Not an AI that dumps it all —
a design coach that draws it out and verifies.
Plenty of discovery·validation tools — but the one slot that nails 'is this worth building' was empty. Before code, figure out if it's worth building.
Plus, no separate web app to open — right inside the coding tool you already use.
A preview to browse commands · the real thing runs inside your tool
Supported Coming soon Exploring
Core engines
Not dump-and-done — we dig in before it collapses
Whatever design doc you bring,
persona we find every gap
MULTI-AXIS IN-DEPTH REVIEW ENGINE
Normal flow
39 axes × recursive → until 0 findings
Senior-level review without hiring a PM. Stop months and millions in waste — before you code.
Expert-level gap-finding
Planning·persona·revenue·UX·security·value chain — gaps that 10 senior PMs couldn't catch.
Why the same problem repeats
Not just a list of issues — it reverse-traces why the team keeps designing this way.
Dev architecture too
Deep Architecture Review catches structural collapse risks before you build.
Preserves what works
Finds improvement paths without breaking UX·UI·logic that already works.
Next-action priority
'Right now' · 'before dev' · 'after dev' — what to do first, sorted.
Handoff-ready
Each report comes with a teammate·AI handoff message. Copy and send — done.
"Now I know what our team was missing."
We'd already built the product and spent a million won on paid ads. Three of us were all in. But of 17 signups, the number who experienced the core feature was zero. We didn't know what was wrong, or how to fix it.
At this rate, we'd keep pouring in time and money for the same result. We even started wondering whether to keep going with the idea at all.
We ran Hyper-Review, and it found 45 gaps in our planning doc. Together with a founder consult on the report, the biggest problem turned out to be this: we'd built the product on a thin service design. The persona was off, there was no real user value-chain analysis — so the UX was a mess too. It diagnosed all of it in one hour, and corrected the exact next actions.
This kind of consulting normally takes weeks and millions of won. I had no idea you could get diagnosed and handed a fix this fast. In the end we saved months of time and tens of millions — and could finally build a real product on a real design. In just one hour. I love it.
Grounded in your design,
competitor strategy dug out to the core
CONTEXT-AWARE DEEP RESEARCH ENGINE
Technical deep-dive
context-aware × evidence-graded
Answers you can't google, fetched with full design context. Run by your own AI tool — zero extra cost.
Design-aware research
Researches with your persona·design·tech context in mind, so results plug straight into the design.
Full competitor teardown
Walks into competitor products — onboarding·checkout·UX — and tears them fully apart.
Beyond official docs
Finds answers in GitHub code, community threads, and open source that search won't surface.
Graded evidence
Verified / public / inferred / experiential — every claim tagged with its evidence level.
Regulation & risk
Flags domain regulations, privacy handling, and licensing issues up front.
Flows back to design
Once findings land in the design, their integration quality gets re-reviewed.
"A competitor was already doing it better — and I had no idea."
We were building an AI prompt service. I thought the design was pretty solid, but I'd never run a value-chain analysis. Users had no real reason to choose us.
If we'd launched and marketed it like that, we'd probably have wasted time and money without ever knowing what was wrong.
We ran Hyper-Research, and it found that a direct competitor was already holding the same value-chain segment. It fully tore that competitor apart — what's strong, what's weak, and exactly where we could break in. That one research run pivoted our whole direction. I'd been agonizing over whether to hire a planner — and that's all money. With no capital, saving the time and money was a real relief.
"I finally understand why our service wasn't landing."
It was a health app we'd built over three months. We launched, got downloads, but retention wouldn't come. I asked ChatGPT and all it said was "good direction."
We had no time and no method to properly analyze competitors. The anxiety of burning another three months kept growing.
I dropped our whole planning doc into Hyper-Research, and it found three competitors on its own, walked their products end to end, and tore them fully apart. Which value-chain segment they hold, what they do better than us, where our comparative UX advantage is — once all that came back, I could see the gap we could break into. Setting direction with evidence instead of gut gave me real conviction, and reflecting it straight into my plan was fast and easy. I feel like I can actually do this on my own.
How users actually use it,
identity turned into scenarios
USER-SCENARIO REVERSE-ENGINEERING
User Flow
design truth → user scenario
Replays your design as the persona, step by step, so you see where users stall and drop off — in advance.
Reverse from design
Auto-builds user scenarios from identity·core value·persona·features·value chain.
Competitive context too
Takes value-chain analysis as input to generate scenarios with live competitive context.
