AI Agents: Known Limitations and Workarounds

AI Agents are powerful, but there are some platform-level limitations to be aware of. Use the recommended workarounds below to ensure your Agent behaves consistently and reliably.

Conversation visibility

AI Agents have limited visibility into conversation metadata, history, and internal context.

Channel and source metadata

AI Agents automatically receive basic channel context, including the channel type, channel name, and channel ID. With the right instructions, your AI Agent can use this to adjust its response length, formatting, tone, and behavior to suit different channels.

Ads attribution from Meta and TikTok

When a conversation is opened from a Meta Click-to-Chat Ad or a TikTok Messaging Ad, your AI Agent automatically receives an Ads Context block alongside the channel context. No configuration is required. This block includes:

• Ad Platform: Meta or TikTok

• Ad Campaign: The campaign name

• Ad Group: The ad group or ad set name (where available)

• Ad Name: The individual ad or creative name (where available)

This means you can write instructions that adapt based on which ad a Contact came from. For example, opening with a campaign-specific message, routing to a different team, or triggering a different conversation flow.

Note: The Ads Context block is only included if the ad entry event occurred within the last 20 messages of the conversation. If the conversation has progressed beyond this window, no ad context is included. If a contact opened more than one ad within the last 20 messages, only the most recent ad entry is included. Write your instructions to handle both cases.

Limitations to be aware of:

• Channel and source context are both provided at a high level. While your AI Agent automatically receives structural metadata (such as ad platform, campaign, and ad name), it has no visibility into the actual content of the ad. You'll still need to write instructions that tell your agent what to do based on that context, and what the ad is about.

• AI Agents do not receive source metadata automatically other than when a conversation is initiated from a Meta or TikTok paid ad, which provides the Ads Context block described above.

Recommended workaround:

If your use case depends on knowing where a Contact came from outside of paid ads, use a Workflow to capture information such as ad content, and store it in a Contact field.

For example:

• Create a Workflow with a Conversation Opened trigger

• Add conditions based on channel or source

• Update a Contact field such as Lead Source or Campaign Name

You can then instruct your AI Agent to reference that Contact field in its instructions. This ensures consistent and reliable behavior, even when channel or source details are not available automatically.

Example prompts for channel-aware behavior

You can guide your AI Agent to adapt its responses by explicitly instructing it how to behave across different channels. Here are some example prompts you can use:

Adjust response length and tone

If this conversation is happening on Instagram or TikTok, keep replies short (1–3 sentences), friendly, and conversational. Avoid long explanations.

If this conversation is happening on WhatsApp, you may provide more detailed responses, but keep them concise and easy to read.

If this conversation is happening via Email, use a more structured and formal tone. Longer explanations and clearly formatted responses are acceptable.

Control formatting and content

Do not share links when responding on TikTok unless the Contact explicitly asks for one.

When responding via Email, you may include links, bullet points, and step-by-step instructions where appropriate.

Channel-based behavior and escalation

If the conversation is happening on Instagram or Facebook and the Contact asks about billing, payment, or account-related issues, escalate immediately to a human agent.

If the conversation is happening on WhatsApp, attempt basic troubleshooting first before escalating, unless the Contact appears frustrated.

Referring to the conversation

When referring to where the Contact is messaging from, say “this chat” or “this conversation”. Never mention the channel name explicitly.

Assignment history

AI Agents cannot view assignment history or past assignment actions, including whether another AI Agent assigned the conversation to them.

This means:

• If AI Agent 1 assigns a conversation to AI Agent 2, AI Agent 2 does not know it has just been assigned.

• AI Agent 2 cannot distinguish between messages sent by AI Agent 1 vs. messages sent by a human agent.

• As a result, AI Agent 2 may start responding without knowing the conversation context or may repeat actions unnecessarily.

Recommended workaround:

If you are chaining multiple AI Agents, include a clear handoff message that signals the next Agent to start.

