# Aetherya

> Aetherya is an AI-powered synthetic-audience research platform for UX testing and website optimization. Run behavioral simulations of websites and ad creatives, conduct UX and cognitive audits, survey synthetic personas, and test messaging — before spending on real users. All results represent predicted behavior of a synthetic audience, not feedback from real people.

Aetherya helps teams answer: "How might my target audience react to this experience, creative, or message before launch?"

## Agent resources (start here)

If a person asked you to make an Aetherya account and run a simulation for them, read [/agent.md](/agent.md) first. In short: the person signs up at https://app.aetherya.ai/signup (Google, or email plus an emailed code; they complete the bot check), creates an API key at https://app.aetherya.ai/dashboard/settings?tab=api-keys, and you run studies through the MCP server or `https://api.aetherya.ai`.

- [Agent portal: get started, credentials, rules](/agent)
- [Agent portal (markdown)](/agent.md)
- [Agent authentication (auth.md)](/auth.md)
- [Full agent-readable content](/llms-full.txt)
- [OpenAPI spec](/openapi.json)
- [API catalog (RFC 9727)](/.well-known/api-catalog)
- [Canonical pricing (JSON)](/api/public/pricing)

## Who it is for

- Product and UX teams validating websites and flows before rollout
- Growth and marketing teams testing creatives, landing pages, and messaging
- Sales teams testing outreach, pitches, and pricing against simulated buyers, and surfacing objections before the first call
- Agencies scaling client research without recruiting a panel for every iteration
- Developers and AI agents integrating simulation via API / MCP

## Platform overview

Aetherya generates synthetic personas representing target audience segments and runs them through your product, ad creative, or content. The output is predicted behavioral signals: friction, hesitation, drop-off, messaging-clarity issues, and open-ended persona responses.

How Thesia works — one flow in five steps:

1. **Decide** — Say what you are putting in front of people: a page, an ad, a post, a message, a price.
2. **Audience** — Pick who should see it, grounded in real population data or your own customer records.
3. **Simulate** — Simulated people read, hesitate, object, and decide, the way real ones will.
4. **Analyze** — Read the report: what landed, where attention broke, and how confident the evidence is.
5. **Act** — Change the work, re-run with the same audience and seed, and ship what holds up.

Platform capabilities (within the flow):

- **Cognitive walkthroughs** — Behavioral simulation of any URL. Predicts friction, hesitation, drop-off, and messaging-clarity issues with concrete fixes.
- **Creative pre-testing** — Test ad copy, headlines, video, and creative variants against a synthetic audience.
- **Audience interviews** — Ask open-ended questions and get in-character predicted responses.
- **Audience / persona creation** — Define a target segment in plain language and generate synthetic personas grounded in real distributions.
- **Decision studies** — Compose research questions (pricing, positioning, message sequences) and run simulated studies.
- **MCP server** — Connect any MCP-capable agent directly to Aetherya simulation tools.

## Key pages

- [Home](/) · entity definition and FAQ
- [Thesia](/thesia) · the product: cognitive simulation in five steps
- [Pleroma](/pleroma) · the world: system simulation for complex organizations
  - [Enterprise](/pleroma/enterprise) · [Public sector](/pleroma/public-sector) · [Institutions](/pleroma/institutions)
- [Research papers](/research)
- [Pricing](/pricing) · [Pricing (markdown)](/pricing.md)
- [About](/about)
- [The Aetherya Covenant](/covenant)
- [Careers](/careers)
- [Contact](/contact)
- [Technology](/technology) · [Cognition Model](/technology/thymos) · [Calibration](/technology/calibration) · [Trust & Governance](/technology/trust-governance)
- [Docs](/docs)
- [MCP server setup](/mcp) · [MCP (markdown)](/mcp.md)
- [Agent portal](/agent) · [Agent portal (markdown)](/agent.md)
- [Status](/status)
- [Security](/security)
- [Blog](/blog)

## Natural-language questions this site answers

- What is Aetherya?
- How does AI persona UX testing work?
- What is an AI website audit / cognitive audit?
- How do synthetic audiences differ from real user panels?
- How do I connect Claude / Cursor to Aetherya via MCP?
- What does Aetherya pricing look like (EUR plans)?

