MCP-native · works with claude.ai, Claude Desktop & Cursor

Your AI already thinks like a top-tier consultant. Give it the strategic memory to act as your chief of staff.

Hoshin Kanri is the strategic memory all your agents share: one living X-Matrix — objectives, initiatives, KPIs, decisions, review cadences — readable and writable through MCP. Your CEO's Claude, your CFO's Cursor, your consultant's agent: same truth, each with their own rights, every action audited. And the agents keep it alive, week after week.

claude.ai — hoshin-kanri + linear

You /weekly_sync

Weekly Sync — Mon 09:00

4 initiatives read, 3 linked to Linear

→ « Onboarding revamp » : 68%, 2 blocked issues

1 Linear project maps to no initiative — strategy drift?

Proposed weekly agenda: 2 KPIs off-track, 1 pending decision…

The strategy matrix in Miro or Excel: made once, never reopened.

Every leadership team knows the artifact: the X-Matrix built in Miro or Excel, where formatting took more time than the strategic thinking, frozen the day it was presented. Meanwhile the agents arriving in your company run on the opposite excess — piles of unstructured context: markdown files, RAG dumps, chat history. Abundance of unstructured context is the enemy of agentic efficiency. Toyota solved this problem for humans sixty years ago: policy deployment — one bounded, correlated page from vision to daily work. That proven frame is exactly the structured context agents need: light enough to hold entirely, auditable, and alive because agents update it every week.

One strategic operating system, three forcing functions

A framework that forces coherence

The X-Matrix: 3-5 year objectives (North), annual objectives (East), initiatives (South), KPIs (West) — linked by correlation strength in all four corners. Nothing enters the strategy without earning its place in the chain. Board-ready, exportable — and compact enough for an agent to hold entirely in context.

Rituals that force follow-through

A 5-level meeting hierarchy from strategic reviews to daily stand-ups. Agendas, action items and decisions traced from vision to daily work — the catchball, structured. The review is where strategy deploys or dies.

A score that forces honesty

5 computed metrics — coverage, correlation density, orphans, vision-to-KPI chains, leading/lagging indicator balance. One number that answers the only question that matters: would this strategy survive contact with reality?

How Hoshin Kanri works — five steps, one page

Policy deployment aligns your 3-5 year vision with daily actions. Here is the loop — and what your agent does at each step.

  1. 1

    Set the direction

    3 to 5 breakthrough objectives for the next 3-5 years — the North of the X-Matrix. Few enough to mean something.

    Your agentturns notes and ideas captured mid-conversation into candidate objectives in the idea inbox.

  2. 2

    Cascade into annual objectives

    What must be true this year for the vision to stay credible (East). Negotiated with the teams — the catchball — not decreed.

    Your agentchecks every annual objective actually supports a long-term one, and challenges those that support none.

  3. 3

    Deploy initiatives and KPIs

    Improvement initiatives (South) and the indicators that will prove they work (West) — an owner on every row.

    Your agentflags orphan initiatives, unmeasured objectives and a lagging-heavy KPI set via the completeness score.

  4. 4

    Review on cadence

    A 5-level meeting hierarchy, from strategic review to weekly sync. The review is where strategy deploys or dies.

    Your agentprepares each agenda: pulls progress from Linear or Jira, updates statuses, lists off-track KPIs and pending decisions.

  5. 5

    Adjust and learn

    Decisions traced, initiatives re-arbitrated, the matrix kept alive — hansei, the reflection that closes the loop.

    Your agentdiagnoses how deeply each strategic theme is deployed and proposes arbitrations for the next cycle.

Plug in your AI. Get a chief of staff.

Hoshin Kanri ships an MCP server with OAuth 2.1: connect it to claude.ai, Claude Desktop or Cursor in two minutes, next to your Linear or Jira MCP. Every teammate connects their own assistant — your consultant too: same matrix, each with their own rights, every action audited. The agent stops being a chatbot: it reads objectives, checks initiatives, tracks KPIs, prepares reviews, flags drift — a collaborator, applying one simple rule:

Strategy, reviews and KPIs → Hoshin Kanri. Tasks, issues and sprints → your execution tool.

11 MCP tools · 9 guided prompts · idea inbox, deployment diagnosis, boardroom artifacts, public share links. Enterprise: federate it behind your company's Cortex Gateway as the steering backend, next to your business apps.

The weekly_sync prompt, built in

  1. 1Reads your initiatives and their linked execution projects (external_ref)
  2. 2Pulls progress and blockers from Linear or Jira through their MCP
  3. 3Updates initiative statuses and flags strategy drift — untracked work, unlinked initiatives
  4. 4Prepares your weekly cadence agenda: off-track KPIs, blocked initiatives, pending decisions

Clear boundaries, by design

Why & What

Objectives, initiatives, KPI targets, correlations, reviews, decisions

Hoshin Kanri
How

Projects, issues, sprints, assignments, daily tracking

Linear · Jira · Asana
How much

Measurement data, dashboards, time series

Your BI stack

No task management, no Gantt charts, no daily notifications. Ever. That work belongs to tools that do it well — your matrix just stays linked to them.

