--- title: Active pairing — The Agentic AI Hub | daily.dev description: The AI writes alongside you all day, handling the boring parts while you steer and review everything as it lands. Shapiro estimates about 90% of AI-native developers live here. canonical: https://daily.dev/agentic-ai-hub/paths/l2/ og:type: website og:url: https://daily.dev/agentic-ai-hub/paths/l2/ og:title: Active pairing — The Agentic AI Hub | daily.dev og:description: The AI writes alongside you all day, handling the boring parts while you steer and review everything as it lands. Shapiro estimates about 90% of AI-native developers live here. og:image: https://daily.dev/assets/og/agentic-ai-hub-l2.png?v=71862637 og:site_name: daily.dev og:locale: en_US twitter:card: summary_large_image twitter:site: @dailydotdev twitter:creator: @dailydotdev twitter:title: Active pairing — The Agentic AI Hub | daily.dev twitter:description: The AI writes alongside you all day, handling the boring parts while you steer and review everything as it lands. Shapiro estimates about 90% of AI-native developers live here. twitter:image: https://daily.dev/assets/og/agentic-ai-hub-l2.png?v=71862637 --- [Skip to main content ](#main-content) L2 # L2: Active pairing The AI writes alongside you all day, handling the boring parts while you steer and review everything as it lands. Shapiro estimates about 90% of AI-native developers live here. [Start reading → ](/agentic-ai-hub/coding-tools-cli-agents/?path=l2&i=0) [Check yourself first ↓ ](#quiz) 1. [ 1 CLI agents Two families here: IDE assistants (autocomplete + chat + in-editor agents living in your editor) and CLI/terminal agents (you talk to an agent in the shell. › ](/agentic-ai-hub/coding-tools-cli-agents/?path=l2&i=0) 2. [ 2 AGENTS.md & CLAUDE.md In Context, Skills & Memory Agents are only as good as what they know when they start, and by default they start knowing nothing about your repo, your conventions, or last week's decisions. › ](/agentic-ai-hub/context-skills-memory/?path=l2&i=1#agentsmd-and-claudemd-conventions-in-the-repo) 3. [ 3 What an agent actually is In Agentic Engineering: Core Ideas "Agentic coding" is an overloaded term. › ](/agentic-ai-hub/agentic-engineering-core-ideas/?path=l2&i=2#what-an-agent-actually-is) ## Check yourself. One question per step. Take it cold to find where to start, or after reading to see what stuck. Nobody's grading you. Best so far: Question 1 of 3 1. Step 1 What was the defining 2025→2026 shift in coding tools? A From proprietary models to open source B From desktop IDEs to cloud-only editors C From per-seat pricing to free tiers D From smarter autocomplete to agents that plan, edit, and run The shift was to agentic tools that plan, edit many files, run commands, and iterate, with pricing largely moving to usage credits on top of a seat. [Covered in step 1 · CLI agents → ](/agentic-ai-hub/coding-tools-cli-agents/?path=l2&i=0) Next question → 2. Step 2 Beyond build and test commands, what makes AGENTS.md most valuable? A The "why we don't" decisions and lessons written back each session B Auto-generated API documentation for every module C A pinned list of approved dependencies and versions D Onboarding docs that replace the human-facing README AGENTS.md is the vessel for compound learning: hard-won lessons and "why we don't" decisions get written back so every future session and parallel agent starts smarter. [Covered in step 2 · AGENTS.md & CLAUDE.md → ](/agentic-ai-hub/context-skills-memory/?path=l2&i=1#agentsmd-and-claudemd-conventions-in-the-repo) Next question → 3. Step 3 A working coding agent fits in \~400 lines: "an LLM, a loop, and enough tokens." What follows from that? A Building a competitive agent is mostly a prompt problem B What separates agents is the scaffolding around the model C Agent quality is decided by model choice alone D The loop needs a framework to be production-ready If the loop itself is a few hundred lines of boilerplate, nearly everything that makes one agent better than another lives in the harness around the model. That's the section's key lesson. [Covered in step 3 · What an agent actually is → ](/agentic-ai-hub/agentic-engineering-core-ideas/?path=l2&i=2#what-an-agent-actually-is) See