---
name: sales-imario
description: "iMario (imario.ai) platform help — a synthetic-research \"human layer\" where reusable Synthetic Individuals (built from a plain-English brief, a LinkedIn profile, or a personality assessment, each with persistent working/episodic/semantic memory) run across six jobs on a visual Canvas: audience research, concept/product validation, sales-outreach and content testing, CX/journey design, sales-enablement rehearsal, and AI-agent personality via API. Use when setting up an iMario Canvas or Synthetic Individual, choosing how to build a cohort (brief vs LinkedIn vs personality twin), grounding it in a Knowledge Base, interpreting a synthetic report or the 90%-parity claim, reusing one persona across studies, wiring the Pro-gated API into a production agent, or judging whether a synthetic \"yes\" is real demand. Do NOT use for comparing synthetic-research/persona/idea tools or the validate-before-building method (use /sales-idea-validation), or the pure-play study tool with a public API (use /sales-syntheticusers)."
argument-hint: "[describe what you need help with in iMario]"
license: MIT
version: 1.0.0
tags: [sales, pre-launch, platform]
---

# iMario Platform Help

iMario (imario.ai) is a **synthetic-research and audience-intelligence** platform that calls itself
"the human layer of AI." Instead of a one-shot study tool, its unit is a **reusable Synthetic
Individual** — a constrained cognitive model (not plain LLM roleplay) with a **Deep Identity**
narrative, **Expert Reflection** panels (demographer / psychologist / economist), **Knowledge
Boundaries**, and a **three-layer memory** (working / episodic / semantic, with Ebbinghaus decay) that
**persists across sessions**. You build a cohort three ways — a **plain-English brief**, a **LinkedIn
profile**, or a **personality assessment** ("synthetic twin") — and run tasks against them on a visual
**Canvas** (a node editor that replaced the old funnel flow), grounded in your own files via a
**Knowledge Base** (RAG). The same individual can be reused across **six jobs**: Discover (research),
Validate (concept/product), Launch (sales outreach & content testing), Optimize (CX/journey), Scale
(sales/service enablement), and Build (**AI-agent personality via API**).

Its signal is **directional, not demand**: synthetic individuals model existing/public/training data,
so they skew **agreeable, generic, and Western-biased** and can't surface a genuinely *new* unmet need.
The 90%+ "human parity" figure is a **vendor claim** — treat any synthetic result as a **hypothesis to
disconfirm with real behavior**, not a green light.

## Step 1 — Gather context

If `references/learnings.md` exists, read it first for accumulated platform knowledge.

Ask only what you can't infer:

1. **What do you want from iMario?**
   - A) Build a **Synthetic Individual / cohort** — pick the input (brief / LinkedIn / personality twin)
   - B) Set up a **Canvas** task — research, concept test, content test, journey, or sales rehearsal
   - C) **Ground** it in your own data (Knowledge Base / RAG upload) for specific answers
   - D) **Interpret** a synthetic report, distribution, or the 90%-parity claim you already have
   - E) **Reuse one persona** across multiple jobs, or **automate** via the Pro-gated API / production agent
   - F) Decide **whether to trust it** — is this a valid stand-in for real research?
2. **What's the question and who's the audience?** A sharp brief + Knowledge Base yields usable signal;
   a vague one yields generic filler.

Skip-ahead: if the user wants to **compare** synthetic-research/persona/idea tools across the market, or
the validate-before-building *method*, that's a `/sales-idea-validation` question — route in Step 2.

## Step 2 — Route or answer directly

| If the user's question is about… | Route to |
|---|---|
| Comparing synthetic-research/persona/idea tools, or the validate-before-building **method** | `/sales-idea-validation {question}` |
| The **pure-play** synthetic study tool with a **documented public REST API** (Bearer, SDKs, SSE) | `/sales-syntheticusers {question}` |
| A **data-grounded persona you chat with** built from your GA4/CRM/social | `/sales-delve` or `/sales-marketing-mary` `{question}` |
| Running a **real** demand test (smoke-test page, waitlist, pre-sale) after synthetic signal | `/sales-idea-validation` or `/sales-funnel` `{question}` |
| Analyzing **real-customer** NPS/CSAT/VoC feedback (post-launch) | `/sales-customer-feedback {question}` |

When routing, give the exact command: "This is a {domain} question — run: `/sales-idea-validation {original question}`"

Otherwise, answer iMario-specific questions using Step 3.

## Step 3 — iMario platform reference

**Read `references/platform-guide.md`** for the full reference — the Synthetic Individual model
(Deep Identity, Expert Reflection, Knowledge Boundaries, three-layer memory), the three cohort inputs,
the Canvas node editor and six jobs, Knowledge Base / RAG grounding, the API/webhook/UI-only tag on each
module, best-effort credit-based pricing and the Pro API gate, the data model (Synthetic Individual /
Canvas / Task / Cohort JSON shapes), and quick-start recipes.

