User Guide
Use Siesta AI to finish real work: ask an agent, attach files, create tasks, run workflows, review tool actions, and keep useful context available for the next conversation.
Read the Product Introduction for the platform model, then use this guide to choose the practical surface for the work.
Learn to Work With AI
Choose the right task
Recognize language-heavy, reviewable work where AI can help and where a tool or human decision is still required.
Write better prompts
Use role, context, task, format, and constraints to create a clear and inspectable request.
Review and reuse prompts
Diagnose weak outputs, handle uncertainty, and maintain a small library of tested team templates.
Explore enterprise patterns
See how governed data, specialist review, and human decisions support complex document workflows.
Start With The Smallest Surface
Ask in Chat
Use Chat for one-off drafting, analysis, file review, and fast questions. Name the audience, source, output format, and next action.
Choose an agent
Use an Agent when the work needs a prepared role, approved tools, trusted sources, or a repeatable way of answering.
Track work
Use Tasks when work should be tracked, reviewed, continued later, or handed to another agent or teammate.
Use sources
Use data collections for uploaded files and synced sources such as Google Drive, SharePoint, OneDrive, Jira, Confluence, Azure Storage, Azure File Share, or approved website data.
Repeat workflows
Use Workflows when the same process should run again with clear inputs, checks, and tool actions.
Continue past work
Use conversations, recordings, Tool Executions, and saved context when you need to recover evidence or explain what happened.
A Practical Order Of Work
- Pick the right place. Open Chat for a single request, choose an agent for role-specific work, create a task for follow-up, use sources for trusted knowledge, or run a workflow for repeatable operations.
- Make the request inspectable. Give the source, expected output, constraints, and whether the agent may use tools. Ask for a preview before any external write action.
- Check the trace. If a tool was used, inspect the conversation and Tool Executions. Look at the action, approval state, arguments, result, and failure message before retrying.
Use This Guide When
- You need a good first prompt for Chat or an Agent.
- You are not sure whether to use sources, saved context, tasks, or workflows.
- A connection expired, a tool is missing, or an external action failed.
- You need to explain to an admin exactly what went wrong.
Good First Requests
Use the Support FAQ data collection and draft a customer reply. Keep it under 120 words and do not send it.
Create a task from this conversation for the Operations agent. Set the status to In review and include acceptance criteria.
Review the failed tool execution and tell me which connection, permission, or input needs attention.
Feature Map
| Need | Practical guide | Product Specification | Check |
|---|---|---|---|
| Draft, summarize, compare, analyze | Ask in Chat Effectively | Chat | Did you provide source, format, and audience? |
| Role-specific answer or action | Choose and Use Agents | Agents | Does the agent have the right data, tools, and access? |
| Follow-up work | Use Tasks to Track Work | Tasks | Is the status clear: Todo, In progress, In review, or Done? |
| Company files and synced sources | Use Sources and Files | Data | Is the source processed and attached to the right agent? |
| Durable internal knowledge | Save Reusable Context | Memory | Is the knowledge maintained and scoped to the right team? |
| Repeatable process | Repeat Work With Workflows | Workflows | Are inputs, approvals, and failure checks clear? |
| External system action | Use Connections Safely | Tools | Did the action succeed, fail, or wait for approval? |