# LumenFlow documentation > Public product documentation for LumenFlow. Full article bodies: [llms-full.txt](https://lumenflow.cloud/llms-full.txt). ## Getting Started - [What is LumenFlow?](https://lumenflow.cloud/docs/what-is-lumenflow): LumenFlow is the governed agent runtime and control plane for AI work. Agents on LumenFlow take real actions — write code, run tests, send email, manage calendars, run workflows — under policy, approval, and evidence rules you control. LumenFlow is proprietary software licensed by Hellmai Ltd under the LumenFlow Proprietary License. - [Architecture Overview](https://lumenflow.cloud/docs/architecture-overview): How LumenFlow's kernel, cloud, and governed surfaces fit together to enforce policy and produce evidence. - [Installation & Setup](https://lumenflow.cloud/docs/installation-setup): Create a standard workspace for real governed work. Managed inference requires available credit; starter credit, when offered, is a one-time grant. - [Your First Workflow](https://lumenflow.cloud/docs/first-workflow): Walk through a complete governed workflow — delegate, approve, execute, and audit. - [Next Steps](https://lumenflow.cloud/docs/next-steps): Where to go from here — set up governance policies, explore the control-plane SDK, or try Sidekick. - [Playground and demo workspaces](https://lumenflow.cloud/docs/playground-overview): Three ways to try Sidekick: the public playground (fixed scenarios), a demo workspace (sample data and simulated connector effects), and a standard workspace (persistent real work under your governance). Use a standard workspace to prove actual execution. - [LumenFlow on mobile](https://lumenflow.cloud/docs/mobile-app): LumenFlow's mobile app carries the same governed workflows as the web dashboard — you can initiate, review, approve, and resolve governed work from your phone, not just watch it. The iOS app is in beta; Android is coming soon. - [LumenFlow Desktop](https://lumenflow.cloud/docs/desktop-app): LumenFlow Desktop is a beta desktop shell around your workspace, currently Linux only — a global command launcher, system tray, native notifications, and deep links, not just a browser shortcut. ## Governance & Policy - [What Are Governance Bridges?](https://lumenflow.cloud/docs/bridges-overview): Governance bridges connect your organization's approval culture to AI-driven automation. - [Agent Telemetry & Governance Evidence](https://lumenflow.cloud/docs/agent-telemetry-and-governance-evidence): When you connect a runtime, LumenFlow captures the full activity surface of your agents and records governance evidence — across any client, model, or BYOK setup — so you can see what your agents did and prove it followed policy. - [Approval Flows](https://lumenflow.cloud/docs/bridges-approval-flows): Design approval workflows — from auto-approve to multi-step escalation chains. - [Cost Controls](https://lumenflow.cloud/docs/bridges-cost-controls): Cap workspace spend with named Rules — warn or block, on a daily, weekly, or monthly period. - [Audit & Compliance](https://lumenflow.cloud/docs/bridges-audit-compliance): Every AI action is logged with full context — satisfying audit requirements. - [Regulated trust posture](https://lumenflow.cloud/docs/regulated-trust-posture): What the regulated-industry governance tier provides, and what LumenFlow does not claim. - [Roles & Permissions](https://lumenflow.cloud/docs/bridges-role-permissions): Control who can configure governance rules, manage connections, and access sensitive data. - [Policy Controls](https://lumenflow.cloud/docs/bridges-custom-policies): The policy controls LumenFlow enforces today: trust levels, approval-required tools, fail-closed mode, MCP server admission and organization fleet configuration. There is no policy language you write yourself. - [Autonomy policies and tool-call approvals](https://lumenflow.cloud/docs/autonomy-policies): Autonomy policy decides which actions Sidekick can take on its own and which require human approval. Trust levels (Supervised, Balanced, Autonomous, Custom) are presets over a tool-call gate, a budget gate, and an approval-required tool list. At every trust level, once Sidekick has read content from a connected app or MCP server, consequential actions route to the Approvals inbox before Sidekick proceeds. - [EU AI Act Article 12 