Aurora | Synthflow

Aurora in the Synthflow sidebar

Aurora is an AI agent that works inside your Synthflow workspace. You can think of it as the product analyst or forward-deployed engineer that lives in your project. It is here to help you find answers and get things done fast. To manage Synthflow from an AI tool like Claude Code or Codex instead of the dashboard, use the Claude Code and Codex connectors.

Unlike a general-purpose chatbot, Aurora is connected to your workspace: your agents, call logs, knowledge bases, actions, and simulations. It can reference real configuration and call data, then run actions in Synthflow on your behalf. Describe what you want in natural language and Aurora can:

Build and update agents: Create agents, draft and refine prompts, work with Flow Designer flows, publish drafts, and compare versions before you go live.
Configure actions and integrations: Scaffold, create, attach, and test actions without stepping through every screen in the agent editor.
Manage knowledge: Create knowledge bases, add items from files or URLs, and attach bases to the agents that should use them.
Analyze calls: List and inspect calls, pull analytics, play recordings, and surface summaries when you ask product or operations questions.
Test before launch: Create and run simulations, start test calls, and validate agent behavior from the chat.
Answer how-to questions: Search Synthflow documentation when you need feature explanations or setup guidance.

The main interface is Aurora in the main sidebar: one thread where you type a request, attach context, and review what Aurora did. Every capability above is powered by the same Aurora core and the capabilities it uses behind the scenes. For step-by-step control in the UI, the feature guides on this site remain the source of truth.

Capabilities

When Aurora works on a task, it uses workspace capabilities such as the ones below.

Capability	Description
Add Knowledge Base Item	Add an item to a knowledge base.
Attach Action to Agent	Attach an action to an agent.
Attach Knowledge Base to Agent	Attach a knowledge base to an agent.
Confirm Action	Ask for or record confirmation before an action runs.
Create Action	Create a new action for an agent.
Create Agent	Create a new AI voice agent.
Create Knowledge Base	Create a new knowledge base.
Create Simulation Case	Create a simulation test case.
Create Simulation Suite	Create a suite of simulation tests.
Delete Action	Delete an action.
Delete Agent	Delete an agent.
Delete Knowledge Base Items	Delete items from a knowledge base.
Detach Action from Agent	Remove an action from an agent.
Execute Simulation Suite	Run a simulation suite.
Fetch URL	Fetch content from a URL.
Get Action	Retrieve details for a specific action.
Get Agent	Retrieve details for a specific agent.
Get Agent Actions	Retrieve actions attached to an agent.
Get Agent Knowledge Base	Retrieve the knowledge base attached to an agent.
Get Agent Version Diff	Retrieve a structured diff between agent versions.
Get Call Analytics	Retrieve analytics for calls.
Get Call Details	Retrieve details for a specific call.
Get FSM Schema	Retrieve the schema for a finite-state machine.
Get Knowledge Base	Retrieve a knowledge base.
Get Simulation Session	Retrieve a simulation session and its results.
Get Webhook Log Detail	Retrieve details for a specific webhook log.
Initialize Action	Initialize or scaffold a new action.
List Actions	List available actions.
List Agent Versions	List versions for an agent.
List Agents	List available agents in the workspace or account.
List Calls	List recent or matching calls.
List Contacts	List available contacts.
List Integrations	List connected integrations.
List Knowledge Bases	List available knowledge bases.
List Phone Numbers	List available or connected phone numbers.
List Simulation Cases	List simulation test cases.
List Simulation Suites	List available simulation suites.
List Simulations	List simulation runs or sessions.
List Subaccounts	List subaccounts under the current account.
List Voices	List available voices for agents.
List Webhook Logs	List webhook execution logs.
Play Recording	Play or retrieve a call recording.
Publish Agent Draft	Publish an agent draft as the active version.
Save Learning	Save a learning or reusable instruction.
Search Agents by Prompt	Search agents by their prompt or instructions.
Search Docs	Search product documentation for answers.
Show Call Card	Display a call summary card.
Show Form	Render a form for collecting structured input.
Show Table	Render structured data as a table.
Show Version Diff	Display differences between agent versions.
Start Test Call	Start a test call with an agent.
Test API Call	Test an API call or action execution.
Update Action	Update an existing action configuration.
Update Agent	Update an existing agent configuration.
Validate FSM	Validate a finite-state machine configuration.

Memory

Aurora Memory keeps context for the conversation you are in. As you work in a thread, Aurora automatically remembers details from earlier messages, such as which agent you are changing, files you attached, or how you want a task handled. That context helps Aurora stay aligned with what you already said instead of asking you to repeat the same setup in every reply.

