--- title: "Guides" description: "Task-oriented walkthroughs for everything you'd want to do in Cerevisor." slug: guides section: guides canonical_url: https://cerevisor.com/docs/guides last_verified: 2026-05-18 last_verified_version: "1.2.0" updated_at: 2026-05-18T15:08:18.053416+00:00 --- Pick the guide that matches what you're trying to do. Each one is self-contained; you don't need to read them in order. ## Building workflows The bread and butter. How to design, configure, and run multi-agent workflows. - [Add and configure agents](./building-workflows/add-and-configure-agents.md): every field in the Agent Config popup, when to fill which, smart defaults. - [Connect agents](./building-workflows/connect-agents.md): handoffs, auto-connect, manual wiring, handoff formats. - [Attach markdown files](./building-workflows/attach-markdown-files.md): input files, output files, the markdown panel, the drop zones. - [Control flow: conditions, loops, gates](./building-workflows/control-flow-conditions-loops-gates.md): the four connection flow types and when to use which. - [Run and monitor](./building-workflows/run-and-monitor.md): the Run button, the Execution Modal, pausing, stopping, replaying. - [Use the chat builder](./building-workflows/using-the-chat-builder.md): natural-language workflow construction, attaching skills + files, the floating window. ## Working with skills Skills are reusable, focused capabilities you assign to agents. Cerevisor scans your skill folders and merges them into the Skills panel. - [What are skills?](./working-with-skills/what-are-skills.md): the concept, the file format, where they live. - [Browse and assign skills](./working-with-skills/browse-and-assign-skills.md): the Skills panel, drag-to-agent, the Skill Viewer. - [Create a skill in the Workshop](./working-with-skills/create-a-new-skill-in-workshop.md): templates, the editor, validation. - [Skill compatibility with providers](./working-with-skills/skill-compatibility-with-providers.md): why some skills only work with some providers. ## Providers Cerevisor is provider-agnostic. Mix Anthropic, Gemini, Claude Agent SDK, local Ollama, OpenAI Codex CLI, and Cursor in one workflow if you want. - [Provider overview](./providers/overview.md): the six provider types, the library, defaults, per-agent overrides. - [Anthropic](./providers/anthropic.md): API key, model catalog, cost. - [Gemini](./providers/gemini.md): API key from Google AI Studio, 2.5/3.x families, >200K-tier pricing. - [Claude Agent SDK](./providers/claude-agent-sdk.md): Claude Code's harness running in-process via delegated loop. - [OpenAI-compatible & local models](./providers/openai-compatible-and-local.md): Ollama, OpenRouter, vLLM, LM Studio, Together, Groq, Fireworks, OpenAI itself. - [OpenAI Codex CLI](./providers/openai-codex-cli.md): device auth, sandbox modes, ChatGPT subscription. - [Cursor Agent](./providers/cursor-agent.md): API key, local + cloud execution. - [Per-agent provider overrides](./providers/per-agent-overrides.md): mixing providers in one workflow. - [Managing the Provider Library](./providers/managing-the-provider-library.md): add, remove, set default, deletion guards. ## Memory & Learning Cerevisor remembers you across sessions: your preferences, your patterns, what's worked. - [Memory overview](./memory-and-learning/overview.md): the four memory stores, how they interact, what's local-only. - [Your user profile](./memory-and-learning/user-profile.md): editing, the current-focus block, what's auto-managed. - [Harness memory & meta-cognition](./memory-and-learning/harness-memory-and-meta-cognition.md): what the harness learns from runs, observations, self-portrait. - [Disagreements & proposals](./memory-and-learning/disagreements-and-proposals.md): when the harness wants to change your profile and you push back. - [Data inventory & consent](./memory-and-learning/data-inventory-and-consent.md): what Cerevisor knows about you, classification by data type, the local export bundle. - [Exporting your data](./memory-and-learning/exporting-your-data.md): the right-to-portability JSON bundle. ## Situational Awareness What the harness believes vs. assumes, what's changed since you last looked, what's still unknown. New in v1.2.0. - [Situational Awareness overview](./situational-awareness/overview.md): the three slices (taskwork, agent, teamwork), state labels, belief attribution, freshness. - [Configure and run](./situational-awareness/configure-and-run.md): the SA Directive, the per-agent uncertainty badge, the wave situation report, fixation warnings. ## Workspaces & scheduling - [Multiple workflows (World View)](./world-view-multiple-workflows.md): workspaces, the rail, cross-workflow links, the world canvas. - [Scheduling & pipelines](./scheduling-and-pipelines.md): cron schedules, multi-workflow pipelines, budget caps. ## Advanced Power-user surfaces. Skip until you need them. - [MCP servers](./advanced/mcp-servers.md): connect any Model Context Protocol server and expose its tools to your agents. - [Loop & Enhance](./advanced/loop-and-enhance.md): automatic detect-fix-rerun cycles. - [Cursor cloud runs](./advanced/cursor-cloud-runs.md): run workflows on Cursor's cloud VMs. - [Embedded apps (Windows)](./advanced/embedded-apps-windows.md): put Outlook, Excel, and other native apps on the canvas. - [Web search providers](./advanced/web-search-providers.md): configure Tavily, Perplexity, Linkup. ## Licensing - [Licensing & tiers](./licensing-and-tiers.md): trial, free, paid; what each unlocks; how to upgrade; deactivating a seat.