create Study

curl -s -X POST "https://app.askditto.io/v1/research-studies" \
  -H "Authorization: Bearer $DITTO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Consumer Perceptions of [Topic]",
    "objective": "Generate research-backed content on [topic] with quotable insights",
    "research_group_uuid": "UUID_FROM_STEP_1"
  }'

Response nests under data.study — access via response["study"]["id"].

Step 3: Ask the 7 Content Questions

Ask one at a time. Poll to completion between each (see Polling Strategy). Do NOT batch questions — batching produces shallow, disconnected answers.

Step 4: Poll Until Complete

curl -s "https://app.askditto.io/v1/jobs/JOB_ID" \
  -H "Authorization: Bearer $DITTO_API_KEY"

Wait 45-50 seconds before first poll, then 20 seconds intervals. Poll ONE job_id as proxy.

Step 5: Complete the Study

curl -s -X POST "https://app.askditto.io/v1/research-studies/STUDY_ID/complete" \
  -H "Authorization: Bearer $DITTO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"force": false}'

Step 6: Extract Content Building Blocks + Get Share Link

curl -s "https://app.askditto.io/v1/research-studies/STUDY_ID/questions" \
  -H "Authorization: Bearer $DITTO_API_KEY"

curl -s -X POST "https://app.askditto.io/v1/research-studies/STUDY_ID/share" \
  -H "Authorization: Bearer $DITTO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"enabled": true}'

UTM tracking (mandatory):

• Cold email share links: ?utm_source=ce
• Blog article share links: ?utm_source=blog

The Content Question Framework (7 Questions)

Questions follow a narrative arc — not an investigative sequence. The arc produces content that reads as a story, not a survey report.

The Narrative Arc

Q1-Q2 = "Before" (the problem state)
Q3    = "Turning point" (the possibility of change)
Q4-Q6 = "Substance" (evidence, comparison, evaluation)
Q7    = "Payoff" (unfiltered truth, strongest quotes)

Q1 — First Impressions (opening hook material)

"When you think about [product/category], what's the first thing that comes to mind? What's your honest impression?"

Extract: Opening hook, first-impression reactions, headline candidates.

Q2 — Pain Stories (relatable anecdotes)

"What's the biggest frustration or unmet need you have with [category]? Tell me about a specific experience."

Extract: Pain point stories for article body, relatable anecdotes.

Q3 — The Turning Point (possibility of change)

"If a product could [your value proposition], how would that change things for you? What excites you? What makes you sceptical?"

Extract: Excitement = opportunity content. Scepticism = objection content.

Q4 — Current State (competitive landscape)

"How do you currently solve this problem? What tools, services, or workarounds do you use? What do you spend on it?"

Extract: Competitive landscape content, cost comparisons, workaround stories.

Q5 — Product Reaction (direct feedback)

"Looking at [product/website/feature], what stands out? What's confusing? What would make you want to try it?"

Extract: Product reaction quotes, UX feedback, conversion triggers.

Q6 — Decision Criteria (comparative content)

"If you were choosing between [product] and [top alternative], what would tip the decision? What evidence would you need?"

Extract: Competitive content, proof point needs, decision criteria.

Q7 — Unfiltered Truth (the payoff — strongest quotes)

"Is there anything about [category] that you feel companies just don't understand? What do you wish they knew?"

Extract: Strongest quotes for social media. Unfiltered frustration for positioning. Best content hooks.

Content Building Blocks

Extract from every study:

Blog Article Structure

7 sections, 1,000-2,500 words:

1. Hook (50-100 words) — Lead with the headline finding
2. Context (100-150 words) — Why this topic matters now
3. Who We Asked (100-150 words) — Panel demographics, methodology
4. What We Asked (50-100 words) — Question themes, approach
5. Key Findings (400-800 words) — THE CORE. 3-5 findings, each with data point + quote + implication. This is where the study data lives.
6. Implications (150-200 words) — What this means for the industry
7. Conclusion + CTA (100-150 words) — Summary + link to live study

SEO Optimisation

GEO Optimisation (Ge