IceShore
Configuration management for engineers who build and maintain systems with AI

Your AI gets better
at system maintenance.

IceShore gives your AI what each system does for the business — its use cases.

VALUE

Bind your AI-grown systems, with AI.

IceShore guides your AI to write down what each system does for the business — its use cases — then hands them back. Your AI answers the business impact of a change and how far it propagates.

We want to overhaul the delivery-tracking system. Which parts of the business does it affect, and how many users in total?
It hits all four use cases. Device Location Stream Ingestion / Real-Time Parcel Tracking Query / Periodic Route Optimization Batch / Device Registration & Metadata Management. 250,000 recipients + 500 drivers + 20 operators = 250,520 people. All four converge on DynamoDB MetadataTable.
Got it. Let me check the architecture.
Sample architecture "Parcelyon delivery tracking" detail: the use cases your AI read, the architecture it understood, and the three comprehension axes Correct your AI's understanding Review your AI's understanding Verify the raw data the AI wrote Your AI's understanding, visualized
Check and correct your AI's understanding on the auto-generated architecture.
Let me look at the related systems too.
Sample workspace overview: the systems your AI has mapped, and how well your AI understands them (configuration-management outcomes) AI understanding status The systems your AI has mapped
Check your AI's understanding across the systems you own, and close the gaps in maintenance.
WHY NOW

Maintaining systems now takes AI.

Silhouette of human evolution, from ape to upright human
84%of developers use AI tools ('25)
20MGitHub Copilot total users
+45%disclosed vulnerabilities per year ('25, record high)
The unmaintainable system monster that ever-growing code creates

Ever-growing code

Copy-pasted lines went from 8.3% to 12.3%, duplicated blocks up 8x. Refactoring fell from 25% to under 10%.

Source: GitClear 2024

Dependencies and risk you can't see

Nobody can tell what a change hits. Systems sprawl, and finding them at all becomes the problem.

Source: Backstage / large-scale reports

Not enough time

Developers spend 58% of their time on comprehension, and 42% of the week dealing with technical debt.

Source: Microsoft research / Stripe

“What does this system actually do for the business?” No amount of code analysis will tell you — it was never written in the code. IceShore has your AI write it down as use cases and hands them back, adding depth and edge to your judgement.

HOW IT WORKS

How IceShore works.

Your AI
You
IceShore
Inject business context(via MCP)
Visualize AI's understanding(via the website)
Answers you can trust

Startup CTO or tech lead

Situation

A small team shipping fast with AI, and running everything it ships.

Challenge

Hand maintenance to the AI and the answers ignore business impact and dependencies.

With IceShore

With the use cases in hand your AI answers precisely, and you keep your pace.

Enterprise dev or IT manager

Situation

Every department built its own tools with AI. You need the org-wide view.

Challenge

Change impact is unreadable, so the inventory stalls and the approvals stall with it.

With IceShore

AI answers impact questions across the org, and sharing hands over no credentials.

SI or consultancy architect

Situation

You maintain and extend legacy systems you inherited or someone else built.

Challenge

No docs, no original authors. Ask the AI and it misses what the system is for.

With IceShore

Your AI drafts the use cases from your docs and code; you correct them and teach it back. Past projects stay available.

How your data is handled

  • Inference happens on your AI. IceShore never sends your content to a generative AI.
  • Credentials are masked before they are stored. Access keys, private keys, connection strings and passwords are detected, redacted and logged.
  • Connections use OAuth 2.1 + PKCE. MCP is authorised with signed access tokens.
  • You can read exactly what the AI wrote. The History tab opens each saved file version by version, down to the diff against the previous one.
  • Hosted in the AWS Tokyo region. Stripe processes payments; we never hold card data.
Privacy statement→

What you can check for yourself

  • The data format is public. An architecture is a text file in ADL (Architecture Description Language). The language spec and schema are published on GitHub under Apache-2.0, so what you export stays readable outside IceShore. Spec and schema→
  • The setup steps are public. Claude Code, Claude Desktop, Codex, Cursor, Cline, GitHub Copilot and Windsurf, each with config you can paste as-is. Connect→
  • You can see the running thing without signing up. The screenshots on this page are the real sample workspace. You can open the same one. Open the sample→
PRICING

Start free. Bind it together as a team.