readiness](https://lumenflow.cloud/docs/eu-ai-act-article-12-readiness): The EU AI Act's record-keeping (Article 12) and human-oversight (Article 14) requirements for Annex III high-risk systems become enforceable on August 2, 2026. This article maps each requirement to a LumenFlow primitive so a regulated buyer can answer compliance questions concretely. - [Governed AI compute: campuses and data centres](https://lumenflow.cloud/docs/campus-governed-compute): Building, running, or managing a data centre, data center, or GPU cluster for AI? LumenFlow is not a facility-management (DCIM) system — it never runs power, cooling, or hardware. What it does is govern and prove the AI compute on the floor: a sealed, independently re-verifiable proof bundle per tenant (utilisation and cost, data residency, carbon, SLA) plus energy and power monitoring. - [Energy and carbon provenance](https://lumenflow.cloud/docs/energy-carbon-provenance): LumenFlow monitors the electricity behind your AI work: it ingests facility power and carbon-intensity signals and PUE, attributes power draw and energy down to the individual compute run and token, and reports every figure with how it was derived — measured, modelled, or estimated — so reporting rests on provenance, not a single blended guess. - [Coordination inbox](https://lumenflow.cloud/docs/coordination-inbox): The coordination inbox is where decision cases land when automated actions conflict or a rule decides a person should weigh in — see what's waiting, who's been asked, and acknowledge each one. - [Shadow-agent inventory](https://lumenflow.cloud/docs/shadow-agent-inventory): A bounded inventory of agent-like activity LumenFlow can observe — its own governed runtimes, agents that describe themselves, and telemetry you send it. Confirm-only: acknowledge or set aside what you see; it never acts on its own. ## Developer Guide - [API & SDK Access](https://lumenflow.cloud/docs/api-reference): Programmatic access for connected runtimes, workspace exports, and governed automation flows. - [Governed Runtimes Overview](https://lumenflow.cloud/docs/governed-runtimes-overview): How connected runtimes enroll through LumenFlow Cloud and stay governed centrally. - [Control-Plane SDK Quickstart](https://lumenflow.cloud/docs/control-plane-sdk-quickstart): Enroll a connected runtime, understand the bootstrap command, and meet the v1 contract. - [Delivery Orchestration](https://lumenflow.cloud/docs/delivery-orchestration): Manage software delivery initiatives, work units, dispatch lanes, and operator actions through the hosted delivery API. - [Runtime Sessions](https://lumenflow.cloud/docs/runtime-sessions): Inspect hosted runtime workflows, turns, continuations, and operator actions for governed agent execution. - [DORA Metrics](https://lumenflow.cloud/docs/dora-metrics): Track deployment frequency, lead time, change failure rate, and mean time to recovery for AI software delivery. - [Traces and Evidence Chains](https://lumenflow.cloud/docs/traces-and-evidence): Browse task execution traces, span-level detail, and evidence receipt chains for auditability. - [Memory Sync](https://lumenflow.cloud/docs/signals-and-memory): Share project state across agents with version-based conflict resolution. - [Observe Dashboard](https://lumenflow.cloud/docs/observe-dashboard): Cross-workspace governance overview — evidence vault, external agents, fleet health, and rollout posture. - [Gates and Policy Enforcement](https://lumenflow.cloud/docs/gates-and-policies): Monitor gate health, pass rates, policy denials, and compute performance across governed workspaces. - [Fleet Management](https://lumenflow.cloud/docs/fleet-management): Monitor connected-runtime inventory, drift detection, policy distribution, and authority modes. - [Connected-Runtime Enrollment](https://lumenflow.cloud/docs/connected-runtime-enrollment): Enroll external runtimes via the enrollment API, manage credentials, and monitor health. - [Connections: Trusted Compute](https://lumenflow.cloud/docs/connections-trusted-compute): Run AI work on your own trusted compute under LumenFlow's governed runtime, with policy, approvals, and proof. - [Connected Compute](https://lumenflow.cloud/docs/connected-compute): Route governed work to customer-owned machines or LumenFlow-managed runners with one policy, lease, evidence, routing, and