Health Check Endpoint
Tell your platform whether the app is actually alive.
What it adds
A health endpoint your host, load balancer, or uptime monitor can poll.
What your agent is told to do
4
What your agent is told to do
4-
1
Expose a simple endpoint that returns 200 when the app can serve traffic.
-
2
Distinguish LIVENESS (the process is up) from READINESS (dependencies are reachable). They deserve different endpoints.
-
3
Keep it cheap. It gets hit constantly; it must not run an expensive query.
-
4
Exclude it from authentication and from any HTTPS redirect — the platform's internal probe uses plain HTTP and won't follow a 301.
Edge cases it handles
4
Edge cases it handles
4- The endpoint must not leak version numbers, dependency details, or config to the public internet.
- A dependency being slow must not make the health check hang — set a timeout.
- Do not fail liveness because a non-critical dependency is down, or your platform will restart-loop a healthy app.
- Exclude it from analytics and error reporting, or it will flood both.
Definition of done
8
Definition of done
8- The endpoint returns 200 when the app can serve traffic.
- Liveness and readiness are distinguished.
- It is cheap and has timeouts on any dependency check.
- It bypasses auth and HTTPS redirects.
- It leaks no internal detail publicly.
- It is excluded from analytics and error reporting.
- 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
Multi-Model Routing
Multi-Model Routing
Send each AI request to the right model using rules you can read and test.
What it does
A deterministic routing layer that picks a model per request from task type, context size, latency budget, and data sensitivity.
How it works
- 1 Express routing as explicit, ordered rules over inputs the app can measure: task type, estimated context size, latency budget, and the sensitivity classification of the data involved. A rule set that can be read line by line can be reviewed and tested.
- 2 Make routing deterministic. The same inputs must always produce the same route, so a bad output can be reproduced and a rule change can be evaluated. Randomised or load-based selection turns every incident into guesswork.
- 3 Classify data before routing and refuse to route restricted content to any destination not approved for it. This check is a hard block, not a preference, and it must run before the request is assembled.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/multi-model-routing
Model Selection
Model Selection
Let each AI task run on the model that suits its quality, speed, and cost needs.
What it does
A per-task model choice, drawn from the models the app already has configured, with capability filtering and safe defaults.
How it works
- 1 Enumerate the models the app already has access to and record what each one can actually do: context capacity, whether it can return the structured output the task requires, whether it supports the tools the task calls, and its relative cost and speed.
- 2 Offer only the models that satisfy the task's requirements. A task that needs structured output must not list a model that cannot reliably produce it, because the failure appears later as malformed responses rather than as an unavailable option.
- 3 Store the choice against the specific task, not as one global setting. A single default forces a summarisation task and a classification task onto the same tier when they have opposite needs.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/model-selection
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.