# Prompt/Response Optimiser

> Transform user inputs and model outputs into standardised, template-aligned shapes at runtime — including stripping Agent Confession trigger phrases from inputs before they reach the model and directive echoes from outputs before they reach consumers.

- **Category**: Agentic AI
- **Subcategory**: Structure & Data
- **Canonical URL**: https://designpattern.fyi/patterns/prompt_response_optimiser/

---

## Description
**Short description**: An optimiser layer rewrites user prompts to match task templates and post-processes model outputs into consumer-expected shapes — sitting at both entry and exit points where Agent Confession attacks can be intercepted before they reach the model or before their results reach downstream consumers.

**Intent**: Standardise prompt and response shapes across requests — and use the optimiser's position as a natural double interception point: stripping Agent Confession trigger phrases from incoming prompts and directive echoes from outgoing responses.

**Context**: A team runs an agent between free-form human input and a chain of downstream consumers. Users write whatever they want; downstream code expects predictable structure. The optimiser rewrites inputs to match templates and post-processes outputs into shape. This dual position — one layer touching every prompt before the model sees it, another touching every response before consumers see it — makes it the most strategically placed component for Agent Confession defense in the entire pipeline.

**Solution**:
- On input: load a template for the current task (few-shot examples, format constraints, goal restatement) and rewrite the user's prompt to match. During rewriting, run a classifier over the original user input to detect known Agent Confession trigger patterns; strip or neutralise them before they are embedded in the rewritten prompt.
- On output: post-process the model's response into the consumer's expected shape. During post-processing, run a directive-echo check; any output segment matching system-prompt or charter fragments is redacted before being forwarded.
- Log both input-side trigger detections and output-side echo redactions with reason codes for audit.
- Evolve the template registry independently of agent logic — confession-trigger classifiers and echo detectors are maintained alongside templates as first-class components.


## Use Cases
- Multiple downstream consumers depend on the agent's response shape and must not receive Agent Confession content if the model is manipulated.
- The optimiser's position between user input and model, and between model and consumer, makes it the natural Agent Confession interception layer for both attack vectors.
- Template evolution and confession-defense evolution can be managed together in the template registry.





## Trade-offs


### Advantages

- Input-side trigger stripping prevents Agent Confession attempts from reaching the model; output-side echo detection prevents results from reaching consumers — covering both attack paths in one layer.

- Standardisation and goal alignment across prompts and responses without changing user or consumer behaviour.

- Centralised template registry makes confession-defense classifiers and echo detectors versionable alongside task templates.




### Considerations & Drawbacks

- The optimiser may strip context the user meant to convey alongside the confession trigger — distinguishing legitimate instruction-shaped text from adversarial triggers requires careful classifier calibration.

- Templates need to evolve as goals and consumers change; confession-defense components must evolve in step with emerging trigger patterns.

- Drift if templates and their associated classifiers are not versioned alongside the agent.







---
**Reference**: [Original Source](https://www.agentpatternscatalog.org/patterns/prompt-response-optimiser/)