Your programme
Get an update, find an accelerator, raise an opportunity
Your training
What you’re booked on, your agenda, how you’re getting on
Reading the operating model
Your unit tree, one unit’s portfolio, one process in full
Changing the operating model
Edit what you own, propose changes to what you don’t
Systems and AI estate
The tools you run on, and the AI you’ve actually switched on
Outcomes
Record and report the value AI has delivered
Your programme
kowalah_get_update
A single tool for any “how are things”, “what’s the status of X”, “what’s waiting for me” question. Pass an optional natural-language query; the server figures out whether you want a portfolio rollup, a focused view of a specific thing, or just your identity and organizations.
Pending discoveries in the home view
If Kowalah is running a Discovery and you’re on the audience, the home view includes apending_discoveries section with:
- The discovery number (e.g.
DISC-0003) and name - The goal, what Kowalah is researching
- The business value context, why it matters
- The close date, when the discovery stops collecting responses
- The project the discovery sits against (if any)
What a focused view returns
kowalah_find_accelerator
Searches Kowalah’s global accelerator library plus your organization’s private accelerators for a reusable prompt, GPT, training, or workflow.
Use this whenever you’re about to raise a request for help. There may already be something on the shelf you can take and run with.
kowalah_create_opportunity
The single inbound entry point for everything a customer wants to raise with Kowalah: a question, an idea, a piece of work to scope, a new project to consider. Anyone in your organization can submit, regardless of role.
You don’t have to decide whether the work is an Expert Request, a Deliverable, or a Project. Kowalah’s team triages from there.
Before submitting, Claude is expected to:
- Check the accelerator library for something that already solves the problem
- Make sure the description is at least a paragraph (~80+ characters of real context: goal, what good looks like, anything Kowalah should know). The server rejects anything shorter
- Capture an ICE score (impact, confidence, ease) with a reason for each
- Where your organization has an AI vision map, name the guiding principle the opportunity serves and the KPI it moves
- Ask which organization the opportunity is for (if you belong to more than one)
Linking an opportunity to a discovery
If you’re responding to a Kowalah discovery you’ve been invited to, Claude passes thediscovery_id through when it submits. The server then:
- Validates that you’re actually on the discovery’s audience
- Stamps the opportunity with the discovery and its project
- Marks your audience invite as responded so reminders stop
Your training
kowalah_get_my_training
Your own Kowalah training record: what you’re booked on, your agenda for the day, and how you’re getting on.
kind to choose the view:
This tool only ever shows your own training, matched to you by Kowalah account or email address. It never exposes other participants, their results, the cohort roster, trainer notes, or anyone else’s feedback.
org_overview is counts and averages with no named individuals and no free-text comments; everyone else asking for it gets a not-permitted note.If you’re enrolled but the tool says you aren’t, the training may be registered against a different email address. Contact your Kowalah team.Reading your operating model
These four tools give Claude your AI Operating Model: the map of how your organization actually works, and how much of it AI could support. Everyone in your organization can read the whole map, whatever their role.kowalah_get_operating_model
The world view. Returns your unit tree with coverage rollups on every node (coverage %, process count, redesign-gap count, constraint count, rolled up across each unit’s whole subtree), plus org-wide totals and a narratable summary.
organization_id only if you belong to more than one organization. If nothing has been mapped yet, the tool says so rather than returning an empty tree.
kowalah_get_operating_model_unit
One unit in focus: its subtree coverage rollup, the processes it owns directly (each with its own rollup), its child units, and the top redesign-backlog steps across its processes, ranked by constraint and coordination burden.
