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.
The path.
- Chat assistants The consumer/prosumer chat apps are the front door to each lab's frontier model.
- Prompting 101 Prompting is the highest-leverage, lowest-cost skill in this whole handbook. Small changes in how you frame a request move quality more than most people expect.
- IDE assistants 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.
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
-
When choosing a chat assistant in 2026, what should weigh most?
The chat apps now differ less in raw IQ than in surface features, so the handbook says to pick based on ecosystem lock-in rather than benchmark deltas.
Covered in step 1 · Chat assistants -
You're offloading a formatting-heavy task and the output style keeps drifting. What anchors it best?
Few-shot examples anchor format and style far more reliably than describing what you want in words.
Covered in step 2 · Prompting 101 -
Per the rule of thumb, when do you reach for a CLI agent instead of an IDE assistant?
IDE assistants are for flow: you're editing, it helps. CLI agents are for delegation: you describe, and the agent reads, edits, runs, and tests across the repo.
Covered in step 3 · IDE assistants
-
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.
-
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
You're on this rung
-
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
Explore path -
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 -
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 -
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