[research@ai4se] : ~ $
cd ../
[methodology] | | 14 min

# Agentic Engineering Capability Maturity: From Vibe Coding to Production-Grade Collaboration

Agentic Engineering is not a binary switch — it's a maturity spectrum from "fully human-written" to "spec-driven and fully automated." Understanding where you sit on that maturity curve matters more than arguing over which extreme is better.

[agentic-engineering][methodology]

Where the Concept Comes From

Andrej Karpathy coined the term vibe coding in 2025 — AI programming driven by feel, with weak review. By early 2026 he came to prefer Agentic Engineering as the term for professional contexts.

Addy Osmani emphasizes: vibe coding fits exploration and low-risk experimentation; Agentic Engineering points to AI agents that can execute the implementation, while humans still hold responsibility for architecture, quality, and correctness — something that can be written into team practice and governance mechanisms.

Simon Willison’s Agentic Engineering Patterns turns the concept into reusable patterns rather than a terminology debate.

A Trainable Definition

Agentic Engineering is an engineering practice for using coding agents in software delivery: through clear goals, controlled tools, isolated workspaces, version control, automated testing, human review, and traceable evidence, agents participate in implementation and verification, while humans retain final technical accountability.

Five key words: Agent, Engineering, Loop, Harness, Accountability.

For core concepts, see Core Concepts of Agentic Coding Agents; for Harness practices, see Harness Engineering.

The Spectrum With Vibe Coding

ModeBest fitHuman’s responsibilityRisk
Vibe CodingPrototypes, one-off scriptsQuickly express intent, accept the resultHard to maintain, hard to audit
AI-assisted EngineeringLocal productivity gains, autocompleteWrite the core design, review AI outputDepends on individual habits
Agentic EngineeringProfessional delivery, team collaborationDesign goals, verify, own the mergeRequires engineering discipline and governance

In one line: vibe coding is “I barely look at the code but it still runs”; Agentic Engineering is “I let the agent write it, but I can explain, verify, roll back, and take accountability for it.”

Five Stages of Capability Maturity

StageCharacteristicsShare of code output from AI
L1: Assisted autocompleteIDE autocomplete, single-line Copilot suggestions<10%
L2: Conversational codingChat generates functions/modules, human assembles20-40%
L3: Agent collaborationAgent completes tasks autonomously, human reviews50-70%
L4: Spec-drivenSpec → Agent handles the full flow, human signs off on gates80%+
L5: Autonomous teamsMultiple agents work in parallel, human only sets constraints95%+

Where Most Teams Get Stuck

Most teams oscillate between L2 and L3. The bottleneck isn’t model capability — it’s:

  • No reviewable spec
  • The testing system can’t keep pace with generation speed
  • No independent review role

Simon Willison’s Key Patterns

The Tool Loop

LLM + system prompt + tools + observations. Without the ability to execute tools, it’s just a code suggester; with execution capability, the agent converges by running tests. What enterprises need to govern is the Harness, not the model itself.

Git Is a Safety Rope

Every agent session should run inside a branch or worktree; small commits make review and rollback easier. Agents can help explain diffs and organize commits, but they cannot replace human accountability for the merge.

First, Run the Tests

A high-value short instruction to open a session with — it establishes a baseline and nudges the agent to keep validating changes against tests going forward.

Red/Green TDD

Write a failing test before implementing — reduces “code that looks reasonable but was never verified.”

Agentic Manual Testing

Automated tests can’t replace visually verifying the UI; agents can use Playwright and screenshots to perform something like manual testing, while humans still check the key outcomes.

Subagents

Their value is in protecting the main context; a good fit for exploration, impact-scope scanning, and independent review. Over-fragmenting increases coordination cost.

PR Accountability

Anti-pattern: handing a colleague a PR the agent generated that you never reviewed yourself — that’s shifting your accountability onto the reviewer. A good agentic PR is small, reviewable, and backed by test evidence.

Six Capability Domains

  1. Intent & Spec — requirement decomposition, acceptance criteria, risk boundaries
  2. Context & Knowledge — team conventions, architecture decisions, accumulated skills
  3. Harness & Tools — terminal, tests, browser, CI, permissions and sandboxing
  4. Verification & Evidence — tests, screenshots, logs, reproducible experiments
  5. Collaboration & Review — git branches, PR size, review checklists
  6. Learning Loop — retrospectives, failure patterns, tooling improvements, updating knowledge assets

The Path to Leveling Up

TransitionKey action
L2 → L3Agent CLI + sandbox + review gate
L3 → L4Spec system + independent Evaluator + automated gating
L4 → L5Multi-agent orchestration + metrics-driven governance

A 30/60/90-day path:

  • Days 0-30: Branch/worktree boundaries; run tests first; small commits; agent instruction templates
  • Days 31-60: Playwright; red/green TDD; subagents for impact-scope scanning
  • Days 61-90: Codify skills/templates; measure PR lead time and defect leakage; incorporate into CI/CD gates

Anti-Pattern Checklist

  • Handing a colleague an unreviewed PR
  • No baseline tests
  • Only looking at the demo, not the edge cases
  • Delegating one giant task all at once
  • Declaring completion with no evidence
  • Ignoring the skill atrophy of junior engineers

References