metering model. - [Desktop and mobile surfaces](https://lumenflow.cloud/docs/desktop-mobile-surfaces): What the LumenFlow desktop and mobile apps do today. - [Connected Runtime](https://lumenflow.cloud/docs/connected-runtime-reference-bridge): Connect a trusted external runtime to LumenFlow so sessions, governed tool calls, and evidence receipts stay inside the canonical control plane. - [Governed inference API](https://lumenflow.cloud/docs/governed-inference): One typed model call per request, by capability tier, from an inference-only key. Covers the request fields, streaming, tool calling, cache hints, image parts, limits, receipts and every typed refusal. - [Jobs lifecycle: queue, retries and dead letters](https://lumenflow.cloud/docs/jobs-lifecycle): Every job status, how a job queues and waits its turn, retries and backoff, dead letters, requeue and discard, runner claim waits and delayed releases, lease heartbeats and lapse, and the limits that govern them. - [Enterprise Trust](https://lumenflow.cloud/docs/enterprise-trust): Org-scoped trust dashboard, enterprise auth configuration, and governance readiness posture. - [Evidence Vault](https://lumenflow.cloud/docs/evidence-vault): Durable evidence custody, retrieval, and compliance export for governed agent actions. - [Approval Workflows](https://lumenflow.cloud/docs/approval-workflows): Budget, autonomy, and operator-control approvals with discussion threads and transition history. - [Connect a project to LumenFlow Cloud + consume the API](https://lumenflow.cloud/docs/connect-project): End-to-end walkthrough: create a workspace, issue an API key, run npx lumenflow cloud connect from your project, then call the Sidekick API for actions and the engagement-projection API for read-only cross-project consumption. - [Organization-wide observability](https://lumenflow.cloud/docs/org-observability): Organizations running many LumenFlow workspaces can use a single org-scoped token for a cross-workspace view of active work, dispatch, agent activity, cost, and DORA metrics — with role-scoped views for executives, delivery leads, and engineers. - [Bring your own compute (BYOC)](https://lumenflow.cloud/docs/bring-your-own-compute): Run governed work on your own machines. LumenFlow's cloud issues a scoped authorization envelope — permissions, budget, a kill switch, and a confinement posture — to a local runner, then ingests per-action evidence and cost back. Your compute, LumenFlow's governance. - [Federation: governed agents on your own network](https://lumenflow.cloud/docs/federation-private-network): Run LumenFlow's governed agents inside your own private network, connected back to the cloud control plane. Federation keeps execution and data on your side of the boundary while policy, approvals, and evidence stay centrally governed. - [Governed CI/CD pipelines](https://lumenflow.cloud/docs/governed-cicd): Run LumenFlow governance inside your CI/CD pipelines. A first-party action lets your GitHub or GitLab workflows run governed checks and sandboxed tasks and emit the same evidence as any other governed work — so the pipeline is part of the audit trail, not a gap in it. - [Standards-portable evidence (OpenTelemetry)](https://lumenflow.cloud/docs/otel-portable-evidence): LumenFlow's evidence exports in OpenTelemetry's agent-tracing semantic conventions, so the record of what your agents did can be consumed by the observability stack you already run — Datadog, Grafana, and others — without lock-in. - [Connect to LumenFlow via MCP](https://lumenflow.cloud/docs/mcp-server-connection): LumenFlow can act as a server for MCP-compatible AI tools, so they can query your workspace as a connected data source, authenticated with a workspace API key. Today this exposes one read-only tool: a list of your workspace's delivery programs. - [Connect a Linux machine as a Connected Compute node](https://lumenflow.cloud/docs/connected-compute-linux-setup): Pair your own Linux machine to run governed Sidekick work under your workspace's policy — prerequisites, the current verified setup path, doctor diagnostics, firewall posture, and how to drain, quarantine, or remove the node. - [Connect a Windows machine as a Connected Compute node](https://lumenflow.cloud/docs/connected-compute-windows-setup): Pair your own Windows machine to run