Loop · Agentic QA · 2026
Reduce low-value testing. Apply AI where it actually compounds. Reposition QA around quality value instead of test execution.
AI-Native QE Readiness
Walk the full tiered checklist. Critical prerequisites first, then the eight readiness categories. Get a gap report your team can act on this week.
Who Loop is for
If any of these sound like the conversation in your head this quarter, you're in the right place.
“My team is shrinking, but the regression suite isn't. We're drowning in flaky tests.”
Series-B fintech · ~50 engineers
We name the 30% of your suite eating 80% of CI minutes. And the move that gets it back without breaking confidence.
See the audit brief →“Leadership keeps asking about AI. I don't yet have a defensible answer.”
Healthcare SaaS · 120 engineers
We separate AI leverage from AI theater. And give you the boss-ready memo before you sign another vendor contract.
See the entry course →“QA feels less valuable every quarter. I need to reposition the function.”
E-commerce platform · 200+ engineers
We turn QA from test execution into the quality intelligence layer your CTO will forward to the board.
See the operating-model reset →Names + companies anonymized at the speakers' request.
The bookshelf · 4 volumes
Every methodology Loop runs is published as a book. Operating model, frameworks, assessments, adoption path. Free in full, gated only by an email so we can send the bundle.
AI-Native Quality Engineering
QE-2026AI-Native Quality Engineering
Operating model for the modern QA function.
AI-Driven TDD
TDD-2026AI-Driven TDD
Tests define intent. AI accelerates implementation.
Bespoke Agentic Pipelines
AGT-2026Bespoke Agentic Pipelines
The multiplier behind every Loop methodology.
Policy as Code
POL-2026Policy as Code
The deterministic floor beneath agentic development.
Live · Self-paced
One day. $1,000/seat. Walk out with a 90-day plan you can hand to your boss on Monday.
Last Tuesday of the month · Limited seats
Read the syllabus →The same operating model packaged as on-demand tracks. First set is in production now. Drop your email on the rail and we'll send word when it lands.
4 tracks planned · Track 01 in production
See the courses landing →Watch · Latest
Apr 28, 2026
If you want to start controlling AI-generated code today, this is the simplest way I’ve found to do it. In the previous videos, I talked about why agentic development breaks at scale and introduced the concept of policy as code as a way to fix it. In this video, I’m showing how to actually get started. The idea is straightforward. Instead of relying only on prompts, rules, or memory to guide AI, you introduce a deterministic layer that scans your codebase and flags violations. Think of it as a much more comprehensive, fully customizable linting system that works alongside tools like Claude. What surprised me is how easy it is to get a first version working. In this walkthrough, I show how you can go from zero to a basic policy as code setup in a very short amount of time. We start by generating a small set of rules, wire up a simple scanner, and immediately run it against a real codebase. Even with a basic setup, you’ll start catching issues and inconsistencies right away. This is not the full system I use in production. At scale, this turns into hundreds or even thousands of rules, with more advanced concepts like evidence layers, caching, and reporting. But the goal of this video is to show that you don’t need any of that to begin. If you’re using AI to write code and you’re starting to see drift, inconsistency, or quality issues over time, this is a practical way to start putting guardrails in place. Over time, what I’ve found is that as you add more rules, the amount of drift drops significantly, and the system becomes more reliable without slowing development down. If you haven’t watched the earlier videos in this series, I’d recommend starting with those for more context on why this approach exists and how it fits into a larger agentic workflow. If you try this yourself, I’d be interested to hear what kinds of rules you end up writing and what it catches in your codebase.
Watch on YouTube →
Apr 27, 2026
I spent time building with “agentic factories” - multi-agent pipelines that promise fully autonomous workflows. On paper, they look like the future. In practice, they broke down in ways that matter: reliability, coordination, and real-world constraints. In this video, I break down where these systems failed, why they fail structurally, and what actually worked instead in production. If you're building with AI agents, this will save you time (and probably some pain).
Watch on YouTube →
Apr 24, 2026
Claude and other AI agents are incredibly good at writing code. The problem is they don’t stay consistent over time. In the first few iterations, everything looks great. Output is fast, patterns are mostly correct, and it feels like you’ve unlocked a new level of development speed. But as the codebase grows, small inconsistencies start to compound. Patterns drift, structure degrades, and eventually the system becomes harder to maintain than it was before. That’s the problem this video is about. In this walkthrough, I break down how we use a concept called policy as code to control AI-generated code in real systems. Instead of relying only on prompts, rules files, or memory, we introduce a deterministic layer that enforces how code is allowed to be written. Every time an agent makes changes, those changes are checked against a large set of rules. If something doesn’t match the expected patterns, it fails. The agent has to fix it before moving forward. This ends up acting like a much more comprehensive version of linting, but tailored specifically to your architecture, your patterns, and your codebase. The result is that we’re able to keep the speed benefits of AI while dramatically reducing drift and long-term degradation. This video focuses on how the system works in practice. What kinds of rules we write, how they’re structured, and how they integrate into an agentic workflow using tools like Claude. If you’re experimenting with AI coding and running into issues with inconsistency or quality over time, this is one approach that has worked well for us. I’ll also be doing follow-up videos on how to implement this from scratch and how it fits into larger agentic pipeline systems. If you’ve tried something similar or have different approaches to controlling AI-generated code, I’d be interested to hear about it.
Watch on YouTube →How to work with Loop
A senior, AI-fluent SDET joins your team and beachheads the new operating model by living it.
Read the brief →An async-first private review of where your QA model is losing leverage. And what to do first.
Read the brief →Get QA, engineering, and product aligned on who owns quality and how release confidence gets measured.
Read the brief →6–10 weeks. Move QA from test execution to release confidence with measurable ROI.
Read the brief →Track record
30+
Engagements shipped
94%
On-time releases
−42%
Avg. regression CI minutes
0
Critical escapes (last 12 mo)
Numbers reflect engagements where Loop ran the operating-model reset or the transformation sprint. See the client roster for the full case set.
Writing
Most QA functions were built for a world where humans wrote all the code. That world is gone. Here's the operating model we've deployed across 30+ engagements to replace it.
8 min read →Everyone is shipping AI agents with giant prompts. The teams getting real leverage are building purpose-built pipelines with roles, permissions, and project-specific rules instead.
6 min read →We redesigned the TDD workflow for AI-assisted development. Tests define intent, AI accelerates implementation, and engineers own verification. The results changed how we think about quality ownership.
7 min read →Resources
Drop your email and we'll send the asset. No drip funnel, no sales calendar. One email, the file, and you're done.
The exact week-by-week plan QA leaders use to defend headcount and prove output in a single quarter.
Six metrics your CTO actually cares about. Escape rate, regression drag, recovery time, leverage ratio, AI yield, ownership clarity.
Stop QA-as-bottleneck. Map every test layer to a named owner so engineering can't push everything down to your team.
12 questions. Honest score. Tells you whether your team is a cost center, a guardrail, or a leverage multiplier.
Plug in your CI minutes, retry rate, and team size. Get the dollar figure flaky tests are costing you this quarter.
How to keep release safety from collapsing when your team is shrinking and your scope is growing.
Engagement ladder
Free books and resources. Evaluate Loop's thinking with no cost.
Open the bookshelf →Public courses and workshops. Walk out with a 90-day plan.
See the workshops →A private audit of where your QA model is losing leverage.
Read the brief →Embedded SDETs, the operating-model reset, or the transformation sprint.
See all engagements →90-Day QA Leverage Plan
Coming soonUse it on Monday · Editable doc + Notion template