Recommended Trending AI-Native SDLC: Engineering Delivery from Intent to Production
Agents made the build step nearly free — now planning, review, and deployment are the bottleneck. Rebuild your delivery lifecycle as a loop: committed artifacts (intent.md → spec.md → plan.md → PR → incident), skills and hooks as governance-as-code, continuous evals on your agent setup, AI review with human approval, and production signals that write the next intent. For tech leads, platform engineers, and engineering managers.
Oleksii Anzhiiak
Software Architect, Senior .NET Engineer & Co-Founder
By the end you'll be able to
- Redesign your team's delivery lifecycle as a loop where every stage commits an artifact the next stage reads
- Run intent.md → spec.md → plan.md on real features, with policy applied while the spec is written
- Turn institutional knowledge into CLAUDE.md, skills, and hooks — and know which policies need a deterministic backstop
- Gate agent configuration changes with a continuous eval suite and every PR with AI review plus human approval
- Close one production loop: deterministic detection, agent diagnosis as intent.md, human triage
Is this course for you?
This is right for you if you…
- You're a tech lead or staff engineer whose team writes code with agents but still ships at the old pace — and you suspect the process, not the tools
- You're a platform or DevOps engineer asked to make agentic coding safe: hooks, managed settings, CI gates, and audit trails
- You're an engineering manager in a regulated or audited environment who needs agent speed without losing traceability or separation of duties
Don't take this course if you…
- You haven't used an agentic coding tool day to day yet — take #26 first; this course redesigns the process around that loop
- You're looking for a tool tutorial — this is a lifecycle and governance course; product specifics are covered only where they illustrate a pattern
- You have no repository or team process you can change — every module ends with an artifact committed to a real repo
Who teaches this
Oleksii Anzhiiak
Software Architect, Senior .NET Engineer & Co-Founder
Oleksii Anzhiiak is a Software Architect, Senior .NET Engineer, and Co-Founder of ToyCRM.com and ProfectusLab. With over 15 years of experience, he specializes in distributed systems, cloud infrastructure, high-load backend development, and identity platforms. Oleksii designs complex architectures, builds secure authentication systems, and develops modern engineering education programs that help students achieve real career results.
Currently leads architecture for ToyCRM.com — a multi-tenant CRM platform built on .NET by our team. The same patterns and design decisions used there appear directly in the courses: identity & auth, distributed services, code review culture. You learn from engineers actively shipping production code, not from a textbook.
Syllabus
Six modules — one per lifecycle stage. Each ends with an artifact committed to your own repo, so by week six your team runs a working AI-native loop, not a slide deck:
- 1 Module 1: Plan — why build stopped being the bottleneck; keeping control objectives while changing enforcement; the artifact thread (intent → spec → plan → diff → PR → incident); writing an intent.md template and skill; choosing a system of record alongside Jira and other legacy tools
- 2 Module 2: Design — requirements and design in one session; generating spec.md from an accepted intent with policy skills for security, compliance, and UX; making the agent flag conflicting policies; routing concerns to named owners; codifying the pass as a slash command and measuring post-plan spec rework
- 3 Module 3: Build — plan mode by default and plan.md as the contract the PR is checked against; a CLAUDE.md under one page and the 'same mistake twice' rule; skills advise, hooks enforce; auto mode for routine work; parallel sessions in git worktrees and subagents (verifier, simplifier, researcher)
- 4 Module 4: Test — a one-command feedback loop the agent iterates against; failing-test-first bug fixes with hook-protected tests; visual loops for UI; a continuous eval suite of 20–50 real tasks that gates every change to CLAUDE.md, skills, hooks, or model; turning each incident into a permanent eval
- 5 Module 5: Deploy — AI PR review configured in REVIEW.md with severity and nit caps; agents addressing review comments; approval hooks that ask a named release manager; managed settings for secrets, sandboxing, and supply chain matched to data classification; CI judgment jobs, per-environment autonomy tiers, and rehearsed one-command rollback
- 6 Module 6: Maintain & roll out — closing the loop with deterministic detection (rolling baselines, 1σ/2σ/3σ response tiers) and agent diagnoses written as intent.md; recurring security scans and chat-based on-call; a stage-by-stage adoption roadmap with leading and lagging metrics for your team
Prerequisites
Strongly recommended: Claude Code Mastery (#26) for the daily agentic loop and SDD Foundations (#28) for the spec discipline. OpenSpec Mastery (#29) and Claude Agent SDK (#27) are strong companions.
Daily experience with an agentic coding tool (Claude Code or similar). Comfort with Git, pull requests, and a CI system (GitHub Actions or equivalent). A real repository — ideally your team's — to build the loop on.
What you'll build
You leave with an AI-native loop running on your own repository: intent and spec templates, a tuned CLAUDE.md, at least one policy skill backed by a hook, an eval suite gating your agent configuration, an AI review gate with human approval, and one production metric that writes its own intent.md.
