For developers and configurators

Build the workflow, then see exactly how it runs

Pūnaha gives you visible building blocks for knowledge, models, connections, access, workflows, BPMN-based processes and CMMN-based cases. You can validate a definition, publish a controlled version and inspect the running work through the browser or API.

Developers combine named knowledge, model, connection and access resources into a workflow, process or case, validate and publish a controlled version, then execute and inspect its state, events and results.

Building blocks

Pick the building blocks the job actually needs

Knowledge stores

Create tenant-aware vector databases, ingest supported documents and choose semantic or hybrid retrieval for the query pattern.

Model deployments

Manage local GGUF models and supported external providers separately from the workflows that refer to them.

Visual workflow modules

Configure triggers, AI, knowledge, logic, people, documents, connections, messages, waits, batches and reusable workflows in the visual builder.

BPMN-based processes

Model, validate, import, export and execute supported BPMN activities, events, gateways, data and subprocesses.

CMMN-based cases

Design case files, stages, plan items, sentries, planning tables, lifecycle and CMMNDI layout for adaptive work.

Resource access

Assign exact actions for named resources to people, groups and services, then inspect the effective decision.

Explore access governance

Execution evidence

Inspect workflow and case state, append-only events, approvals, human work, audit history and operational logs.

Workflow module palette

Keep provider-specific logic out of the process where you can

Data and rules

Transform values, validate a supported JSON Schema subset, route conditions and evaluate FIRST, UNIQUE or COLLECT decision tables.

Human work

Configure approvals and assigned or role-based human tasks with priority, due time, overdue behaviour and completion shape.

Controlled documents

Extract and split text, redact configured patterns, classify from explicit categories, render templates and create portable file outputs.

Knowledge updates

Queue text into the existing ingestion pipeline with the target database, file metadata and replacement strategy.

Durable messaging

Publish and receive local queue messages, then acknowledge, retry with delay or move them to a dead-letter state.

Schedules and evidence

Use one-time, interval or time-zone-aware cron triggers and record digest-backed evidence checkpoints at important boundaries.

Interfaces and resources

Know which surface you are working with

Developer-facing product surfaces
SurfacePurposeBoundary
Browser applicationConfigure, publish, run and inspect product resourcesPermissions and active licence determine what is visible and allowed
OpenAPI 3.1Inspect and call the routes enabled for the running service setThe document is generated from the services actually enabled
ConnectionsConfigure HTTP, email, Microsoft 365, supported databases and model endpointsCredentials are encrypted; provider and live-environment validation remain explicit
BPMN and CMMN filesExchange supported process and case definitions with diagram informationExternal references require mapping; no formal conformance claim is made
Audit and execution eventsUnderstand changes, permission denials and run behaviourSensitive inspected content is not copied into protection-event metadata

Access and service boundaries

Make the caller, resource and action explicit

A working route is only useful when the right person or service can call it for the right reason.

Resource and action

Authorise an exact action against a named workflow, case, knowledge store, model, connection or other governed resource.

People, groups and services

Use individual users, local or mapped external groups, and explicit service identities.

Explain the result

Inspect the roles, group membership, grants, denials and time boundaries that produced effective access.

Enabled API surface

The generated OpenAPI document reflects the service groups enabled for the running process rather than advertising routes that are not active.

Private service calls

Separated workflow and AI services use an explicit private contract and service access instead of treating internal traffic as automatically trusted.

Connection boundary

Keep provider settings in named resources, then validate the intended target with the customer's network and account.

Explore connections

Conceptual configuration

Let the workflow describe the job, not a particular provider

This small example shows how named resources relate to a workflow. It explains the shape of the configuration; it is not a copy-and-paste API contract.

A published workflow can refer to knowledge, model and connection resources while preserving its own purpose and version. That separation supports deliberate operational change without rewriting every process.

Illustrative workflow resources
workflow: policy-review
version: 4
trigger: weekday-schedule
steps:
  - retrieve: policy-knowledge
  - validate: required-evidence
  - decide: review-routing
  - human-task: subject-matter-review
  - evidence-checkpoint: approved-decision

Delivery lifecycle

Take a draft into operation without skipping the awkward tests

  1. Configure dependencies

    Set up the knowledge, models, connections, roles and storage destinations required by the design.

  2. Model and validate

    Build the workflow, process or case and resolve structural, mapping and permission issues.

  3. Publish an immutable version

    Create a clear operational boundary that running work can remain pinned to.

  4. Exercise success and failure paths

    Test waits, retries, unavailable services, rejected human work and restart behaviour before wider use.

  5. Inspect and improve

    Use execution events, audit history and operational logs to understand behaviour before publishing another version.

What developers tend to ask first

Is the public website built with a JavaScript framework?

No. The Pūnaha public website uses generated HTML, CSS and small amounts of framework-free JavaScript. The local website editor is separate and is not deployed.

Does Pūnaha expose API documentation?

Yes. The Pūnaha executable serves an OpenAPI 3.1 document and embedded Swagger UI. The documented routes reflect the service groups enabled for that running process.

Can workflows use different model providers?

Yes. Workflow steps refer to configured model deployments, which separates workflow intent from the local or external provider connection.

Can access be tested before a user opens the resource?

Yes. The effective-access view explains whether the requested action is allowed and which roles, groups, grants, denials and timing rules contributed.

Are BPMN and CMMN standards formally certified?

No certification or formal conformance claim is made. Pūnaha provides BPMN-based and CMMN-based modelling, validation and supported interchange, while independent review and external-tool evidence remain separate release requirements.

Bring a workflow your developers can challenge

We can walk through its resources, modules, standards and execution path, including the places where you expect it to fail.

Pūnaha app icon

Install Pūnaha

Keep Pūnaha close at hand

Use your browser’s installation option to add Pūnaha to this device.

  1. Open your browser menu.
  2. Choose Install app or Add to Home Screen.