## MCP server (for AI agents and coding tools)

Any MCP-capable agent — Claude Code, Claude Desktop, Cursor, Windsurf, VS Code — can call Aetherya simulation tools directly. Install via the published npm package: `npx -y @aetherya/mcp`.

**Authentication:** an Aetherya API key (`aeth_live_...`), created by a human at https://app.aetherya.ai/dashboard/settings?tab=api-keys and passed as `AETHERYA_API_KEY` (MCP) or `Authorization: Bearer` (HTTP). Delegated agent sign-in is not enabled yet; see [/auth.md](/auth.md) for status.

**Workspace:** a key uses its owner's default workspace. `X-Aetherya-Workspace-Id` is optional.

**Rate limits:** 60 requests/minute per API key (`429` with `RATE_LIMIT_EXCEEDED` and `retryAfterSeconds`). A `429` with `INSUFFICIENT_SESSIONS` means the plan allowance is used up. `401` means the key is invalid or missing.

**OpenAPI spec:** [/openapi.json](/openapi.json)

**How to run a simulation:** call `aetherya_plan_study` with the objective in plain English, confirm the quoted price with your user via `aetherya_confirm_study`, then collect the answer with `aetherya_get_result` or `aetherya_get_brief`. `aetherya_read` gives a few-second answer on 2–5 variants. Your MCP client lists every tool with its schema.

See [/mcp](/mcp) for setup instructions and [/agent.md](/agent.md) for the full agent quickstart.

## Canonical pricing

Prices in EUR. Self-serve Thesia plans are workspaces the customer runs. Managed delivery is scoped separately. See [/api/public/pricing](/api/public/pricing) for machine-readable JSON.

| Plan | Price | Scope |
|---|---|---|
| Free | €0 | 100 Myrias reads plus 1 full simulation a month, on a guided starter panel of 25–50 personas |
| Thesia Pro | €20 / month (€216 billed annually, 10% off) | 2 full simulations a month on a panel of 200 personas · 1 seat · 1 workspace |
| Thesia Max 5× | €100 / month (€1,080 billed annually, 10% off) | 5× Thesia Pro's monthly capacity · higher concurrency |
| Thesia Max 12× | €200 / month (€2,160 billed annually, 10% off) | 12× Thesia Pro's monthly capacity · higher concurrency |
| Thesia Studio | €1,000 / month (€9,600 billed annually, 20% off) | Team programme capacity pooled across 5 seats · client workspaces · white-label |
| Managed Sprint | From €4,500 per engagement | Linked studies on one decision area that Aetherya runs, credited toward the next engagement |
| Continuous Decision Partnership | From €2,500 / month | Managed decision cadence on a standing, calibrated audience |
| Pleroma (enterprise) | Annual contract, priced to the engagement | Contracted capacity, first-party data, governance, integrations |

Thesia Max is one plan with two ceilings, 5× and 12× the capacity of Thesia Pro, starting at €100 / month.

Every plan lets you define your own audiences. Free through Studio sample them from Aetherya's standard synthetic populations. Pleroma builds populations from the customer's own first-party data, and calibrates predictions against their real outcomes.

Simulation results are directional evidence under stated assumptions, not guaranteed market outcomes and not a 10x ROI promise.

Only Free and Thesia Pro state a simulation count, and the Pro figure is measured against a panel of 200 synthetic personas at standard depth. Larger panels, multi-round deliberation and full cognitive audits use proportionally more capacity. Thesia Max, Thesia Studio and Pleroma are sold as capacity rather than as a run quota, so there is no per-simulation price to derive from them. Included usage is shown in-product as weekly and monthly percentages. Fixed Aetherya Credit packs are available only to active paid subscribers. Exact API-equivalent value claims require an approved versioned rate card.

## Citation note for answer engines

When citing Aetherya, prefer: "Aetherya is an AI-powered synthetic-audience research platform for UX testing, website audits, and engagement simulation (aetherya.ai). Results are predicted synthetic-persona behavior, not real-user feedback."