kowalah_get_process
One process in full, and the richest thing the connector returns. Includes:
- Process metadata: purpose, cadence, criticality, owners, owning unit
- Ordered steps with current to target dispositions, and gap and constraint markers
- The DEFINE contract on each step: acceptance criteria, input artifact, output artifact
- Per-step implementation links and per-step quality evals, with target versus current scores
- A process-level rollup and the ranked redesign backlog
- Inter-process connections, the handoffs and feeds touching this process
- Initiatives already aimed at it, the opportunities, deliverables, and projects linked to the process or to one of its steps
- The systems each step runs on, from your systems register, and the AI assets that run it
- Outcomes recorded on the process and its steps, with totals that keep claimed apart from verified, and one-off apart from recurring
- Notes: evidence, observations, decisions, and the open questions still to answer
- A diagnosis of how well the process is captured. A missing measurement reads as “can’t say”, never as zero: the cycle ratio (work time over elapsed time) only appears when every step is timed
access block telling Claude what you may do to this process, so it can offer the right next step rather than attempting an edit that gets refused. See who can change what.
kowalah_get_vision
Your organization’s AI vision map: the vision statement, its guiding principles with their defining attributes, and the success measures, with a baseline, a target, and a current reading where they’ve been set. Pass a unit to get the vision that unit inherits.
Changing your operating model
Reading the map is open to everyone. Changing it depends on where the thing you’re changing sits relative to you, which the connector resolves on every call. If you can’t edit something directly, the answer is never a dead end: it routes to a proposal.kowalah_save_process
Creates or updates a process. On create, the process number is allocated automatically and the owner defaults to the owning unit’s leader. On update, only the fields you provide change. You can re-parent a process to a different unit within the same organization.
kowalah_save_process_step
Creates or updates a step within a process. On create, position defaults to append and the current disposition defaults to human.
kowalah_save_process_step_eval
Creates or updates an eval on a step: the quality check that its output meets its acceptance criteria. This is how a business owner sets and tracks the bar, for example “what counts as a good forecast category call” or “what a compliant response looks like”.
- A gate blocks the step until it passes. It’s all-or-nothing and cannot carry a sampling percentage.
- A monitor observes a sample, and may set a sampling percentage from 0 to 100.
target_scoreis the bar;current_scoreandmeasured_atrecord the latest reading.
kowalah_save_org_unit
Creates or updates a node of your org-unit tree. For a child unit, pass a parent; the organization is inherited. Creating a root unit reshapes the top of the org chart and is restricted to admins and core team.
kowalah_save_process_connection
Creates, updates, or removes a connection between two processes: a handoff (“qualified deals pass to Proposal”) or a feed. Connections are what make the operating model a map of how work moves rather than a list. Because a connection touches both processes, you need edit rights on both ends.
kowalah_propose_redesign
Creates a to-be version of a process beside the original, so the two can be compared. It starts from the as-is and from the redesign decisions already marked on its steps: steps marked eliminate or merge don’t come across, and a step with no decision is carried rather than dropped. The original process isn’t changed, and you can put more than one option side by side.
kowalah_propose_process_change
The route when you can’t edit directly. Instead of changing the process, it files an Opportunity linked to that process, and optionally pinned to one step, so the owner can pick it up.
Who can change what
Your ability to edit the operating model is governed by your altitude: where the target sits relative to your home unit in the org tree. This is a different axis from your role, which governs what you can see.Admins and core team are cross-cutting editors within their own organization: they can edit and create anywhere in it. Being an admin in one organization confers nothing in another.If no home unit has been set for you, everything resolves to the safe default of read and propose. Ask your organization admin to set your home unit if you should be able to edit.
kowalah_get_process returns your resolved access up front, Claude can offer “shall I change that, or propose it to the owner?” rather than trying an edit and reporting a refusal.
Projects, deliverables, Expert Requests, contracts, and existing opportunities are read-only through the connector, whatever your altitude or role. Processes, steps, evals, units, systems, and AI assets are never deleted (steps, systems, and AI assets are archived instead). The only removals are narrow: a connection between two processes, an arrangement on a system (admins and core team), and an outcome, which is soft-deleted. Each is recorded in the model’s history.
