API Explorer
Let developers try real API requests from inside the app.
What it adds
An in-app request builder that runs calls against your API and shows the exact request and response.
What your agent is told to do
6
What your agent is told to do
6-
1
Generate the request form from the API's own schema so parameters, types, and required fields cannot drift from the real endpoints.
-
2
Execute calls through a server-side proxy that attaches credentials, so a key is never placed in browser-visible code or the network tab.
-
3
Restrict the proxy to your own documented API endpoints only. An explorer that will call an arbitrary URL is an SSRF hole with a nice UI.
-
4
Run requests with the current user's real permissions and show endpoints they cannot call as denied rather than hiding them — a silent omission reads as a missing feature.
-
5
Mark unsafe methods clearly and confirm before sending. A POST from a documentation page still creates real data.
-
6
Do NOT store request or response bodies in history without redacting authorization headers, tokens, and any field the API marks sensitive.
Edge cases it handles
6
Edge cases it handles
6- Copyable curl and code samples must contain a placeholder, never the live credential the proxy used.
- Very large responses will freeze the browser if rendered whole. Truncate with a way to download the full body.
- Requests must time out and be cancellable, or a slow endpoint hangs the panel indefinitely.
- Explorer traffic counts against rate limits. Label it distinctly so a developer can tell exploration from production usage.
- The explorer must follow the API version the account is pinned to, and say which version it is calling.
- Where the API has a sandbox or test mode, default the explorer to it and make switching to live an explicit, obvious act.
Definition of done
8
Definition of done
8- The request form is generated from the API schema, not hand-maintained.
- Credentials are attached server-side and never exposed to the browser.
- Only documented first-party endpoints are reachable through the proxy.
- Permission-denied endpoints are shown as denied rather than omitted.
- Stored history has authorization headers and sensitive fields redacted.
- Generated code samples use credential placeholders.
- The feature matches the existing design system.
- No existing functionality is broken.
Related features
AI Cost Budgets
AI Cost Budgets
Cap what AI features are allowed to spend before the bill arrives.
What it does
Monetary spending limits on AI work, scoped by workspace, feature, and time period, enforced before a run starts.
How it works
- 1 Find every place the app calls a model and route all of them through one accounting point that records estimated and actual spend against a scope. A budget that only covers the chat feature is not a budget.
- 2 Estimate the cost of a run from the size of its input before dispatching it, and refuse anything that would exceed the remaining budget on its own.
- 3 Reserve the estimate against the budget when the run starts, then reconcile to the real usage figures when it finishes, releasing whatever was over-reserved.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/ai-cost-budgets
Prompt Versioning
Prompt Versioning
Tie every AI output to the exact prompt version that produced it.
What it does
Immutable, numbered versions of each prompt, with the run configuration recorded and every output stamped with the version used.
How it works
- 1 Make every publish create a new immutable version rather than overwriting the previous text. Editing history in place destroys the only record of what produced last month's outputs.
- 2 Capture the whole run configuration with each version, not just the wording: which model tier and parameters were used, which tools were available, and the expected output shape. A prompt that behaves differently under different settings is not one prompt.
- 3 Stamp every generated output with the version identifier that produced it, and keep that stamp with the record so an output found later can be traced back to its exact instructions.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/prompt-versioning
Retrieval Debugger
Retrieval Debugger
Show exactly which sources, chunks, and scores produced a given AI answer.
What it does
A per-answer inspector showing the query as issued, the filters applied, the candidate chunks with their scores, and what reached the model.
How it works
- 1 Capture for each answer the query as it was issued, the filters applied, the candidates returned with their scores, and which of those actually made it into the request after the context ceiling was applied.
- 2 Show results after permission filtering, with a count of how many candidates were excluded and why. Displaying the pre-filter set turns the debugger into a way to read content the viewer cannot open.
- 3 Present each scoring stage separately — keyword, semantic, and any reranking — because a chunk that ends up first overall may have been rescued by one stage after being buried by another, and a single blended number hides that.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/retrieval-debugger
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.