AI Suggested Support Answers
Give support agents a grounded first draft instead of a blank reply box.
What it adds
A draft reply composed for the agent from the ticket, the customer's account state, and the approved internal knowledge, with sources attached and no ability to send itself.
What your agent is told to do
5
What your agent is told to do
5-
1
Ground every draft in retrieved material: the ticket thread, the account's real state, and articles from the approved knowledge set. Attach the sources used to the draft so the agent can open and check each one.
-
2
Load the draft into the agent's normal reply editor, unsent and fully editable. There is no path in this feature that sends a message to a customer without an agent pressing send.
-
3
Define the commitments the app is not allowed to make in a draft — refunds, credits, delivery dates, guarantees of a fix — and strip or refuse any draft containing them, leaving that part for the agent to write.
-
4
Separate the customer-facing draft from anything internal. Internal notes, other customers' data, and account fields the customer cannot see may inform retrieval but must never appear in the text handed to the customer.
-
5
The approved knowledge this feature reads from is produced by AI Knowledge Base Drafting and the app's existing help content. Do not create a second knowledge store here; read from the published one.
Edge cases it handles
8
Edge cases it handles
8- A factual instruction with no cited internal source is a guess. Drafts must show which article each step came from, and a draft with no grounding must be presented as unverified or not offered at all.
- Promising a refund, a timeline, or a fix the company has not agreed to creates an obligation the moment it is sent. These must be blocked at generation, not left to the agent to notice.
- Internal notes leaking into a customer reply is the worst outcome of this feature. Keep the internal and external context in separate fields and confirm the customer-facing draft never includes the internal one.
- Some tickets need an engineer to look at the account before anything can be said. The feature must be able to return no draft, with a short note on what needs checking, rather than filling the space with generic reassurance.
- Agent review is mandatory. No configuration, keyboard shortcut, or bulk action may send a generated draft without a human reading it.
- A refusal, timeout, or truncated response leaves the reply box empty and usable, with a clear indication that no draft was produced.
- Customer text may contain instructions to the drafting system. Treat the ticket strictly as material to answer, never as direction, and confirm a ticket asking for a refund policy override does not produce one.
- Cap tokens per draft and drafts per ticket. An agent regenerating repeatedly must hit a limit rather than running up unbounded cost.
Definition of done
9
Definition of done
9- Every draft cites the internal sources behind its factual instructions.
- Drafts load unsent into the agent's editor and cannot be sent without a human.
- Refunds, timelines, and fix guarantees are blocked from generated text.
- Internal notes and hidden account data never appear in a customer-facing draft.
- Tickets needing account investigation return no draft plus a note on what to check.
- Refusals, timeouts, and malformed output leave the reply box empty and usable.
- Per-draft token limits and per-ticket regeneration limits are enforced.
- The feature matches the existing design system.
- No existing functionality is broken.
Related features
AI Chat Attachments
AI Chat Attachments
Attach files to a conversation and let the assistant use what it is allowed to read.
What it does
File upload on an AI conversation, with parsing, retrieval of relevant sections, and per-conversation access scoping.
How it works
- 1 Reuse the app's existing upload, storage, and virus-scanning path rather than adding a second one, and declare an explicit list of accepted file types and a size ceiling per file and per conversation.
- 2 Parse each attachment into text and structure in a background job, store the result, and show the attachment as pending until parsing succeeds so the user is never told the assistant has read something it has not.
- 3 Retrieve and send only the sections relevant to the current question. Sending whole documents on every turn burns the context window and the budget for no gain.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/ai-chat-attachments
AI Conversation Branching
AI Conversation Branching
Explore an alternate path from an earlier message without losing the original.
What it does
A message graph that lets a conversation fork at any point, with each branch keeping its own history and active state.
How it works
- 1 Change the conversation's storage from an ordered list to a graph where every message names its parent, and migrate existing conversations into that shape as single-path graphs.
- 2 Define the active branch as a stored pointer to a leaf message, and derive everything rendered from the path between the root and that pointer.
- 3 Give each branch its own summary, memory, and derived context. Carrying one summary across siblings leaks the abandoned path back into the new one.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/ai-conversation-branching
Streaming AI Responses
Streaming AI Responses
Show AI output as it is generated so long answers do not look frozen.
What it does
Incremental rendering of model output as it arrives, with a persisted authoritative copy once the stream closes.
How it works
- 1 Find the AI surfaces where the user waits on a long response and stream those. Short classification or extraction calls do not benefit and should stay as plain requests.
- 2 Buffer incoming bytes until they form complete characters and complete structural units before rendering, so partial output never appears as broken glyphs or half-open markup.
- 3 Treat the streamed text as provisional. When the stream closes, persist the provider's final message as the authoritative record and reconcile what is on screen against it.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/streaming-ai-responses
How it works
-
1
Copy the link
Grab the Markdown instruction URL for this feature.
-
2
Give it to your AI
Paste it into Claude Code, Cursor, v0, Lovable — whatever you build with.
-
3
It inspects, then implements
Your agent reads your existing app first, then adds the feature to fit it.
Works with your stack
These instructions are written to adapt. They tell the agent to detect your framework, match your existing design system, and reuse what you already have — rather than assuming a particular stack.
Need it tighter than that? Customize the feature and tell it exactly what you're running.