Solo stays free. The more of the team uses it, the deeper your AI's understanding grows.

Ramping up just one new hire faster already avoids opportunity cost in the tens of thousands of dollars (our estimate: the new hire's salary x 1.5 months, plus the salary of the existing members supporting them).

Free
$0
  • For one person (no member invitations)
  • Create architectures (unlimited), used from your own AI over MCP
  • Change history and diffs
  • Guest viewers (up to 3, view only)
Try without signup
Business
$39/ seat·mo (excl. tax)
Customers in Japan are billed in JPY: 6,000 JPY (6,600 JPY incl. tax)
  • Everything in Team
  • Look back 12 months of audit log (the last 30 days on Free and Team)
  • Download the audit log as CSV
  • Bulk member updates (CSV upload)
  • Access rights list CSV export (with approval date & last sign-in)
Start 14-day free trial

Prices are in USD and exclude tax. Customers in Japan are billed in JPY (3,000 / 6,000 JPY per seat·month, excl. tax), with Japanese consumption tax added.
Team and Business begin with a 14-day free trial (one seat, no card required; it reverts to Free afterwards with no automatic charge).
A seat is one paid place in a workspace (equivalent to one licence or one user seat elsewhere). Guests don't use a seat, so they cost nothing. On Free they can view; commenting starts on Team.
Both Team and Business start at one seat. For larger rollouts or specific requirements, email support@iceshore.ai.

FAQ

Frequently asked questions

Is my code sent to an AI?

IceShore never sends your content to a generative AI. Drafting and answering both happen on the AI you already use. IceShore acts as an MCP server, returning architecture information when your AI asks for it.

Where is my data stored?

In the AWS Tokyo region (ap-northeast-1). Stripe processes payments and we never hold card data. The details are in our privacy statement.

What if a config file contains credentials?

They are detected and masked before anything is stored. Access keys, JWTs, private keys, connection strings and password or token values are covered, on both the in-app save path and the MCP save path. Every detection is recorded.

Can I verify what the AI wrote?

Yes. In the History tab of your own architecture (editor or above), each saved file opens version by version, down to the diff against the previous one. Every version records whether it was written by the AI over MCP or edited by a person.

Which AI can I use it from?

Any AI client that speaks MCP. Authorisation uses OAuth 2.1 + PKCE with signed access tokens, so you are not locked to one AI vendor.

How far does the free plan go?

Free forever for a single person. Creating architectures, connecting over MCP and change history are all included. Paying starts when you invite members to work together. On the Free plan after a paid plan has ended, the members you already had can view and export the architectures, but no one can edit them.

What happens when I cancel or change seats?

Cancelling keeps your access until the end of the current billing period — nothing is cut off immediately. After that the workspace switches to the Free plan: you can still view and export your architectures, but no one can edit them. Members stay. You cannot invite anyone new, and any share link already issued stops working. Subscribing again restores editing. Adding or removing seats is prorated at that moment (increases are billed immediately; decreases are credited against your next invoice — they are not refunded).

Do you issue a Japanese qualified invoice?

Yes. We are a registered invoice issuer in Japan (registration number T7010001137750, Launchers Co., Ltd.). Invoices carrying the number are available in the app under "Invoices & payment method". The payment receipt emailed after checkout does not include it.

VISION

Toward a world where humans and AI behold the same ice field, and walk together.

The age of AI-grown systems, multiplying without end. The countless systems we've created drift on like ice floes. IceShore wants to be the icy shore that gently moors them together, with AI.