AI Tool Calling Framework
Give the model a governed catalogue of app actions instead of ad hoc, unchecked calls.
What it adds
A registry of app capabilities exposed to the model, with per-user scoping, strict argument validation, execution limits, and an audit trail.
What your agent is told to do
5
What your agent is told to do
5-
1
Define each tool once in a registry with its purpose, its argument schema, the permission it requires, and whether it reads or writes. Anything not in the registry is not callable.
-
2
Build the tool list per request from the current user, workspace, and context. Do not publish the full catalogue and rely on the model to avoid the tools it should not use.
-
3
Validate every argument against the schema and reject the call on any deviation. Then apply the same authorization checks the ordinary interface applies, in the app's own code, because a tool call is an untrusted request that happens to arrive from a model.
-
4
Enforce ceilings on the number of calls per turn, recursion depth, wall-clock time, and token or cost spend. Stop cleanly at the ceiling with an explanation rather than looping until something times out.
-
5
Do not let a write tool execute directly when a user-visible plan is warranted. Approval, plan display, and partial-failure reporting are owned by AI Agent Actions with Approval; this framework owns the catalogue, validation, and limits it runs on.
Edge cases it handles
8
Edge cases it handles
8- The tool list is scoped per request. A user who loses access mid-conversation must not be able to call a tool that was available earlier in the same thread.
- Reject any call whose arguments fail the schema, including extra fields, wrong types, or out-of-range values, and return the rejection to the model as a correctable error rather than coercing the value into something plausible.
- Tool results are untrusted input. Text pulled from a record, a document, or a third party may contain instructions aimed at the model, so it must be clearly delimited as data and must never be able to grant permissions or expand the tool list.
- Ceilings on call count, recursion, execution time, and spend must all be enforced, and the loop must terminate visibly at whichever is hit first. A model that calls the same read tool repeatedly is the normal failure, not the rare one.
- Record every call, its arguments, its outcome, and its duration, with secrets, tokens, and personal data redacted before anything is written. The log exists to explain what happened, not to reproduce the payload.
- A tool that fails, times out, or is unavailable must return a structured failure the model can reason about, rather than an exception that ends the conversation.
- Write tools need idempotency keys, because a model that does not see a result will call again.
- Registry changes are a compatibility surface. Removing or renaming a tool must not break conversations already in flight.
Definition of done
9
Definition of done
9- Only registered tools are callable, and the list offered is built per request from the current user and context.
- Every argument is validated against a strict schema, and failing calls are rejected rather than coerced.
- Authorization is enforced in application code on every call, independently of the tool list.
- Call count, recursion depth, execution time, and spend ceilings are enforced and terminate the loop cleanly.
- Tool output is treated as untrusted data and cannot expand the model's permissions or tool list.
- Every call and outcome is recorded with secrets and personal data redacted.
- Tool failures return a structured result rather than ending the conversation.
- 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 Suggested Support Answers
AI Suggested Support Answers
Give support agents a grounded first draft instead of a blank reply box.
What it does
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.
How it works
- 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.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/ai-suggested-support-answers
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
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.