governed Sidekick work under your workspace's policy — prerequisites, the current verified setup path, doctor diagnostics, firewall posture, and how to drain, quarantine, or remove the node. ## Dashboard Guide - [Dashboard Overview](https://lumenflow.cloud/docs/dashboard-overview): The LumenFlow dashboard is your command center across workspaces. Authenticated users land in Sidekick — the conversation surface where you ask, approve, and review work. Jobs gives a non-conversational workspace overview; Settings holds configuration; Agents is the operator depth surface for job and runtime state. - [Workspace Management](https://lumenflow.cloud/docs/dashboard-workspace-management): Create, configure, and switch between workspaces for different teams and projects. - [Activity feed and proof](https://lumenflow.cloud/docs/dashboard-activity-feed): Monitor real-time activity — actions taken, proposals pending, and governance events. The standalone activity bucket folds into Sidekick's Proof widget and Notifications; per-job activity remains a drill-down inside Jobs. - [Analytics & Reporting](https://lumenflow.cloud/docs/dashboard-analytics): Track token usage, action volume, approval rates, and cost trends over time. - [Team Members](https://lumenflow.cloud/docs/dashboard-team-members): Invite teammates and assign roles via the API — there is no dashboard Team management screen today. - [Workspace Settings](https://lumenflow.cloud/docs/dashboard-settings): Configure workspace defaults, timezone, language, and general preferences. - [Notifications](https://lumenflow.cloud/docs/dashboard-notifications): Configure alerts for approvals, stalled agents, and delegated work that needs your attention. - [Search](https://lumenflow.cloud/docs/dashboard-search): Find conversations, actions, and audit entries across your workspace. - [Keyboard Shortcuts](https://lumenflow.cloud/docs/dashboard-keyboard-shortcuts): Navigate the dashboard faster with keyboard shortcuts and command palette. - [Governed Work in Flight](https://lumenflow.cloud/docs/dashboard-delivery): Track everything Sidekick is doing right now, and the operator inbox for work that needs a human look. - [Runtime Dashboard](https://lumenflow.cloud/docs/dashboard-runtime): Inspect governed agent sessions, workflow state, and operator controls from the runtime dashboard. - [Pipeline Metrics](https://lumenflow.cloud/docs/dashboard-pipeline): Script execution telemetry for the last 7 days, from the workspace overview panel host. - [DORA Metrics Dashboard](https://lumenflow.cloud/docs/dashboard-dora): Delivery performance metric cards for the last 7 days, from the workspace overview panel host. - [Evidence Chain Traces](https://lumenflow.cloud/docs/dashboard-traces): There is no dedicated traces page — recent evidence appears on the workspace overview, and full trace detail is API-only. - [Agents: operator surface for agents](https://lumenflow.cloud/docs/dashboard-studio): Agents is the operator depth surface. It shows the job graph, action rail, output explorer and live runtime overlay. Consumers stay in Sidekick. - [Replay: governed replay chain](https://lumenflow.cloud/docs/dashboard-replay): Replay is the workspace-level surface at /dashboard//observe/replays that shows the latest governed replay chain — the full evidence trail correlating a builder job with its delivery, runtime, and evidence outputs. Use Replay to audit what happened after the fact, prove a decision, or reconstruct the chain Sidekick followed. - [Objectives](https://lumenflow.cloud/docs/objectives): Objectives is the workspace review page for outcomes you've delegated to Sidekick in conversation — priority, status, success criteria, and progress, all created and updated by talking to Sidekick, not by filling in a form. ## Model Configuration - [Model Configuration Overview](https://lumenflow.cloud/docs/model-config-overview): Use managed inference by default, or connect your own model keys for advanced control. - [Supported Providers](https://lumenflow.cloud/docs/model-config-providers): The provider kinds LumenFlow connects to: OpenAI, Anthropic, Google, Mistral, and any OpenAI-compatible endpoint. Models come from each provider's live catalogue. - [API Key Management](https://lumenflow.cloud/docs/model-config-api-keys): Add, rotate, and secure your LLM provider