ompsure
  • Reviews
  • Pro
  • Pricing
  • Template
Sign InSign Up
ompsure

Code quality that happens automatically.
Free for personal use.

Audience

  • Who's It For?
  • For Creators
  • For Developers

Features

  • Code Graph
  • Security
  • Code Review
  • Testing
  • Deployment
  • Memory

Product

  • Plugins
  • Control Panel
  • Proof
  • Catalog
  • How It Works

Plans

  • Pricing
  • Pro Patterns
  • Commercial License
  • Starter Template

Resources

  • Getting Started
  • Documentation
  • Reviews
  • Affiliate Program

© 2026 Et'al Software Solutions. All rights reserved.

  • Template License
  • Plugin License
  • Refund Policy
  • GitHub
Viewing as
ProofPatternsAI Infra

AI Infra

AGENCY

17 patterns · 47 working examples

The non-obvious rule

An AI agent's behavior needs written, versioned rules — like a contract — not scattered prompt tweaks nobody can audit or roll back.

What's covered here

17 patterns · 47 working examples

These aren't chapter titles — each one is an enforced rule your AI builds against. And the patterns don't just teach the shape: the working examples are real code that lands in your project.

AI agents

Modeling an AI persona separately from which model providers back it

AGENCY
Memory graph

A memory graph deliberately kept narrow instead of open-ended

AGENCY
Thinking sessions

Recording an agent's reasoning steps without ever mutating history

AGENCY
Request logs

Reconstructing a full agent turn from its individual model calls

AGENCY
Trust and supervision

How much an AI agent can do unsupervised, and who signs off on the rest

AGENCY
Interaction mode and routing

Letting a human take over an AI conversation and hand it back cleanly

AGENCY
Agent automations as workflows

Recurring AI agent work modeled as workflows instead of task fields

AGENCY
Dynamic grounding prompt

Structuring an agent's prompt so most of it can actually be cached

AGENCY
Agent executor runtime

The control loop between a model and its tools, with real checkpoints

AGENCY
Model provider abstraction

Swapping model providers without rewriting every call site

AGENCY
Tool registry and dispatch

Giving an AI agent and a UI form the exact same tool, not two versions

AGENCY
Screen registry and routing

Letting an AI agent navigate the app's real screens, not a shadow copy

AGENCY
Guardrails constitution

Guardrails an agent can't argue its way around under pressure

AGENCY
Fleet and delegation

Delegating work across a fleet of agents without one bottleneck plane

AGENCY
Agent persona and pressure

Keeping an agent's persona and limits from drifting under sustained pressure

AGENCY
Agentic patterns map

Choosing an agent framework versus building the loop yourself

AGENCY
Task aware model routing
AGENCY

What breaks without it

Nobody can answer "why did the AI do that" after the fact, because the behavior was never written down.

All areas

Back to the full census.

Why this works

The mechanism argument that applies here.

Pricing

See which plan unlocks ai infra.

See your plan's patterns