Frequently asked questions

Which models can I use? Any model reachable through OpenRouter, OpenAI, Anthropic, a vLLM server or Ollama, configured under your organisation's model providers. Each agent and each LLM node picks its own model.

Why does changing the Model tab not change the model? The workflow's LLM node has a model of its own. A model set on the node overrides the Model tab for that step; a new agent's LLM node has none and follows the Model tab. Create a draft of the workflow, open the LLM node, choose Inherit on the provider (or set the model you want there) and publish. See Models and providers.

How do I make the assistant answer from my documents? Create a knowledge base, add the documents, build an index, test retrieval, then attach the knowledge base in the agent's Knowledge tab. The default workflow already contains a knowledge retrieval node.

How do I add web pages to a knowledge base? Open the knowledge base, choose Add documents → Web pages and paste the addresses, one per line (up to 500 per import). Each page's main text is imported, and the vector index updates by itself when the import finishes. Use Refresh from source when a page changes. Only public addresses can be imported, and importing a whole site at once is planned. See Knowledge bases.

Why was my knowledge base skipped? Open the run in Logs: the knowledge retrieval step shows the reason. "disabled" means the Knowledge retrieval node in the published workflow is switched off; attaching a knowledge base on the Knowledge tab does not switch the node on. Create a draft of the workflow, open the node, turn Enabled on (keep "agent defaults" as the knowledge source so it uses the knowledge bases attached on the Knowledge tab) and publish. Other reasons the step reports: no knowledge base attached, the index not built yet, or the retrieval trimmed away by the context budget.

How much does AgentRow cost? See Plans, pricing and what's next: a one-month trial, then E-commerce, Silver, Gold and Platinum plans that differ by volume and support, with Row or your own model keys, and support seats per team member.

Can I share or sell my agents? You can share them: under Platform → Marketplace an owner or admin shares a tool, a toolbox, an agent or an app as a free listing, public (installers get an editable copy) or private (a sealed copy they can use but not open). Credentials never travel; the installer fills them in. Each version is reviewed before it goes live, and installations are told when you publish a new one and update in place when they choose (Plans, pricing and what's next). Selling, by subscription or one-time purchase, comes later; to register interest as a creator, use the contact form on agentrow.io and choose Marketplace creator.

Why did my agent not use a tool? Open the run in Logs. The toolbox step shows which tools were bound for each model call and why others were excluded (for example, tool selection kept only the top matches). The generation shows the exact tool definitions the model received. If the tool was not bound, raise max tools, pin the tool, or let the model widen its tool set with search_tools.

Why did the model call a tool that was not available? With tool selection on, the model sees which tools are bound and which are not. If another tool's description tells it to call an unbound tool, it may try; the call returns an explicit error and the model binds the tool on its next turn. Pinning companion tools together avoids the extra turn.

How do I let the assistant remember users? Set the agent's Memory tab to "remember this user" and let the app identify users with an identity token. Memory candidates appear for approval unless automatic saving is enabled.

Can end users chat without an account? Yes, when the app's auth context enforcement is "allow anonymous". Switch to "require verified" when the assistant must know who it is talking to.

How do I sign a user in on my website? After login, your backend signs a JWT with the app secret containing at least sub and exp, and your page calls AgentRow.identify(token). Never sign tokens in the browser.

How do I hide tool activity from end users? Per tool, set widget events to hidden. For built-in tools, use the app's Install tab setting. Developers embedding the widget can also turn tool activity off entirely.

What happens when a tool fails? The failure is returned to the model as an explicit error, logged on the tool call, and the model decides how to answer. Nothing is retried or substituted silently beyond the retry policy you configured.

Why was a tool call to an address refused? AgentRow calls only public internet addresses, over http or https, on port 80, 443 or 1024 and above (database and infrastructure ports excepted). The error names the reason: OUTBOUND_ADDRESS_BLOCKED means the host is, or resolves to, a private, local or reserved address; OUTBOUND_HOST_BLOCKED an internal host name or one without a dot; OUTBOUND_PORT_BLOCKED a port that is not allowed. Publish the service at a public https address with its own authentication. See Guardrails, approvals and safety.

How do I test changes without affecting users? Edit the draft and use the test chat. End users keep the published version until you publish.

How can I see what a run cost? Open the run: tokens and cost appear per generation and in the run total. Analytics aggregates them by agent, app, model and period.

Where are conversations stored and can I delete them? In your AgentRow organisation. Deleting a conversation removes its messages, runs, logs and checkpoints; shared retrieved text is kept only while other conversations reference it.

Can I build my own chat UI instead of the widget? Yes. The widget script exposes a headless client with the same session, streaming and conversation methods, and the end-user API can be called directly from your own frontend or backend.

Can agents call other agents? Not as a tool: the agent tool type is disabled (see Guardrails, approvals and safety). An app routes between several agents instead: add an Agent node for each on the app's Workflow tab, behind a Router (Apps and end users).

How do I connect my Shopify store? Install the AgentRow app on the store and open it in the Shopify admin (Apps → AgentRow). Choose Link to AgentRow, sign in, and pick the organisation and the chat app that answers shoppers. Then switch on AgentRow chat under App embeds in the theme editor, create Shopify store tools (Tools → New tool → Shopify store) and attach them to the agent, add a Shopify store node to the app's Chat (in), and publish the app. See Shopify store assistant.

What is a toolbox? The workflow node that holds the tools for a model call and runs the calls the model makes. Agents can have more than one, each with its own tools, selection rules and limits.

What is Finalize? The last node of an agent workflow. It produces the visible answer, applies formatting and citations, and is the only place from which text streams to the user.