For the API surface (Pro-gated, no public developer docs at research time), read
`references/imario-api-reference.md`.

Answer using only the relevant section — don't dump the full reference.

## Step 4 — Actionable guidance

You no longer need the platform guide — focus on the user's specific situation.

- **A synthetic "yes" is not demand — say so every time.** Whatever the user asks, make explicit that
  Synthetic Individuals model existing/public/training data, so they run **agreeable, generic, and
  Western-biased** and can be **confidently wrong**. Frame every result as a **hypothesis to disconfirm
  with a real behavior test** (smoke-test click, reply, pre-sale) — keep the *objections, angles, and
  language* it surfaces (its real value), take the go/no-go from real strangers, and route the real test
  to `/sales-idea-validation`.
- **Treat the "90%+ human parity" figure as a vendor claim, not proof.** When the user cites it, note it
  is self-reported (the site itself pegs quantitative agreement near ~89% and admits real survey retest
  agreement is only ~93%), varies sharply by question type (weak on behavioral/emotional/cultural), and
  is not a validity verdict — don't let it substitute for a real behavior test.
- **Play iMario's actual edge: reuse + memory.** Its differentiator over one-shot tools is that the
  **same Synthetic Individual persists across sessions and jobs** — build a cohort once, then reuse it
  across Discover → Validate → Launch → rehearsal on the **Canvas**. Point the user here when they want
  continuity, not a fresh throwaway panel each time.
- **Ground it in a Knowledge Base and sharpen the input — output tracks input.** A thin brief yields
  generic filler ("garbage in, garbage out"). Tell the user to **upload real data** (interviews,
  tickets, segment defs) to the Knowledge Base and write a **specific brief**, or anchor to a **LinkedIn
  profile / personality assessment** for a sharper individual. Note Knowledge Base file limits are
  plan-gated (Free: 1 KB / 1 file).
- **Present pricing and the API gate as best-effort.** It's **credit-based** (Free 500 one-time credits;
  Starter/Pro monthly credits; PAYG packs) and **API access is Pro-tier-and-above** with **no public
  developer docs** found — say figures are best-effort and confirm at imario.ai/pricing before relying
  on them; for API specifics, tell the user to request docs from iMario.
- **For the "Build" / production-agent use case, set expectations.** The API pipes a Synthetic
  Individual's personality into a production agent, but it's **Pro-gated and undocumented publicly** —
  scope any integration as "confirm auth + endpoints with iMario first," and don't invent endpoint
  shapes. If the user needs a **documented public API today**, point them to `/sales-syntheticusers`
  as the alternative.

If you discover a gotcha or tip not in `references/learnings.md`, append it there with today's date.

## Gotchas

*Best-effort from research (2026-07) — credit pricing, plan gates, the Pro API surface, and the
"parity" figures move; verify at imario.ai and imario.ai/pricing.*

- **Sycophancy / agreeableness bias.** Synthetic Individuals tend to *please* — shallow, overly
  favorable feedback that can approve a concept real users would reject. Never read a positive synthetic
  reaction as validation.
- **It can't surface a NEW unmet need.** It models existing/public data, so it's strongest at
  *pre-testing a hypothesis you already have* and weakest at discovery. Don't use it to "find the problem."
- **The 90%+ parity claim is vendor-reported and question-dependent.** It's strongest on structured
  attitudinal questions and weak on behavioral, emotional, and culturally specific ones. Don't treat it
  as a validity guarantee.
- **Western/geographic and identity bias.** Outputs skew toward Western, majority perspectives and can
  flatten identity groups — be cautious generalizing across markets/segments.
- **Garbage in, garbage out.** A thin brief or empty Knowledge Base yields generic filler. Ground the
  cohort and write a specific brief before trusting any theme.
- **API is Pro-gated and undocumented publicly.** API access unlocks only on **Pro and above**, and no
  public developer docs were found — don't assume endpoints/auth; request docs from iMario and confirm
  before building. Free tier is heavily limited (10 SIs/mo, 1 LinkedIn profile, view-only report).

