── ── AI & agents
Agent Delegability Assessment
Teams usually decide how much to hand to an agent by watching a demo. The demo shows what the model can do. It says nothing about what a mistake costs or whether anyone will notice one. The two failure modes look opposite and are equally expensive. If every output gets a human review, the time savings vanish and reviewers become…
Run Agent Delegability Assessment on a real problem
Bring something you're actually deciding — free, in the browser.
How it works
Output: Delegation Map (task × level × gate × promotion/demotion rules)
1. Decompose. Break work down to "one input → one output" tasks. Gate: input and output cannot be stated → run sop-systemization first. 2. Score six dimensions (1–5). Frequency · rule clarity · cost of error · reversibility · data access (can the agent lawfully read what it needs) · verifiability (can a human judge right/wrong in about a minute). Also record the exception rate (%), measured, not guessed. 3. Assign a level. Apply caps in this order: - High cost of error and irreversible → max L2 - Low verifiability → max L2, regardless of other scores - Exception rate > 20% → max L2; split the exception path out as its own task - High frequency + clear rules + reversible + easy to verify → start at L3 - L4 only by promotion from a stable L3 that meets its error-rate target Gate: data access insufficient → do not delegate; fix permissions first. 4. Attach gates. For each level write: who approves, what they approve, the time limit, the amount/scope cap, and the action log. 5. Set promotion and demotion rules. Pre-set an error-rate threshold and an observation window. Crossing the threshold demotes the task one level automatically. 6. Stop-rule: the task's value is below the cost of approval and supervision → keep it manual or delete the task.
Output template: Task · Freq · Rules · Error cost · Reversible · Data · Verifiable · Exception % · Level · Approver + cap · Log · Promote when · Demote when
When to use it
- user says 'which work can we hand to an AI agent', 'how far can this process be automated', 'does the agent need human approval', 'how much permission should the agent get', asks 'can the agent just do this on its own?', or is preparing to let an agent take over a business process
When not to use it
When the decision is routine and reversible, applying a formal method costs more than it returns.
Worked example
Moffatt v. Air Canada — A Customer-Facing Chatbot at the Wrong Autonomy Level (2022–2024)
The facts here come from the tribunal's written reasons: Moffatt v. Air Canada, 2024 BCCRT 149, British Columbia Civil Resolution Tribunal, issued February 14, 2024. The decision does not describe how Air Canada configured its chatbot. Air Canada "did not provide any information about the nature of its chatbot" (para. 14). The scoring below is therefore this skill's reconstruction from the record, and is labeled that way.
Install this skill (free, MIT)
npx skills add deciqAI/knowledge-skillsUseful? Star the repo — stars help other builders find it.
Related mental models
An agent that is live without logs, quality metrics or alerts fails quietly.
AI agents can research every prospect before writing to them, at close to the cost of a mass blast.
An AI shopping agent does not respond to photography, mood or persuasive copy.
AI drives the marginal cost of a draft toward zero, so the bottleneck moves to consistency, accuracy and compliance.