Skip to content
Pyrana

Glossary

Defined terms

Words the site uses with a specific meaning. Across the site, the first use of a term on a page is underlined and links here.

Absent, not refused
How the platform answers for what a caller may not see: the item is missing from results and a direct request resolves as not found. Nothing in the response reveals that the item exists.
Where it is explained
Access profile
What a member of an App may do: read, run, approve. Combined with a scope entitlement it becomes one grant.
Where it is explained
Agent Studio
Where agent configuration is authored within the platform's guardrails. Skills brought from elsewhere are re-run through it.
Agentic application (App)
A full-stack business application in which people and agents work over the same pages, data, knowledge, and outputs, under one identity, one authorization model, and one audit record. On Pyrana an App is configuration on a platform that is built once.
Where it is explained
App configuration
The one configuration that declares an application: its surfaces, targets, agents, workflows, tool sources, resources, access, and knowledge. Compiled into an immutable, content-digested version; activated by moving one pointer.
Where it is explained
Application state
What no existing system holds: plans, decisions, reviews and exceptions. Kept by the App's own extension service, in the same cluster and behind the same gate, with its own records and history.
Where it is explained
Approval lane
A named group or relation (the requesting user, a finance group, a workflow, a tool relation) that receives an independent obligation to approve. Reviewer eligibility is checked at decision time.
Classification
How carefully a Context Unit may change: absolute (never auto-changes), regulated (needs a human), contextual, tribal (conflict-checked), derived (updates itself).
Where it is explained
Colleagues' results
In a workflow, the published results of the agents an agent waited for, for the same entity or the entities below it. They reach the agent as files.
Connections
How Pyrana reaches the systems a company already runs, and replaces none of them: APIs, databases, MCP tool servers, files and drives. A connection acts as the signed-in person or as a service identity, and its writes can be held for approval.
Where it is explained
Context engine (cortIQ)
The layer that holds company knowledge as typed, classified, evidence-backed Context Units in a knowledge graph, retrieves them for agents, and accounts for what each run retrieved, injected, and cited. cortIQ is Pyrana's context engine, formerly the Context Engine.
Where it is explained
Context Unit (CxU)
The unit of knowledge in cortIQ: one atomic claim, its verbatim supporting passage with source and location, a knowledge type, a classification, an evidence grade, a quality score, and an identity that is a content hash.
Where it is explained
Copilot
The App's assistant, auxiliary to its pages: it answers questions about what is on screen with the same authorization as the person, and it is the pathway to personal pages. Not the primary interface.
Door
How a call arrives: the App's own pages, the copilot, the API, MCP from another agent, a schedule, or an external event. Every door leads to the same gate.
Durable execution
Work that survives waits, restarts, and deploys. Workflow lanes run on Temporal workers and resume from a checkpoint after any interruption.
Where it is explained
Engine-side agents
Agents inside the context engine: a query agent that plans the graph walk and repairs its own queries, and a learning agent that scores what was retrieved and used and flags units that never help.
Execution record
The one record every call leaves: caller, App version, target, resource versions, authorization outcome, approvals, effects with receipts, and the context cited. Written before dispatch.
Where it is explained
Extension
A client-owned durable backend service deployed in the same cluster, built with the platform library that handles authentication and authorization, reachable only through the platform. Used for custom business logic and storage.
Where it is explained
Finish checks
The rules an agent must pass before it may finish: required outputs, their shapes, data actually pulled. If a rule fails the agent is told what is missing and goes back to work; if its steps run out first, the run ends as failed, not as a finished result.
Where it is explained
Frozen invocation
The immutable proposal a reviewer approves: the operation, its exact arguments, scope, and evidence, under a hash. The waiting agent cannot alter it; it is revalidated before it dispatches once.
Governed loop
The six steps every agent runs inside the Pyrana Harness: admit, plan, act, observe, validate, publish. Plan, act and observe repeat until validate accepts; the configuration decides what the agent knows, what it may use and when it is done.
Where it is explained
Helper agent
A named sub-agent that an agent hands part of its work to. A helper runs its own governed loop under the same access and the same record.
Knowledge type
What kind of claim a Context Unit is: axiomatic, empirical, prescribed, or procedural.
Where it is explained
Lane
An execution mode in the Pyrana Harness: direct (deterministic, no model), agent, workflow (durable), batch, or event.
Where it is explained
MCP
Model Context Protocol. Every App exposes an MCP server, so any agent (Claude, ChatGPT, a client's own) can work with the App as the user, under the user's own authentication and authorization.
Named data call
A query or an API call written and tested ahead of time; the agent fills in the parameters only. It declares whether it reads or writes, runs only against approved addresses, caps its rows, and publishes its result next to the analysis, unchanged.
Where it is explained
Numbers by code, words by agents
The figures people rely on are computed by tested code the agents call, named data calls and scripts. The agent reads the result and writes the words, citing the figures it used.
Where it is explained
Page context
What the platform hands the agent about the page a person is on: which page, which entity, which period, which resource versions.
Personal page
A page a person asks the copilot for. The copilot authors it from the resources and read capabilities the person may use; the backend compiles it with no network, imports, storage, or authority; the browser renders it with every read still authorized. Read-only by default.
Where it is explained
Playbook
Guidance an agent reads when it needs it, instead of carrying it in the prompt: how a kind of work is done, with examples. Versioned with the agent's configuration.
Push, activate, deploy
Push compiles the App configuration into an immutable version and registers the App identity. Activate moves the active pointer, is audited, and requires an App owner; rollback is an activation of a prior version. Deploy ships a frontend image and registers and activates nothing.
Where it is explained
Pyrana Harness
The runtime and orchestration layer: native tool calling, planning, subagents, checkpoints and resume; durable workflows that fan out, wait, retry, and finish.
Where it is explained
Resource
A versioned, immutable, attributed output of an App: v1 published by a run, v3 revised by the copilot on behalf of a person. Publishing against a stale version is refused. Pages read a resource at an exact version.
Scope entitlement
The slice of data a caller's profile applies to: an entity, a project, a review queue. What a caller may not see is absent from results, not denied.
Skill
Reusable know-how shared across agents and loaded on demand, in sections, when an agent's plan calls for it.
Standing set
A set of Context Units preloaded before an agent's first turn, for example an entity's policies.
Surface
A declared page where a person works. The platform knows what the person is looking at and hands it to the agent as exact page context.
Target
An operation the App can perform, declared once and reachable from many doors through one gate.
The gate (admission)
The eight-step check every call passes before anything runs: identity and idempotency key; active App version; target exists and caller allowed; references resolved to exact versions; one authorization check; execution row and audit record written in one transaction; dispatch; outcome recorded. Fails closed.
Where it is explained
The platform picture
The one-page architecture of the platform: twelve blocks, from cortIQ and connections through agents, workflows, applications and application state, to models, hosting, observability, build and release, with security and governance around every block.
Where it is explained
Tool approval policy
A rule over an operation's typed arguments (thresholds, membership, existence, compound rules) that decides whether a person must approve before it runs.
Where it is explained
Tool source
A connection an App binds to: REST, ODBC, MCP and MCP gateways, Databricks, Snowflake, Google Drive, OneDrive. Tools are specific to the job; the agent passes the entity and the period, the tool holds the query.