Detects missing scenarios
When Hyper-Review flags 'missing user scenario', it auto-proposes generation.
Guides when design is thin
If the needed design is missing, it points you to Review or coaching first.
User Flow · Story Map
Maps the full path from first entry to feeling the core value.
Down to test seeds
Pulls ready-to-use test seeds straight from the scenario.
"I feel like we can finally build and improve the product properly."
After getting our problems diagnosed and next actions corrected through Hyper-Review and a founder consult, we pulled User Flow, Story Map, and test seeds all at once with Hyper-Scenario.
On top of that, the consult revealed our user-tracking infrastructure design wasn't properly in place, so we redid the dev design.
Building on that, we fully overhauled the UX/UI — and I feel like we can finally build and improve the product the right way.
"All the features were there — but no path to the core."
We built a commerce app. Product listing, checkout, delivery tracking — all the features were there. But of our signups, under 2% ever reached a purchase. I knew it was a flow problem, not a feature problem, but I had no idea where to fix it.
At this rate it felt like we'd just keep piling on features and getting more complex.
I put our design into Hyper-Scenario, and the full flow from first entry to purchase came out as a scenario. It showed exactly where users dropped before feeling the core value, and we redesigned onboarding based on the User Flow. We added zero features — just fixed the flow — and conversion went up.
You're not alone — the engines circulate.
One alone is valuable, but circulating keeps raising quality.
Review spots a gap → Research brings the evidence.
Reflect research into the design → Review re-checks it.
Scenario builds the user flow → Review checks scenario quality.
Coach reinforces the design → Review + Scenario + Research circulate again.
Connect
Paste a URL, log in. Done.
No API keys, no config secrets. Pick your tool, paste the prompt to your agent, and it connects itself. One login lasts 30 days.
Add the PurplePrint MCP to Claude Code.
Server name: purpleprint, transport: http, URL: https://purpleprint-mcp.purpleprintai.workers.dev/mcp.
Register it globally (user scope), and add alwaysLoad: true to mcpServers.purpleprint in ~/.claude.json
(this prevents /purpleprint:* slash commands from going missing in recent Claude Code IDE). If editing the file directly, save as UTF-8 no BOM.
Walk me through Authenticate in /mcp, and when done confirm that /purpleprint:start shows up. Add the PurplePrint MCP to this editor.
Server name: purpleprint, URL: https://purpleprint-mcp.purpleprintai.workers.dev/mcp.
Register it as a remote/http MCP in this tool's settings — globally (user settings, e.g. ~/.cursor/mcp.json or VS Code user settings), not just one project.
If an OAuth/authorize flow is needed, walk me through the browser login.
If commands don't show up, restart the editor or open a new chat/thread and check again. Add the PurplePrint MCP to Codex.
Server name: purpleprint, URL: https://purpleprint-mcp.purpleprintai.workers.dev/mcp.
Register it as a streamable HTTP MCP in ~/.codex/config.toml (shared by Codex CLI/IDE) and complete the OAuth login.
On Windows PowerShell, if codex.ps1 is blocked by the execution policy, run it as cmd /c codex mcp ...
When done, verify with codex mcp list. It's fine if /purpleprint:start doesn't appear in the / menu —
just confirm that saying "start PurplePrint" lets you use the pp_start tool. No coding tool? We're expanding reach — Antigravity·Lovable (coming soon), ChatGPT (Business+, exploring).
Connected but commands won't show or work? Restart the editor or re-authenticate. If stuck, run server-health to diagnose. Per-tool details in Docs.
What's different
Not a dumping AI — a coach that draws it out & verifies
Ask ChatGPT·Claude to "design it" and you get something plausible. But —
MCP in-flow
Everyone else is a separate web app. We work inside the Claude Code·Cursor·Codex you already use.
Coaching-to-spec (L3)
Plenty of discovery·validation·biz-plan tools. We fill the empty 'turn ideas into a service design that'll ship (L3)' with conversational coaching.
What we don't do
Stronger by leaving out
We don't tool-lock you
No direct OAuth into GitHub·Notion. Source-agnostic normalization.
We don't send your chat
Ideas·artifacts stay local. Only progress meta on the server (content-free).
We don't force a web app
No new tab, no signup — right inside the agent you use.
Pricing
One add-on, next to your AI subscription
List $20 · beta price
- 2-week free trial — no card
- Phase 0~9 coaching + Hyper-Review
- Builder level · my-growth analytics