API keys in LumenFlow. - [Default Model Settings](https://lumenflow.cloud/docs/model-config-defaults): Configure per-conversation defaults — temperature, token limits, and system prompts — for your workspace. These defaults apply within whichever workspace AI source you've chosen (managed inference or BYOK); they don't change the source itself. See workspace-ai-source for the workspace-level managed-vs-BYOK decision. - [Workspace AI source: managed inference vs BYOK](https://lumenflow.cloud/docs/workspace-ai-source): Every workspace has a single AI source that decides who pays for and operates the model that powers Sidekick. New workspaces default to managed inference (LumenFlow runs the model). You can switch to BYOK to point Sidekick at your own provider key. This is workspace-level — it's separate from per-conversation model selection. - [Bringing your own model through OpenRouter](https://lumenflow.cloud/docs/byok-openrouter-and-free-models): Connect an OpenRouter API key as a bring-your-own-model source, discover what's actually available and what it costs directly from OpenRouter's own live catalog, and understand why LumenFlow never promises a specific model stays free. ## Sidekick - [Building software with Sidekick](https://lumenflow.cloud/docs/building-software-with-sidekick): Software delivery is one of the Jobs Sidekick handles. In this scenario it claims work units, writes code in an isolated worktree, runs tests, and opens pull requests — all under your policy and approval rules. It works with your code host and deployment tools rather than replacing them. - [Sidekick Overview](https://lumenflow.cloud/docs/sidekick-overview): Sidekick is LumenFlow's governed AI agent. It takes actions on your behalf across software delivery, communication, scheduling, data, and workflows — every action passes through policy and approval gates. - [Chat Interface](https://lumenflow.cloud/docs/chat-interface): Navigate Sidekick's chat UI — threads, attachments, keyboard shortcuts, and more. - [Delegating Tasks](https://lumenflow.cloud/docs/delegating-tasks): Prompt patterns, multi-step tasks, and best practices for effective delegation. - [Connections](https://lumenflow.cloud/docs/connections): Connect Gmail, Outlook, Greenhouse, Slack, and custom tools to expand what Sidekick can do. - [Memory & Context](https://lumenflow.cloud/docs/memory-context): How Sidekick maintains context across conversations and learns your preferences. - [Approvals & Governance](https://lumenflow.cloud/docs/approvals-governance): Configure what Sidekick can do automatically and what needs your approval. - [Workflows](https://lumenflow.cloud/docs/workflows): Build multi-step automations with conditional logic and approval gates. - [Billing & Costs](https://lumenflow.cloud/docs/billing-costs): Understand LumenFlow's pricing, token metering, and cost controls. - [Routines](https://lumenflow.cloud/docs/sidekick-routines): Schedule recurring automations, link them to objectives, configure reactive routing, and control trust with autonomy policies. - [Briefings](https://lumenflow.cloud/docs/sidekick-briefings): Receive scheduled email digests summarizing routine outcomes, objective progress, and delegated work status. - [Notifications](https://lumenflow.cloud/docs/sidekick-notifications): One bilateral inbox for what Sidekick needs from you and what it just did for you — with per-type preferences and multi-transport delivery. - [MCP Servers](https://lumenflow.cloud/docs/sidekick-mcp-servers): Register, authenticate, and manage Model Context Protocol servers that give Sidekick access to custom tools. - [Tools](https://lumenflow.cloud/docs/sidekick-tools): Browse available tool connections, test capabilities, manage MCP servers, and control which tools Sidekick is allowed to use. - [Onboarding](https://lumenflow.cloud/docs/sidekick-onboarding): Onboarding is conversational: a new workspace opens straight into chat, and Sidekick asks for whatever it needs — a model source, a connector — as your first request requires it. - [Settings](https://lumenflow.cloud/docs/sidekick-settings): Manage billing, BYOK and managed-inference model configuration, spending budgets, trust levels, destination defaults, and team permissions from the workspace Settings surface. Owners and admins see the full surface; members see a