Prompt Versioning
Tie every AI output to the exact prompt version that produced it.
What it adds
Immutable, numbered versions of each prompt, with the run configuration recorded and every output stamped with the version used.
What your agent is told to do
5
What your agent is told to do
5-
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.
-
4
Keep the active version per environment separate, so promoting a version in a test environment does not change what production runs. Publishing to production must be a deliberate act.
-
5
Support rollback to any earlier version without discarding newer drafts. Rolling back must change which version is active, not delete the work that came after it.
Edge cases it handles
8
Edge cases it handles
8- A published version must be immutable. Allowing an edit in place means every output stamped with that version is now attributed to text that no longer exists.
- Model tier, parameters, available tools, and output schema must be recorded with the version. Without them, a reproduction attempt runs the same words under different conditions and gets different results for reasons nobody can see.
- Rolling back must leave newer drafts intact and re-promotable, rather than treating rollback as a delete of everything after the target version.
- Each environment must track its own active version, or a test promotion silently changes what customers receive.
- Comparing versions is meaningless unless both are run against the same fixed evaluation cases. Store a shared set of cases and their results per version rather than judging on ad hoc examples.
- An output stamped with a version that has been deleted must still resolve to something readable, so version records must be retained for as long as any output references them.
- Version storage grows without limit if every keystroke is a version. Distinguish drafts, which may be overwritten, from published versions, which may not.
- A run started against one version and completed after a promotion must be recorded under the version it actually used, not the one that is active when it finishes.
Definition of done
8
Definition of done
8- Publishing creates a new immutable version and never modifies an existing one.
- Each version records the model tier, parameters, available tools, and expected output shape used with it.
- Every generated output is stamped with the version that produced it and remains traceable later.
- Each environment has its own active version and promotion between them is explicit.
- Rollback changes the active version without deleting newer drafts.
- Two versions can be compared against the same stored evaluation cases with results retained per version.
- The feature matches the existing design system.
- No existing functionality is broken.
Related features
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
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
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.