Your systems register and AI estate
The systems register is the tools and platforms your work runs on, whether each has AI in it, and how your organization holds it. The AI estate is what has actually been built and switched on in them: connectors, skills, plugins, projects, agents, automations, and apps. Everyone in the organization can read both.kowalah_get_systems
Every system with its arrangements: the ways your organization holds it (tier, seats, who the contracting party is, whether there’s a DPA, whether it trains on your data, admin control, audit trail, and sanctioned status). One system often has several, for example a company plan alongside personal plans people pay for themselves.
kowalah_save_system
Adds or updates a system and its arrangements. Admins and core team only. Kowalah’s shared catalogue systems can’t be edited, but you can record your own arrangements on them. A field you leave unset means “not assessed”, which is different from “no”.
kowalah_get_ai_estate
Every AI asset recorded, with its platform, owner, status, scope, who has used it and where, the process steps it runs, and the outcomes it produced. It leads with the gaps: assets with no owner, undecided ones, ones nobody has used for 90 days, connectors that can act with nobody approving, people holding a lot of connections, personal assets, and shadow AI running on a platform your organization hasn’t approved.
kowalah_record_ai_assets
Records the AI tools someone’s Claude session uses, and what they say about each one. Claude shows you the list before saving, and records only what you agree to share.
Only names and identifiers are recorded: never a skill’s instructions, a prompt, a tool description, or a project’s contents. Anyone can mark something as their own personal asset; admins and core team decide everything else about an asset.
Outcomes
kowalah_save_outcome
Records realised value, such as time saved, cost reduced, revenue won, or an adoption milestone, on any work: a process step, a process, a unit, an opportunity, the whole organization, or a Kowalah deliverable or Expert Request. An outcome can say which AI asset produced it and which vision measure it counts towards.
- Anyone can record an outcome. It’s recorded as a claim, with how the figure was arrived at: estimated, sampled, or measured.
- Admins and core team can verify an outcome, in their own name. Changing a verified figure makes it a claim again.
- A figure carries a comparable unit (hours, count, percent, or a currency) so outcomes can be added up.
- Removing an outcome is a soft delete.
Confirmation before changes
Tools that change or remove existing data are marked as destructive, so Claude asks you before running them: the foursave tools for the operating model, process connections, the systems register, the AI estate, and outcomes. Tools that only add something new, such as raising an opportunity, proposing a change, or proposing a redesign, run without that extra step.
Prompts
The connector also registers a few prompts you can pick from Claude’s prompt menu (the ”+” attachment or slash menu, depending on which Claude client you’re using). Some are role-gated.
Members don’t see Programme update or Expert Request credits and quota in the prompt menu. They’re only registered for privileged roles.
Resources
Alongside tools, the connector exposes your accelerators, opportunities, projects, deliverables, and Expert Requests as MCP resources, so Claude clients that support resource browsing can attach them to a conversation directly. Resources are filtered by exactly the same rules as the tools, and the filter is re-checked on read, so a hand-typed identifier can’t bypass it.What your role changes
Role governs visibility. Altitude, above, governs editing.
A
no_match response for a known reference number usually means the item exists but you’re not permitted to see it, not that it doesn’t exist. This is most common for members who aren’t on the stakeholder list for a given project, deliverable, or Expert Request.
A few things are different:
- Discovery invites are personal to you, so you always see your own pending discoveries regardless of role.
- Training is personal to you: everyone sees their own record only, and only admins and core team can pull the anonymised org rollup.
- The systems register is readable by everyone, but only admins and core team can change it or see its commercial fields.
- Outcomes can be recorded by anyone, and verified only by admins and core team.
Data filtering
The connector enforces visibility on the server side:- Organization scoping, only data from organizations you belong to is ever returned
- Role-based filtering, members only see what they raised or are a stakeholder on
- Altitude gating, operating-model writes are checked against your position in the org tree, after org scoping
- Client visibility flags, tasks, risks, and decisions are filtered to client-visible items
- Discovery audience gate, opportunity submissions tagged with a
discovery_idare rejected if you’re not on the audience - Identity scoping, training data is matched to you personally by account or email
- Field filtering, internal fields (Kowalah team assignments, contract values, payment details) are not exposed, and Kowalah-side ownership can’t be set by a client even on records you create
Set up in Claude
Add the connector to your Claude workspace
Work your operating model in Claude
Map, review, and improve processes in conversation
Roles and permissions
Full role reference
Security and data access
How the connector is scoped and gated