Each rung changes your job: asker, brief writer, curator, architect, boss, orchestrator. The skill that compounds at every rung is verification, because outputs get more polished as you climb, and polish hides errors.
The fluency ladder
Height and color depth encode the same ordering. Select a level for a summary, or open the full cards below.
Each level hands the model more of the work, and you more of the design, governance, and verification.
View as table
| Level | What defines it | The mindset | In insurance |
|---|
Higher is not better. Seniority means reaching for the lowest rung that closes the quality gap: a good prompt beats a pipeline, a pipeline beats an agent, one governed agent beats a fleet. Autonomy is a cost you spend, not a badge you earn.
This page tracks your practice; the companion page tracks the technology itself. See the six stages of AI sophistication. One tells you what vendors can ship; the other, what your team can responsibly use.
The levels, in full
The harness: how slop becomes reliable work
The unit of AI work is no longer the conversation; it is the ephemeral agent. Modern tooling spins up short-lived agents by the thousand: each gets a task, a slice of context, and a set of tools; it works, reports, and is shut down. Fleets run around the clock, and the marginal cost of one more attempt is a few cents of compute.
Most raw agent output is slop: plausible, confident, unverified. Agent fleets do not eliminate slop; they industrialize it. Ten unsupervised agents produce ten times the plausible garbage. So the discipline of the agentic era is not getting AI to produce more; it is building the harness that makes fleet output trustworthy. Generation is cheap; verification is the bottleneck.
| Harness layer | What it is | How it reins in the slop |
|---|---|---|
| Context engineering | Controlling what the agent sees: the right guidelines, forms, and worked examples, and nothing extraneous | Most agent failures are context failures, not model failures; a well-briefed mediocre agent beats a brilliant one guessing |
| Skills | Codified procedures (an extraction playbook, a validation checklist, house style) packaged once, loaded on demand, versioned and tested like software | Tacit expertise becomes an auditable asset; the agent stops reinventing the procedure on every run |
| Hooks | Deterministic checkpoints that fire at lifecycle events: validate every extracted field against the source document, block output containing PII, require the eval to pass before a draft reaches a human | Unlike instructions, hooks are code: they run every time, including at 3 a.m. on agent #4,000 |
| Verification loops | A grader agent or deterministic check scores worker output against ground truth before it flows upstream | Only verified work surfaces; a human reviews what the harness escalates, not everything the fleet produces |
This is what "human-in-the-loop" actually means in 2026: not a person reading everything, but a person reviewing what the harness surfaced. And it is where the NAIC Model Bulletin's "testing and human oversight" expectations physically live: in hooks, evals, and permission gates, not in the policy PDF. Levels 4–6 of this ladder are, in effect, the harness skills: the Workflow Designer builds fixed checks, the Agent Boss wires hooks and goal contracts, the Fleet Orchestrator runs verification loops across teams of agents. Slop is cheap; trust is engineered.
Where the experts disagree
- Prompt engineering: dead or absorbed? The consensus is absorbed. Phrasing skill is now one layer inside context engineering, so the ladder keeps it as a rung, not a destination.
- Agent teams: help or harm? Orchestrator-worker teams report large quality gains on parallel, high-value work at roughly 15x the token cost, and fail on tightly coupled work. Task shape decides.
- What are subagents for? Context isolation, not personas. Role-playing subagents measurably underperform; quarantined context windows are the entire point.
- Retrieve up front or just in time? Long context wins on quality, RAG wins on cost. The working default is hybrid: a thin always-on foundation plus just-in-time fetch.
- Is a ladder even the right shape? Fluency frameworks like Anthropic's 4Ds are competency inventories, not rungs. Treat this as a map of what to learn next, not a ranking of people.
Source links
- Anthropic engineering series: Building effective agents · Context engineering · Multi-agent research system · Prompt engineering docs · AI Fluency framework
- Practice research: Mollick/HBS, "Centaurs and Cyborgs on the Jagged Frontier" · Rethink Priorities usage surveys · Microsoft Work Trend Index (Frontier Firm)
- Architecture and harness: LangChain on context engineering · Cognition, "Don't Build Multi-Agents" · HumanLayer, 12-factor agents · DAIR.AI Prompt Engineering Guide
The "context engineering moment" references Karpathy's and Lütke's June 2025 posts; the June 2026 harness section draws on the same engineering sources above. Market and regulatory claims live on the AI roadmap, which carries numbered references.