- Artifact-driven SDLC: intent.md, spec.md, plan.md
- CLAUDE.md, skills, and hooks as governance-as-code
- Feedback loops and continuous evals in CI
- AI PR review, approval gates, and managed settings
- Closed-loop maintenance with deterministic detection
Where this fits in your career
Read alongside this course
Securing Agentic Development: Zero Trust for Coding Agents
A coding agent is a new kind of insider: fast, tireless, holding real credentials, and reading content an attacker can write. Here's how I'd apply Zero Trust to agentic development — least agency, sandboxes, agent identity, deterministic hooks, and a human at the production gate — without strangling the velocity that made agents worth adopting.
Multi-Agent Systems in 2026: When One Agent Beats Five
Multi-agent architectures look impressive on a whiteboard and cost a lot in production. Here's when splitting work across agents actually helps, which coordination patterns fit which problems, why the current advice is to fold subagents back into one loop with progressive disclosure, and a decision framework you can use before you draw the second box.
CLAUDE.md, Skills, Hooks, or Subagents: What Goes Where
Most frustration with coding agents comes from putting the right instruction in the wrong place. A practical guide to the steering mechanisms of an agentic coding tool — what each one is for, a decision table, the anti-patterns I see most, and the order I'd roll them out in.
First lesson on us. Decide after meeting your instructor.
Sit in on the first session. If after lesson 1 you decide the instructor isn't the right fit, you don't pay for it — and no awkward conversation. (Trial offer applies to courses with more than 5 lessons; this one qualifies.)
Pricing & what's included
What's included
- 12 live sessions × 2 hours each — taught by the instructor, not a recording playback
- Slide deck for every session — yours to keep and refer back to
- Working code files and any data files used in class — cloned to your machine
- Weekly homework with personal code review from the instructor
- Recording on request — give the teacher a heads-up ("can't make Tuesday, please record it") and the session is recorded for you
Frequently asked questions
How much time per week will this take?
Plan for the live sessions plus roughly 1.5–2 hours of practice per session. Most students who finish on schedule put in 4–6 hours a week total. If you put in less, you still finish — it just takes longer.
What if I miss a class?
Tell the teacher BEFORE the session — "I can't make Tuesday, please record it" — and the teacher records that lesson and sends it to you. Recordings aren't a default catch-up archive; they're produced on request when you give a heads-up. After the lesson you do the homework, bring questions to the next session.
What's included in the price?
Live sessions with the teacher; the slide deck for each session (yours to keep); the working code files and any data files used in class; weekly homework with code review; and recordings of the sessions you give advance notice for. Anything beyond that — a certificate, alumni access, mock interviews — is listed explicitly in "What's included" above the FAQ for the courses where it applies.
What if I sign up and the teacher isn't a fit?
For courses with more than 5 lessons, the first session is effectively a trial — if after lesson 1 you decide the teacher isn't a fit, you don't pay for it. We'd rather you walk away after one lesson than push through 9 weeks of bad chemistry. (Courses with 5 or fewer lessons are short enough that the standard pricing applies — the trial offer doesn't make sense at that length.)
Can I get a refund partway through?
Yes. Within 14 calendar days of purchase you can withdraw and get a full refund on request, no reason needed — that's your statutory right under Georgian consumer-protection law. On top of that, our own guarantee: if you've attended fewer than 3 lessons, we refund in full with no deductions. Refunds go back to your original payment method within 14 days.
Can I switch the language of instruction?
The live sessions run in the language listed under "Available Languages" above. Slides and code files are typically available in all four (English, Russian, Ukrainian, Georgian). Many students attend sessions in one language and read materials in another — that's normal.
Will I be ready for a real job after this course?
One course rarely gets anyone hired by itself — for any field. What this course gives you is the foundation a junior hiring manager expects: working code you wrote yourself, the vocabulary to read other people's code, and the practice habits that make you employable. The honest answer to "am I ready?" is on our roadmap (link in the page header) — open the level you want to reach and read the "You're ready when" checklist.
Can I pay in instalments?
Yes for courses with a "Monthly Payment" option in the at-a-glance ribbon — usually two or three equal monthly payments. Courses without that option are paid in one go. If the price is the blocker, write to us — we look at every case.
You may also like
Advanced
OpenSpec Mastery: Production Spec-Driven Workflows for AI Coding Agents
Operationalize SDD with OpenSpec — the open-source spec framework that treats specs the way Git treats code. Master /opsx:propose, /opsx:apply, and /opsx:archive on a real brownfield codebase. CI gates, multi-engineer collaboration, retrofitting legacy specs, and the workflow rituals that make it stick.
Intermediate
Spec-Driven Development Foundations: From Philosophy to Operating Model
Learn to write specs that agents actually obey, ship code as a cache of a durable spec, and operate the spec→context→evals trinity on real codebases. Vendor-agnostic, tool-agnostic, brownfield-ready — the methodology course that pairs with any agentic stack.
Advanced
1:1 Backend & Architecture Review
A private 1:1 architecture-focused session to identify risks, clarify trade-offs, and define concrete next steps. We review your backend architecture and code, assess production readiness, and deliver a clear action plan tailored to your goals.