personal preferences view. - [Troubleshooting](https://lumenflow.cloud/docs/troubleshooting): Common issues, error messages, and how to resolve them. - [Outputs, artifacts, and destinations](https://lumenflow.cloud/docs/outputs-artifacts-destinations): How LumenFlow saves generated work from Sidekick, external agents, and fleet workers; what managed artifact links mean; and the two ways a page or app goes public — a hosted app page LumenFlow publishes directly, or a connected deployment destination for a full app — always with your explicit confirmation. - [How LumenFlow looks: jobs, agents, and proof](https://lumenflow.cloud/docs/how-lumenflow-looks): Sidekick is the front door. You ask, LumenFlow plans, agents work, you approve, and proof is kept. This explains the consumer model — jobs, steps, agents, connections, rules, approvals, outputs, and proof — and why visual structure lives inside Sidekick rather than on a separate canvas. - [Managed storage and managed runtime](https://lumenflow.cloud/docs/managed-storage-defaults): Sidekick ships with built-in defaults for storage and execution: managed artifacts holds generated docs, files, and export bundles in LumenFlow-managed storage, and managed runtime runs builder work when no external execution target is connected. You do not need external artifact storage before Sidekick can save internal outputs; public hosting and deployment still require a connected destination and explicit confirmation. - [Builder destinations and publication workflow](https://lumenflow.cloud/docs/builder-destinations): Sidekick chooses a destination for every build it does — code, docs, files, runtime, deployment — based on what your workspace has pinned. Managed defaults work without setup; pinned connectors route work to your owned tools (GitHub for code, Notion for docs, OneDrive for files, GitHub Pages or Vercel for deployments). Risky publication steps go through approval before Sidekick proceeds. - [Landing preference: Dashboard vs Sidekick](https://lumenflow.cloud/docs/landing-preference): Each user can choose where a workspace opens for them — Dashboard (the workspace overview) or Sidekick (the conversation). The preference is per user and per workspace, doesn't change role authority, and doesn't affect teammates. Switch it any time in Settings. - [Governed Sidekick execution](https://lumenflow.cloud/docs/governed-sidekick-execution): How long-running Sidekick work, parallel subagent fanout, governed browser actions, drift evidence, and routine studio fit inside one evidence boundary. - [Autonomous delivery: from one instruction to finished work](https://lumenflow.cloud/docs/autonomous-delivery): Sidekick can take a single instruction and carry it through to finished work — not just answer. Larger asks can branch into several linked pieces of work, with bounded parallel Agents on the independent ones. Autonomous delivery is opt-in per workspace, asks before it starts, streams evidence as it goes, and fails loudly rather than silently. - [Hosted app pages: publish a page Sidekick built](https://lumenflow.cloud/docs/hosted-app-pages): When Sidekick builds you a simple, self-contained page — a demo, prototype, or small utility — you can ask it to publish that page directly and get a real, shareable link. Publishing always asks for your explicit confirmation first, every page is checked before it goes live, and you can unpublish it any time. Bigger apps with a backend route to a connected deployment destination instead. ## Use Cases - [Email Automation](https://lumenflow.cloud/docs/usecase-email-automation): Automate email drafting, scheduling, and follow-ups with Sidekick and Gmail. - [Data Analysis](https://lumenflow.cloud/docs/usecase-data-analysis): Use Sidekick to query databases, generate reports, and surface insights from your data. - [Team Coordination](https://lumenflow.cloud/docs/usecase-team-coordination): Coordinate meetings, standups, and cross-team communication with Sidekick. - [Customer Support](https://lumenflow.cloud/docs/usecase-customer-support): Triage support tickets, draft responses, and escalate issues with Sidekick. ## Integrations - [Integrations Overview](https://lumenflow.cloud/docs/integrations-overview): How LumenFlow connects to external services across Tool Connections, channels, MCP, OAuth, and API keys. - [Google