Per organization. Not per seat.

A steering tool has 5-10 active users — pricing by seat punishes adoption. Every paid tier has a 30-day free trial, no credit card.

Early access: everything is unlocked during the beta — and early adopters keep an advantage when billing starts.

Solo

€0forever
  • Local mode: your data stays on your machine (JSON, zero infra)
  • Cloud: 1 matrix, 2 users
  • Read-only MCP
Start free

Team

€89/month per organization
  • Unlimited matrices, 10 users
  • Cadences, themes, action items
  • Completeness score
  • Full MCP: OAuth, weekly_sync, all tools
  • Exports
Start 30-day trial

Partner

€290/month — 3 client organizations included
  • Then €49/month per additional client
  • Unlimited matrices per client
  • Light white-label (client logo)
  • Assisted onboarding
  • Clients can graduate to their own plan, with their data
Become a founding partner

Enterprise

from €500/month
  • Multi-site, SSO
  • Extended audit trail
  • SLA & deployment support

Frequently asked questions

What is a Hoshin Kanri X-Matrix?

The X-Matrix is the central tool of Hoshin Kanri (policy deployment), a strategic planning method from lean management. It aligns four quadrants on one page: 3-5 year strategic objectives (North), annual objectives (East), improvement initiatives (South) and KPIs (West), with correlation marks showing how each level supports the next. It makes the chain from vision to daily work visible — and auditable.

How is this different from OKR software?

OKR covers one layer: quarterly objectives and key results. Hoshin Kanri adds the 3-5 year direction, explicit correlations between levels, the catchball process and a meeting-cadence system to review it all. If you run OKRs, the X-Matrix maps cleanly onto them — East as Objectives, West as Key Results — with the long-term layer OKR lacks.

Why does strategy execution fail?

Rarely for lack of ideas. Strategy execution fails because objectives change without being re-cascaded, projects drift away from priorities, KPIs stop being reviewed, and each department works from its own version of the plan. Hoshin Kanri attacks each failure point: the X-Matrix keeps the vision-to-work chain explicit, review cadences force the follow-through, and the completeness score exposes the gaps before reality does.

Is this an AI strategy consultant?

No — it is the harness that makes one trustworthy. Frontier models already reason at consultant level; what they lack is structure and follow-through. We provide the proven framework (the X-Matrix), the rituals (review cadences) and the audit (completeness score); your AI provides the thinking. Together they behave like an executive right hand that never lets an idea escape unmeasured — and never hallucinates a strategy outside the frame your team negotiated.

Can Claude or ChatGPT act as an AI chief of staff?

Yes — with a frame. On its own, an LLM forgets your strategy between sessions and cannot verify what actually happened. Connected to Hoshin Kanri through MCP, the agent keeps a permanent strategic memory: it knows why each initiative exists, which decision created it, which KPI it influences, and when it must be reviewed. It no longer just gives ideas — it prepares your reviews, flags drift and proposes arbitrations, week after week. That combination — reasoning from the model, memory and governance from Hoshin Kanri — is the job of a chief of staff.

Why not just give my agent markdown files or RAG?

Because abundance of unstructured context is the enemy of agentic efficiency. A pile of documents forces the model to guess what is current, what is priority, and how items relate. The X-Matrix is the opposite: a bounded, correlated structure — every objective, initiative and KPI explicitly linked, with statuses and owners — small enough for an agent to hold entirely, precise enough to act on. The format is not new: it is Toyota's policy deployment matrix, sixty years of proof that one structured page can steer a company. Structure is the context engineering; the matrix is the format.

What is MCP and what do AI agents actually do here?

MCP (Model Context Protocol) is the open standard that lets AI assistants like Claude use external tools. Hoshin Kanri ships an MCP server: an agent can read your matrix, capture ideas mid-conversation, update initiative statuses, diagnose how well a strategic theme is deployed, and run a weekly sync against Linear or Jira. You connect it to claude.ai with OAuth in about two minutes.

Does it replace Linear, Jira or Asana?

No — by design. Your execution tool keeps the tasks, sprints and issues. Hoshin Kanri keeps the strategy: objectives, initiatives, KPIs and reviews. Each initiative carries a link (external_ref) to its execution project, and the weekly_sync agent prompt keeps the two aligned without double data entry.

Can I use it for free?

Yes, two ways. The cloud Solo tier is free: one matrix, two users, read-only MCP. And the local mode is entirely free and infrastructure-less: your matrix lives in JSON files on your machine, readable by Claude Desktop via MCP — nothing leaves your computer.

Is my data isolated and where is it hosted?

Every query is scoped to your organization (strict multi-tenant isolation), API tokens are stored hashed, access is auditable, and OAuth 2.1 with PKCE secures agent connections. Data is hosted in the EU.

Give your AI the rigor of a chief of staff

Agents know how to execute. Hoshin Kanri tells them what to do, why, in what order — and how to measure success. Free to start, two minutes to connect Claude.

Create your X-Matrix