Technical staff gaining approved access to AI
Previously had effectively no approved access
Evidence library
What you need before adopting AI
Patty publishes more than product explanations. We document what changed in operation, which technical choices mattered, what has been verified, and what remains outside the evidence.
- Operational changeCustomer
- Validation methodMethod
- Technical designSystem
- Scope and caveatsLimits
Patty perspective
Enterprise AI is an operating-system problem, not a model-selection exercise
A good model alone is not enough. Before AI joins real work, the organization must be able to explain who approved what.
This hub gathers the material for setting that standard. We share evidence you can review, not sales claims.
Evidence system
What we publish as evidence
Different questions require different forms of evidence.
01
Example scenarios
Scenarios covering prior conditions, scope, implementation, observed change, and difficulty.
02Technical reports
Benchmarks and measurements with hardware, build, data, method, and explicit caveats.
03Security & governance
How AI identity, data boundaries, approval, execution, and evidence connect at runtime.
04Open technology
Specifications and conformance paths that let third parties inspect delegation and execution receipts.
05Blog
Current perspectives from product, technology, security, and enterprise AI operations.
Reader paths
Read by responsibility
The first question changes with the reader’s accountability.
- 01Example scenarios → AI workforce → governance
Executives
Does AI investment translate into operating outcomes and accountable ownership?
- 02Security & governance → open specifications
Security & compliance
How are data, models, tool execution, and approvals controlled and proven?
- 03Mirr Code → monographs → measurement reports
Engineering
How do agents work in Korean development environments and legacy systems?
- 04Models & training → inference → benchmarks
AI & infrastructure
How should training and GPU inference operate under real constraints?
Example scenario
From prohibited AI to a controlled everyday capability
An example scenario for a public-sector environment that cannot use external generative AI: model serving, the coding agent, policy, and execution records kept inside.
View the scenario- Technical personnel
- Approximately 70
- Deployment
- On-premise · controlled network
- Inference
- Internal distributed GPU infrastructure
- Expanded operation
- Approximately 15–20 specialized agents
Throughput for selected AI-suitable workflows
Not organization-wide productivity; compares manual baselines for code understanding, tests, and repetitive changes
First useful understanding of unfamiliar code
Selected cases that previously consumed most of a day
Research & reports
The method comes before the number
A result matters only when the reader can see what was measured, where, how, and what the result cannot claim.
Finished-path measurements for an engine-native agent browser
A measurement of the complete observe→classify→park→approve→dispatch path when an AI agent is embedded in the browser engine. Semantic snapshots remained around 14–16ms in the tested fixtures, and the governed engine cycle completed in under 25ms.
Read reportDesigning a benchmark corpus for coding agents
Design notes for an end-to-end corpus stratified across eight workload classes, a 50-instance SWE-bench Verified subset, and a context-retention A/B harness, including anti-guess tasks and scorer validation.
Read reportPublication standard
Five questions attached to every claim
Who says it, what was observed, where it applies, how it can be reproduced, and what we are not claiming.
- 01
Source
Separate customer report, pilot observation, internal measurement, and public research.
- 02
Conditions
Record period, participants, hardware, data, and build.
- 03
Method
Explain the procedure that produced the measurement or judgment.
- 04
Result
Separate observed change from its implications for a decision.
- 05
Limits
State where evidence does not support organization-wide, causal, or certification claims.
Explore by problem
Start with the problem your organization is trying to solve
On-premise and closed-network AI
Keep source, prompts, and inference inside the controlled environment.
Korean AI coding
Execution designed around HWP/HWPX, IME, initial consonants, Korean instructions, and local engineering practice.
AI security and governance
Identity, policy, approval, audit, and verifiable execution evidence.
AI agent management
Operate responsibility, tasks, escalation, and resources across many agents.
GPU serving and inference
Distributed serving, scheduling, KV cache, and MoE execution architectures.
Korean RAG and document understanding
Retrieve, extract, and validate Korean documents and business context.