Workspace](https://lumenflow.cloud/docs/integrations-google-workspace): Connect Gmail, Google Calendar, Google Docs, and Google Sheets to your workspace. - [Slack](https://lumenflow.cloud/docs/integrations-slack): Connect Slack for governed sends, provider read access, and guided inbound setup. - [GitHub](https://lumenflow.cloud/docs/integrations-github): Connect GitHub to summarize repository work, inspect pull requests, and manage issues. - [Jira](https://lumenflow.cloud/docs/integrations-jira): Connect Jira Cloud to find matching issues, summarize tickets, and update tracked work. - [Notion](https://lumenflow.cloud/docs/integrations-notion): Connect Notion to find pages, read shared docs, and make bounded note updates. - [Zapier](https://lumenflow.cloud/docs/integrations-zapier): There is no one-click Zapier connect flow. Today, any MCP-compatible client can reach LumenFlow's read-only MCP host with a workspace API key. - [Webhooks](https://lumenflow.cloud/docs/integrations-webhooks): Subscribe an HTTPS endpoint to signed workspace events from Settings → Connections → Webhooks. - [Custom MCP Servers](https://lumenflow.cloud/docs/integrations-custom-mcp): Build and connect custom tools using the Model Context Protocol. - [Microsoft Teams](https://lumenflow.cloud/docs/integrations-teams): Connect Microsoft Teams to send governed messages and receive inbound chat via Bot Framework. - [Discord](https://lumenflow.cloud/docs/integrations-discord): Connect Discord to send governed messages and ingest inbound events via a bridge runtime. - [Telegram](https://lumenflow.cloud/docs/integrations-telegram): Connect a Telegram bot to send governed messages and receive inbound chat via Telegram webhooks. - [Twilio SMS](https://lumenflow.cloud/docs/integrations-twilio): Connect Twilio to send governed SMS messages and receive inbound texts via Twilio webhooks. - [WhatsApp](https://lumenflow.cloud/docs/integrations-whatsapp): Connect WhatsApp Business to send governed messages, manage templates, and receive inbound chat. - [Custom Webhooks](https://lumenflow.cloud/docs/integrations-custom-webhooks): Build bidirectional integrations with any system using custom outbound and inbound webhooks. - [Public Q&A Widget](https://lumenflow.cloud/docs/integrations-public-chat): The public Q&A widget on lumenflow.cloud answers visitor questions about LumenFlow and Sidekick from the public documentation. The widget is read-only and rate-limited; it never accesses workspaces, user data, or operator actions. - [Client Engagement Chat](https://lumenflow.cloud/docs/integrations-client-chat): Provide a private, token-protected chat portal for individual clients with vector-retrieved context. - [Microsoft 365 (Outlook Mail, Outlook Calendar, OneDrive, To Do)](https://lumenflow.cloud/docs/integrations-microsoft-365): Sidekick connects to the Microsoft 365 stack: Outlook Mail for sending and triaging email, Outlook Calendar for scheduling and conflict-aware booking, OneDrive for document storage and retrieval, and Microsoft To Do for task tracking. Each is a separate governed connector with its own scope and approval rules. - [HubSpot](https://lumenflow.cloud/docs/integrations-hubspot): Connect HubSpot to find contacts and companies, summarise deals, log activity, and create or update records. Sidekick respects HubSpot pipeline permissions and routes risky writes through approval before they hit your CRM. - [Greenhouse](https://lumenflow.cloud/docs/integrations-greenhouse): Connect Greenhouse to triage candidates, summarise interview kit feedback, and update candidate stage. Sidekick reads through governed connector access and pushes write actions through approval to keep hiring decisions auditable. - [Yelp](https://lumenflow.cloud/docs/integrations-yelp): Connect Yelp Fusion to look up business listings, reviews, hours, and category metadata. Read-only; useful for outreach research, local-market context, and customer-support workflows where the customer references a venue. - [Linear](https://lumenflow.cloud/docs/integrations-linear): Connect Linear to find and read issues, create and update them, comment, and browse projects — issue tracking and planning from inside Sidekick. - [Calendly](https://lumenflow.cloud/docs/integrations-calendly): Connect Calendly to list event types, check availability, list