## Related skills

- `/sales-idea-validation` — The tool-agnostic validate-before-building method + the full synthetic-research/persona/validator tool landscape (use this to actually decide build-or-not; a synthetic "yes" is not demand)
- `/sales-syntheticusers` — Synthetic Users platform help (the pure-play synthetic **study** tool — single-workflow AI-moderated interviews, but the cluster-rare one with a **real documented public REST API** [Bearer, Python/TS SDKs, SSE, PDF export]; iMario's closest peer, trading iMario's reusable-persona breadth for a documented API)
- `/sales-delve` — Delve AI platform help (data-grounded personas + Digital Twins + Synthetic Research built from your real GA4/CRM/social data — the persona-you-chat-with counterpart; paid, gated API)
- `/sales-marketing-mary` — Marketing Mary platform help (interactive buyer personas you converse with, grounded in real CRM/GA4 data; UI-only, no public API)
- `/sales-customer-feedback` — Real-customer NPS/CSAT/VoC strategy across tools (use once you have live customers; synthetic research is pre-launch only)
- `/sales-funnel` — Build the smoke-test / fake-door landing page that turns a synthetic hypothesis into a real demand test
- `/sales-do` — Not sure which skill to use? The router matches any sales objective to the right skill. Install: `npx skills add sales-skills/sales --skill sales-do -a claude-code`

## Examples

### Example 1: "The synthetic panel loved my concept — should I build it?"
**User says**: "I ran a concept test on iMario and 9 of 10 Synthetic Individuals said they'd buy. It says 90%+ human parity — green light?"
**Skill does**: Explains Synthetic Individuals **model existing/training data and skew agreeable**, so a
near-unanimous "yes" is a **directional signal, not demand**, and the **90%+ parity is a vendor claim**
that's weakest exactly on behavioral/purchase questions. Tells the user to **mine the responses for
objections and language** (the real value) and take the go/no-go from a **real behavior test** — a
smoke-test click or pre-sale — routed via `/sales-idea-validation`.
**Result**: The founder keeps the angles, runs a real fake-door test before writing code.

### Example 2: Reusing one Synthetic Individual across research and sales rehearsal (references/platform-guide.md)
**User says**: "Can I build a buyer persona once and reuse it for both discovery interviews and to rehearse my pitch?"
**Skill does**: Says yes — iMario's edge is that a **Synthetic Individual persists across sessions and
jobs** via its three-layer memory, so you build the cohort once (brief / LinkedIn / personality twin),
**ground it in a Knowledge Base**, and reuse it across **Discover** (research) and **Launch/Scale** (sales
outreach & rehearsal) on the **Canvas**. Notes output tracks input — sharpen the brief and upload real
data — and that each result is still a hypothesis to test with real buyers.
**Result**: One grounded persona reused across jobs instead of a throwaway panel per task.

### Example 3: Piping a Synthetic Individual into a production AI agent via the API (developer/automation)
**User says**: "I want to give my support-bot a real buyer's personality using iMario's API. How do I wire it in?"
**Skill does**: Explains the **Build** use case — the API embeds a Synthetic Individual's personality
into a production agent — but flags that **API access is Pro-tier-and-above** and **no public developer
docs** were found at research time, so it **won't invent endpoints or auth**. Advises scoping the
integration as "request API docs from iMario, confirm auth + endpoints, then build," and points to
`references/imario-api-reference.md` for what is known and its gaps.
**Result**: The user upgrades to Pro, gets the real docs, and integrates without relying on guessed shapes.

## Troubleshooting

### "The Synthetic Individuals agreed with everything — is that real?"
**Symptom**: Tasks return uniformly positive, agreeable feedback that feels too good.
**Cause**: LLM-based individuals exhibit **sycophancy** — they model plausible agreement and skew favorable.
**Solution**: Discard the "verdict," keep the **objections and language** surfaced, and validate the
concept with **real behavior** (smoke test, pre-sale). Ground the cohort in a Knowledge Base and sharpen
the brief to reduce generic agreement. Cross-check via `/sales-idea-validation`.

### Results feel generic / could describe anyone
**Symptom**: Themes are vague and not specific to your product or buyer.
**Cause**: Thin brief and **no Knowledge Base grounding** — "garbage in, garbage out."
**Solution**: Write a **specific brief** and **upload your own data** (interviews, tickets, segment defs)
to the Knowledge Base, or anchor the cohort to a **LinkedIn profile / personality assessment**. Note
Knowledge Base file limits are plan-gated (Free: 1 KB, 1 file). Re-run with a focused task.

### "I can't find the API — how do I automate iMario?"
**Symptom**: You want to pull results or embed a persona but there's no API key or docs in the UI.
**Cause**: **API access is gated to Pro and above**, and iMario publishes **no public developer docs**.
**Solution**: Upgrade to **Pro** to unlock API access, then **request the developer docs from iMario**
(support/sales) — don't assume endpoints or auth from other tools. See `references/imario-api-reference.md`
for the known surface and its gaps; for a tool with a documented public REST API today, consider
`/sales-syntheticusers`.