Build Notes & Research Archive

Technical notes, with the evidence boundaries visible.

Concise architecture notes from projects I have built, plus dated research notes on AI systems and models. Reading times are calculated from the actual text.

Editorial standard: project metrics refer to repository tests or controlled scenarios unless a live production source is linked. Model specifications change; verify the dated primary sources inside each research note.

LLM Infra Aug 2026 · 3 min read

TokensCache: Testing a 35.5% Token Reduction in a Controlled Agent Benchmark

How exact and semantic caching were evaluated with 92 repository tests and a scoped mock coding-agent A/B comparison.

AI Agents Jul 2026 · 2 min read

Reliability Guard: 24 Scenarios for Catching Unsupported Agent Claims

A verification harness for fabricated completion, missing evidence, stale state, and contradictory coding-agent output.

Multi-Agent May 2026 · 3 min read

TruthNet: Building a Four-Agent Fact Checker in Seven Hours

How scope control, adversarial agent roles, a streaming backend, and stage-demo constraints shaped the hackathon build.

AI & Voice Aug 2026 · 3 min read

Interviewlary: Designing Role-Specific Voice Interview Practice

A product and architecture note on voice sessions, role-aware questions, structured scoring, and actionable feedback.

Web Engineering Jun 2026 · 1 min read

RoutineAI: Building a Student Planning App with Next.js and Supabase

Deterministic scheduling, AI-assisted planning, reminders, focus tools, and the 106-test verification scope behind the student planner.

Developer Tools Jun 2026 · 2 min read

Web Dev Skills: Structuring Repeatable AI-Assisted Delivery

How reusable skills, lifecycle prompts, and phased checks make AI-assisted web work easier to review and repeat.

Full Stack May 2026 · 2 min read

KaisLearnAI: Protecting Learning Data with Supabase RLS

A bilingual learning-platform pattern for role-aware access, protected progress data, and database-enforced tenant boundaries.

Full Stack Apr 2026 · 1 min read

StudyK: Connecting a React Admissions Interface to Edge Functions

A practical look at typed form intake, serverless workflows, and automated follow-up for an education consultancy product.

Web Engineering Mar 2026 · 1 min read

Damascus Trip: Designing a Bilingual Guide to Historical Places

A bilingual web guide combining curated place data, search and filtering, favorites, visited state, and right-to-left typography.

AI Education Mar 2026 · 1 min read

Kaiss Tech: Structuring Short, Reusable AI Engineering Guides

Lessons from turning agent workflows, prompting patterns, and tool integrations into concise educational material.

Founder & Ops Jul 2026 · 1 min read

Lary OS: Designing a Founder Operations Control Plane

A planning pattern for executive briefs, vendor monitoring, workflow review, and scheduled operational automation.

AI Systems Jun 2026 · 1 min read

MCOS: Planning Evidence-Backed Content Search with pgvector

A system design for PostgreSQL vector search, research synthesis, source traceability, and human approval gates.

AI & Voice Jul 2026 · 1 min read

Opti: Architecture for a Local Voice Assistant

A private implementation pattern combining wake-word detection, speech recognition, local speech output, and tool execution.

Multi-Agent Jul 2026 · 1 min read

Parallel System: Isolating Coding Agents with Git Worktrees

A specification for parallel agent work using separate checkouts, explicit ownership, and independent validation gates.

Frontier AI Aug 2026 · 2 min read

How to Evaluate Long-Horizon Agent Claims in Frontier Models

A source-checking framework for context length, multi-step tool use, recovery behavior, and long-running agent stability.

Frontier AI Aug 2026 · 2 min read

GPT-5.6 Sol: Separating Peak Token Speed from End-to-End Latency

How to read the official peak-speed claim and measure first-token, tool-call, reasoning, and total task latency separately.

Frontier AI Aug 2026 · 1 min read

How Dynamic Reasoning Changes Fast-Model Evaluation

A practical framework for comparing reasoning budgets, response speed, task quality, and total completion cost.

Frontier AI Aug 2026 · 1 min read

How to Vet Anonymous Reasoning-Model Claims

A cautious approach to model identity, tokenizer clues, context-window claims, retrieval tests, and source confidence.

Frontier AI Aug 2026 · 1 min read

What Reinforcement-Learning Claims Mean for Reasoning Models

A research note on separating training-method claims, observed reasoning behavior, distillation, and reproducible evidence.

Frontier AI Aug 2026 · 1 min read

A Practical Frontier-Model Evaluation Matrix for 2026

A durable comparison framework based on task quality, reliability, latency, total cost, and operational fit—not a static leaderboard.

AI Research Aug 2026 · 1 min read

A Four-Scope Memory Design for Multi-Agent Systems

How user, agent, session, and organization memory boundaries can reduce leakage and make retrieval behavior easier to reason about.

AI Research Aug 2026 · 1 min read

A Practical Guide to Evaluating Test-Time Compute

How to compare inference-time search and verification without assuming that more reasoning tokens always improve task outcomes.

AI Research Aug 2026 · 1 min read

Evaluating Synthetic-Data Feedback Loops

A review framework for generated traces, automated verification, error filtering, and the limits of self-correction.

AI Research Aug 2026 · 1 min read

Designing Safe Self-Improvement Loops for Software Agents

How tests, scoped changes, review gates, and rollback boundaries can constrain automated maintenance and refactoring.

AI Infra Aug 2026 · 1 min read

Model Context Protocol: Designing Safer Tool Connections for AI Agents

A practical introduction to tool schemas, transport boundaries, permission checks, and failure handling in MCP integrations.

Engineering Aug 2026 · 1 min read

Test-Driven Guardrails for AI-Generated Code

Why generated code needs deterministic tests, type checks, reviewable diffs, and explicit evidence before integration.

AI & Voice Jul 2026 · 1 min read

Where Voice-AI Latency Actually Comes From

A breakdown of audio capture, speech recognition, model response, tool calls, speech synthesis, and perceived turn-taking delay.

Multi-Agent Jul 2026 · 1 min read

Sub-Agents or One Prompt? Choosing the Right Orchestration Pattern

A balanced comparison of specialization, coordination overhead, shared context, review cost, and failure isolation.

AI Systems Jul 2026 · 1 min read

Deterministic Validation for Structured LLM Outputs

How schemas, state machines, retries, and explicit rejection paths keep probabilistic output inside application boundaries.

LLM Infra Jun 2026 · 1 min read

The Cost of Oversized Context Windows

A practical look at retrieval quality, token spend, latency, and when selective context beats sending the entire workspace.

No matching technical notes found. Try searching another keyword or model name.