Docs

User Guide

Temporality observes how an AI agent works: what it knew and did, where its knowledge came from, what held up — and returns verified experience to later runs. This section is a practical guide, from installation to everyday work.

Getting started

IntroductionWhat Temporality is, who it is for and what it is made of — a ten-minute overview of the system. Quick startFrom zero to your first agent task — installation, onboarding, the first run.

Working with the agent

Chat and runsDialogue with the agent — from a message to a result: streaming, amendments, approvals, delegation. Agents and teamsCreating and configuring agents — models, tools, sandboxes, evolution; agent teams as pipelines.

Knowledge and experience

KnowledgeHow the agent accumulates experience — the knowledge lifecycle, the area map, dossiers, contradictions, bitemporality. Observability and storageThe dashboard, run traces, the experience timeline and the sandbox file storage. SkillsLiving skills — reusable agent procedures with a contract, versions and quality evaluations. ArtifactsA registry of documents with human approval — coding policies, requirements and instructions agents can trust.

Automation

Inbound and channelsConnect Matrix, Telegram, Slack, Mattermost and webhooks — the agent receives tasks from your team's chat.

Knowledge and experience

PersonalizationFacts about people — how agents remember senders' preferences and roles, where it works, and what it is not.

Automation

TriggersStart agents on a schedule, by webhook or on system events.

Administration

AdministrationUsers and RBAC, the org structure, providers, secrets, sandboxes and quality settings.

Integrations

External agents (experience layer)How to wire any framework or pipeline into the experience loop — events, knowledge extraction, hints.

Administration

Org structure, users and policiesThe department tree, roles and grants, projects and visibility. Org Policies — every dimension, inheritance and the run's effective policy.

Reference

ReferenceEnvironment variables, ports, UI pages and links to the in-depth documents.

Operations

Harness OperationsHow to deploy, configure and operate Temporality as a working harness — the stack, upgrades, providers, authentication, knowledge, skills, sandboxes, observability, backups and troubleshooting.

Working with the agent

Forms & approvalsHow the agent asks a human structured questions — cards in the chat, a button in your messenger, a browser form behind a one-time link — with server-side validation. FilesHow the agent hands files to a human — into the chat, into your messenger — and where to pick them up. Evolution & qualityHow agents propose changes to their own configuration, how the evaluation gate verifies the effect, how to roll a version back — and where evaluation cases come from without hand-writing them. Job titles & groupsA job title is the natural group address — invite every QA engineer to a call, or send the new instructions to all developers.