Example: In AI Agent 1’s instructions

Before assigning the conversation to AI Agent 2, send a message: ‘I’m transferring you to AI Agent 2 who will help you next. Then assign to AI Agent 2.

Example: In AI Agent 2’s instructions

Only start your top-level flow when you see the message: ‘I’m transferring you to AI Agent 2 who will help you next.’ When you see it, greet the user and begin your qualification/support flow.

This ensures:

• AI Agent 2 knows the handoff happened

• AI Agent 2 starts at the right moment

• Users get a smooth transition between agents

Assignment via external tools

When an AI Agent is assigned to a conversation via an external tool — such as Developer API, n8n, or Make.com — the assignment itself will not trigger the AI Agent to reply.

This is expected behavior. Respond.io restricts this to prevent AI Agents from bulk-replying when multiple conversations are assigned simultaneously via automation.

Once assigned, the conversation will appear as assigned to the AI Agent. However, the AI Agent will not proactively send a message. The AI Agent will respond once the Contact sends a message.

Note: There is no workaround for this limitation.

Internal context and message history

AI Agents cannot see internal comments and can only access the most recent 20 messages in a conversation.

Because of this, AI Agents should not rely on channel origin, internal notes, or older conversation context when making decisions.

Recommended workaround:

Store important context in Contact Fields or Lifecycle stages, and instruct the AI Agent to reference those instead.

For example:

• Use Workflows or human processes to keep fields like Plan Type, Customer Status, or Issue Category up to date

• Use Lifecycle stages (e.g., New Lead, Qualified Lead, Customer) to guide how the Agent responds

• In your AI Agent instructions, explicitly reference these fields (e.g., “If Lifecycle is Customer, prioritize support-related responses.”)

This ensures the AI Agent can make consistent decisions using reliable, structured data, even with limited access to older messages or internal comments.

External capabilities

AI Agents primarily operate within respond.io but can now interact with external systems using the AI Agent action: Make HTTP requests. This allows AI Agents to call external APIs to retrieve real-time data or trigger actions in third-party systems.

Learn more about AI Agent action: Make HTTP requests here.

Message types and attachments

AI Agents can only send text messages and are currently unable to send files or media, such as:

• Files (e.g., PDFs, documents)

• Images

• Videos

• Voice notes

• Stickers or other rich media

This means AI Agents should not be used for processes that require sending attachments (e.g., brochures, onboarding documents, invoices, or screenshots).

Recommended workaround:

Use a Workflow step or assign the conversation to a human agent when the Contact requests files or media. You can also configure a Workflow to automatically send the required file (if supported by the channel) before returning control to the AI Agent.

Receiving unsupported messages

When a Contact sends a message type that respond.io cannot process, such as a message reaction or other unsupported format, the AI Agent receives an [Unsupported message] signal in the conversation history.

This means your AI Agent is now aware when an unsupported message is received and can respond accordingly. You can also write instructions to customize how your AI Agent handles these cases.

Example prompts for handling unsupported messages:

Ask the Contact to resend as text:

If you receive [Unsupported message], reply: "It looks like I wasn't able to receive your last message. Could you send it as a text message instead?"

Ignore and do nothing:

If you receive [Unsupported message], do not reply. Wait for the Contact's next message.

Acknowledge without mentioning the limitation:

If you receive [Unsupported message], reply: "I'm not able to view that message type. Feel free to describe what you need and I'll be happy to help!"

Model configuration

AI Agents do not support manual temperature settings because newer AI models no longer expose temperature controls.

If you want to adjust the AI Agent’s “creativity” (similar to temperature), the best approach is to prompt for it directly in your Instructions. For example, you can guide the AI to behave more creatively or more strictly depending on your use case.

High creativity (higher “temperature”):

Respond warmly and creatively in the customer’s tone.

Low creativity (lower “temperature”):

Answer the customer’s question using only the provided company knowledge sources and the conversation history. Do not guess or add new information.

This gives you better control over tone and consistency without needing a dedicated temperature setting.