scheduled events, create scheduling links, and cancel events — scheduling from inside Sidekick. - [Microsoft Dataverse](https://lumenflow.cloud/docs/integrations-dataverse): Connect Microsoft Dataverse to list and describe tables, query and search records, fetch a record, and create records — work with your Dataverse data from inside Sidekick. - [OpenTable](https://lumenflow.cloud/docs/integrations-opentable): Connect OpenTable to find restaurants, check dining availability, hold a slot, and create reservations through partner booking flows — from inside Sidekick. ## Security - [Security Overview](https://lumenflow.cloud/docs/security-overview): How LumenFlow protects your data — encryption, access control, and privacy — and how to report a security issue to security@lumenflow.cloud. - [Encryption](https://lumenflow.cloud/docs/security-encryption): How LumenFlow protects your data at rest and in transit. - [Access Control](https://lumenflow.cloud/docs/security-access-control): Workspace isolation, role-based access, and the credential model. - [Credentials and scopes](https://lumenflow.cloud/docs/credentials-and-scopes): Every credential kind Cloud issues, its prefix, the scopes it can carry, who issues it and how it is revoked, with the scope names the API checks. - [Compliance & Privacy](https://lumenflow.cloud/docs/security-compliance): GDPR, SOC 2 readiness, and data privacy — how LumenFlow handles your data responsibly. - [Independently verifiable evidence](https://lumenflow.cloud/docs/independently-verifiable-evidence): LumenFlow seals evidence anchors. When an RFC 3161 timestamp witness is configured and succeeds, an auditor can independently verify that an anchor root existed by the witnessed time. Check each anchor's witness status before making that claim. - [Compliance export](https://lumenflow.cloud/docs/compliance-export): Export what your compliance selection promises and the audit trail behind it — a workspace-level promise summary, plus an org-level audit-trail export download. - [Which credential is for what](https://lumenflow.cloud/docs/connected-compute-credentials): LumenFlow uses several distinct, narrowly-scoped credentials instead of one all-purpose secret — a signed-in session, a workspace-wide API key for CI, a single-use code for pairing your own machine, and a durable identity for that paired machine. This is the map of who holds each one, how long it lasts, and what it can and can't do. - [Trust Centre](https://lumenflow.cloud/docs/trust-centre): Where to find LumenFlow's public trust centre, sub-processors register, live status feed, and the in-product Trust dashboard for compliance packs, residency pinning, and the Article 12 auditor pack. - [SIEM push recipes (Datadog, Grafana, Sentinel)](https://lumenflow.cloud/docs/siem-push): Point LumenFlow's per-organisation OpenTelemetry collector push at Datadog, Grafana Cloud, or Microsoft Sentinel — one OTLP destination, three destination recipes. ## Billing - [Billing Overview](https://lumenflow.cloud/docs/billing-overview): How LumenFlow billing works — plan tiers, token metering, and payment methods. - [Plans & Pricing](https://lumenflow.cloud/docs/billing-plans-pricing): Compare Free, Team, and Enterprise plans — features, limits, and what's included. - [Usage Tracking](https://lumenflow.cloud/docs/billing-usage-tracking): Monitor token consumption, cost breakdown, and usage patterns in real time. - [Spending Limits](https://lumenflow.cloud/docs/billing-budgets-alerts): Cap Sidekick spend with named, workspace-scoped Rules — warn or block, on a daily, weekly, or monthly period. - [Your inference wallet](https://lumenflow.cloud/docs/inference-wallet): Managed AI usage is paid from a per-workspace inference wallet of prepaid credits. This covers topping up, checking your balance, setting limits, and what happens when credits run low. ## Troubleshooting - [Common Issues](https://lumenflow.cloud/docs/troubleshooting-common-issues): Solutions for the most frequently encountered problems in LumenFlow. - [Error Code Reference](https://lumenflow.cloud/docs/troubleshooting-error-codes): Complete reference of LumenFlow error codes with causes and resolutions. - [Getting Support](https://lumenflow.cloud/docs/troubleshooting-support): How to get help — community, email support, and enterprise support channels.