Skip to content
Foldspace Developers

User Guides

Open in ChatGPT Open in Claude

These guides cover running Foldspace day to day from the dashboard: building and tuning your agent, measuring how it performs, and validating its behavior before changes reach users.

Foldspace has three modules — switch between them from the app switcher in the top-left corner.

Agent Studio

Section titled “Agent Studio”
Agent Studio — build, configure, and test your AI agent My Agent Ask anything… Knowledge Actions lookupOrder resetPassword createTicket Navigation Integrations S H W M

Build and configure your agent: its knowledge, the actions it can run, the pages it can navigate, and how it looks and sounds.

Playground Chat with your agent and test changes before they go live.
Knowledge Base Add and organize the content that keeps answers accurate.
Authoring actions Define the capabilities the agent can run and when to use them.
Defining inputs (schema) Tell each action what data it needs from the conversation.
Task Agents Build sub-agents for complex, multi-step workflows.
Conversations (HITL) Review real chats, debug actions, and train with feedback.
Style & behavior Set appearance, tone, starters, and response rules.
Voice Configure speech-to-text and two-way voice chat.
Setup & embed Activate the agent and drop it into your product.
Integrations Connect Slack, HubSpot, email, and webhooks.
MCP servers Connect external data and tools over MCP.
A2A agents Delegate to and receive tasks from other AI agents.

Analytics

Section titled “Analytics”
Analytics — dashboards, reports, audiences, and session replay Dashboard Reports Audiences A 12 chats B 8 chats C 5 chats D 3 chats Session Replay

Understand how users engage with your agent and your product.

Dashboard A canvas of metric widgets tracking engagement over time.
Reports Build custom analyses across the full metric library.
Audiences Explore and search everyone who uses your agent.
Session replay Watch recorded sessions to see how users interact.
Segments Group users by attribute or behavior to compare them.
AI costs Track token spend and cost per action.
Feature management A/B test and roll out capabilities to specific users.

Trust Lab

Section titled “Trust Lab”
Trust Lab — test suites, scenarios, runs, and scheduled testing Test Suites Sanity Suite 12/12 Regression 28/28 × Edge Cases 9/11 Scenario: Order lookup Where's my order? I found order #1234 Evals Contains order number Called lookupOrder action Run #47 — Results 88% pass rate Schedules Daily @ 6:00 AM Sanity Suite Weekly — Mon 9 AM Full Regression Next run in 4h 22m

Test the agent’s behavior before it reaches users, and catch regressions automatically.

Overview How Trust Lab works and a typical testing workflow.
Dashboard A real-time health view of your test coverage.
Test Suites Group scenarios into the unit you run and schedule.
Scenarios Build test conversations and the evals that grade them.
Runs The execution log, with detail on every failure.
Schedules Run suites automatically so regressions surface on their own.