Memory applies only to the current Aurora chat. When you start a new conversation, that thread begins without the prior chat’s memory. For preferences or facts you want Aurora to remember across chats in this workspace, use Learnings.

Memory is enabled by default. There is no Memory settings screen to edit or clear it in the dashboard today.

Aurora Memory is not the same as Memory of past calls for voice agents. Memory Groups store contact summaries for phone conversations. Aurora Memory applies only to your Aurora chat thread.

Learnings

Learnings are saved at the workspace level. They carry across Aurora conversations, not only the thread where they were created. Aurora can store preferences, naming conventions, or setup details you want available the next time you or a teammate opens Aurora in this workspace.

Learnings are enabled by default. They are not configurable in the dashboard today.

Skills

Aurora inbuilt skills

Aurora includes inbuilt skills that review and improve your agents without manual analysis. Two skills are available today:

Prompt review: Ask Aurora to review an agent’s prompt. It checks for clarity, missing guardrails, conflicting instructions, and suggests improvements based on Synthflow best practices.
Call analysis: Ask Aurora to review previous calls for an agent and identify patterns, failure points, and concrete prompt or configuration changes that could improve outcomes.

Both skills work from the Aurora sidebar. Describe what you want in plain language, for example “review the prompt for my sales agent” or “look at recent calls for my support agent and suggest improvements”.

Attachments

Attach images, call scripts, SOPs, and other supported text-based files to a message, or reference URLs where the product supports them. Aurora reads that material to draft prompts, populate knowledge bases, or scaffold actions that match how your team actually works.

Example prompts

Click the copy control on any prompt to paste it into Aurora, then adjust names, tools, and files for your workspace.

Agent creation

Example prompt
Create an agent that qualifies inbound leads, asks discovery questions, and books meetings with qualified prospects.
Build a sales assistant that calls new website leads, confirms their interest, and schedules a demo.
Turn our lead qualification workflow into an agent that handles calls, captures answers, and updates the CRM.

Action creation

Example prompt
Create an action that sends a Slack message when a high-intent lead books a meeting.
Create an action that updates HubSpot after every completed call.
Create an action that sends a follow-up email when a prospect asks for pricing.

Knowledge base

Example prompt
Create a knowledge base from our sales playbook, pricing sheet, and onboarding docs.
Upload our product docs and turn them into a knowledge base the agent can use during calls.
Create a knowledge base so the agent can answer questions about features, pricing, and integrations.

Calls and simulations

Example prompt
Run a simulation of a call where a prospect asks about pricing and implementation time.
Show me recent calls where prospects mentioned competitor tools.
Simulate a lead qualification call for a mid-market SaaS company.

FAQ

Where do I open Aurora?

Open Aurora from the main sidebar in the Synthflow dashboard. You get one chat thread per conversation: type a request, attach files when you need them, and review what Aurora did in the same place.

What can Aurora do?

Aurora is connected to your workspace data and can act on your behalf. It can build and update agents, configure actions, manage knowledge bases, analyze calls and analytics, run simulations, search Synthflow docs, and more through the capabilities it uses. See Example prompts for starting points.

Can Aurora change an agent I already built?

Yes. Aurora is not only for new agents. Describe the agent and the change you want, and Aurora can update prompts, voices, actions, and other configuration on existing agents. See Update existing agents.

What is the difference between Memory and Learnings?

Memory keeps context inside the current Aurora chat, such as which agent you are editing or files you already shared. Learnings are saved at the workspace level and apply across Aurora conversations, for example naming conventions or setup preferences you want every future chat to respect.

How is Aurora Memory different from Memory Groups?

They are separate features. Aurora Memory applies only to your Aurora chat thread. Memory of past calls stores summaries of voice agent interactions with contacts and injects them into phone conversations. Changing one does not change the other.

What can I attach to a message?

You can attach images, call scripts, SOPs, and other supported text-based files, or reference URLs where the product supports them. See Attachments. If a format is not accepted, Aurora will tell you in the thread.

Can I turn off or edit Memory and Learnings?

No. Memory and Learnings are enabled by default for Aurora. There is no settings screen to disable them or edit stored Memory or Learnings in the dashboard today.

Do I still use the dashboard for detailed settings?

Yes. Aurora orchestrates work across the product, but dedicated pages such as voice configuration, the agent editor, actions, and simulations remain where you review and tune every setting manually.

How is Aurora different from the Claude Code and Codex connectors?

Aurora runs in the Synthflow dashboard with Memory, Learnings, and UI cards for calls and tables. The Claude Code and Codex connectors let you manage the same workspace from your AI tool instead, authenticating with an API key. Both draw on the same capabilities, but Aurora is in-product while the connectors run where you already work.