Engineering reference

From Blocking to Transforming: How My Prompt Hook Evolved

A first-person account of changing a prompt hook from blocking to transformation, with integration behavior and edge cases.

Book a 30-minute call Compare services

Methods, definitions, and examples for the topic discussed here. Check applicability against the task and operating conditions.

Mario Alexandre · March 26, 2026 · auto-scatter prompt-hook sinc-llm

This article follows the design changes from the first prompt hook to the prompt-transforming version, including blocking, fallback, and integration lessons.

Version 1: The Blocker

My first prompt hook was defensive. I was worried about bad prompts reaching the model. I worried about prompts with too little context. I worried about prompts that would make the model ask follow-up questions. I worried about prompts that would start expensive loops. So I built a hook that checked each prompt against a quality score and rejected the ones that scored too low.

v1 — week 1

Quality Gating / Blocking Hook

Hook scores incoming prompts on 3 dimensions (specificity, context presence, constraint clarity). If score below 0.4, rejects prompt and asks user to add more detail before retrying.

Result: annoying. I kept getting rejected on short prompts I knew were fine. Interrupts flow. Abandoned after 3 days.

v2 — week 2

Suggestion Hook

Instead of blocking, the hook suggests improvements to the prompt before sending. "Your prompt is missing constraints — want me to add some?" Requires user to confirm before proceeding.

Result: still interrupts flow. Every prompt requires an extra confirmation step. Exchange rate goes UP, not down. Abandoned after 2 days.

v3 — week 2

Auto-Transform Hook (current)

Hook intercepts every prompt, transforms it into 6-band sinc JSON via Haiku API, injects as system context — all without user involvement. Prompt passes through unchanged. Model gets structure automatically.

Check responses per prompt, API token use, scatter overhead, output quality, and workflow interruption for the same workload.

The Insight That Changed Everything

The key insight was simple: blocking and suggesting both need the user to do something. That creates friction. Friction in a tool that runs on every single prompt is fatal. You stop using the tool. You start hating it. You find workarounds that defeat the whole point.

The transforming design supplies structured context before the model runs. Inspect the generated fields and response rather than assuming the hook establishes output quality.

sinc-LLM — the prompt as a signal to be reconstructed

x(t) = Σ x(nT) · sinc((t - nT) / T)

The author uses the Nyquist-Shannon theorem as an analogy for six-field task specification. Haiku scatter generates a structured prompt; this does not establish perfect intent reconstruction or first-try correctness.

What "Non-Blocking" Really Means

The described non-blocking design passes through the original prompt when the scatter call fails or exceeds its configured 25-second timeout. Check the actual fallback and interruption behavior for your environment.

The described fallback uses templates and keyword rules when the API call fails. Compare its generated fields and output checks with the API-based scatter rather than treating an input score as a quality result.

The Edge Cases I Had to Handle

Three types of input skip the transform completely:

Already sinc JSON: if the input is already a valid 6-band sinc structure, pass it through. Do not scatter it twice. The sinc format is the contract between agents. Scattering it again breaks it.

@agent mentions: if the prompt starts with @, it is routing to a named agent. Do not intercept it. Send it directly. The routing is part of the system design. The scatter hook should not touch it.

/slash commands: same idea. Slash commands are infrastructure instructions, not natural language prompts. Pass them through unchanged.

Everything else gets scattered. One-word prompt: scatter it. "hi": scatter it. A 500-word specification: scatter it. There is no minimum length, no complexity threshold, no shortcut. Every natural language prompt reaches the model with structured sinc context.

// Production AI Engineering

Build AI systems that hold up in production.

sinc-LLM designs, audits, and stabilises production AI infrastructure: from vendor evaluation and cost accountability to incident controls and MCP architecture.

See what we do →

Scope and context

sinc-LLM About Blog Services