results → of 3 * [ 1 CLI agents → ](/agentic-ai-hub/coding-tools-cli-agents/?path=l2&i=0) * [ 2 AGENTS.md & CLAUDE.md → ](/agentic-ai-hub/context-skills-memory/?path=l2&i=1#agentsmd-and-claudemd-conventions-in-the-repo) * [ 3 What an agent actually is → ](/agentic-ai-hub/agentic-engineering-core-ideas/?path=l2&i=2#what-an-agent-actually-is) Try again [Where to next → ](#path-next-title) ## Where to next. Climb to the next rung, or see how the other levels work. 1. L0 ### L0: Manual The ground floor: AI as a search engine and occasional tab-complete. No real productivity change. Everyone starts here. There's nothing to unlock yet. 2. L1 ### L1: Discrete task offloading You hand the AI small, self-contained jobs: write the unit tests, draft the docstring, generate one well-scoped function. The real work is still yours. Chat assistants · Prompting 101 · IDE assistants [Explore path → ](/agentic-ai-hub/paths/l1/) 3. L2 ### L2: Active pairing The AI writes alongside you all day, handling the boring parts while you steer and review everything as it lands. Shapiro estimates about 90% of AI-native developers live here. CLI agents · AGENTS.md & CLAUDE.md · What an agent actually is You're on this rung 4. L3 ### L3: Human-in-the-loop management You mostly stop typing code. Agents run several tasks at once and your day becomes reviewing their work. Most people never go past this level. Own the outer loop · Agentic code review · Role separation · MCP & tools [Explore path → ](/agentic-ai-hub/paths/l3/) 5. L4 ### L4: Specification-driven You define what to build instead of building it: write the spec, set the tests, judge the results. Leave for twelve hours and come back to a green suite. The harness as an artifact · Evals-as-tests · LLMOps & guardrails [Explore path → ](/agentic-ai-hub/paths/l4/) 6. L5 ### L5: The dark factory Agents building the software with humans out of the loop. Shapiro reports it working only for teams under five people, and calls it likely our future. Swarms & fleets · The factory model · Human factors [Explore path → ](/agentic-ai-hub/paths/l5/) [All reading paths → ](/agentic-ai-hub/#paths-start-here) [Browse every chapter ](/agentic-ai-hub/#pages) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/og-image.png?v=a830cdf1","width":1200,"height":630},"sameAs":["https://twitter.com/dailydotdev","https://www.linkedin.com/company/dailydotdev","https://github.com/dailydotdev","https://www.instagram.com/dailydotdev"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","description":"Free, personalized developer news aggregator. Stay on top of software development news, AI coding tools, and web dev - curated daily from trusted sources.","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}},{"@type":"WebPage","@id":"https://daily.dev/agentic-ai-hub/paths/l2/","url":"https://daily.dev/agentic-ai-hub/paths/l2/","name":"Active pairing | The Agentic AI Hub","description":"The AI writes alongside you all day, handling the boring parts while you steer and review everything as it lands. Shapiro estimates about 90% of AI-native developers live here.","inLanguage":"en-US","isPartOf":{"@id":"https://daily.dev/#website"}},{"@type":"ItemList","numberOfItems":3,"itemListElement":[{"@type":"ListItem","position":1,"url":"https://daily.dev/agentic-ai-hub/coding-tools-cli-agents/","name":"CLI agents"},{"@type":"ListItem","position":2,"url":"https://daily.dev/agentic-ai-hub/context-skills-memory/#agentsmd-and-claudemd-conventions-in-the-repo","name":"AGENTS.md & CLAUDE.md"},{"@type":"ListItem","position":3,"url":"https://daily.dev/agentic-ai-hub/agentic-engineering-core-ideas/#what-an-agent-actually-is","name":"What an agent actually is"}],"@id":"https://daily.dev/agentic-ai-hub/paths/l2/#steps"},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev/"},{"@type":"ListItem","position":2,"name":"The Agentic AI Hub","item":"https://daily.dev/agentic-ai-hub/"},{"@type":"ListItem","position":3,"name":"The adoption ladder","item":"https://daily.dev/agentic-ai-hub/#levels"},{"@type":"ListItem","position":4,"name":"Active pairing","item":"https://daily.dev/agentic-ai-hub/paths/l2/"}]}]} ```