Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Criterio

    1

    Six lenses for looking at systems before you decide.

    Free

    1 useSecurity scanned
    Criterio

    Criterio

    Example session with this skill installed

    We run customer support for a mid-sized travel company. We're about to launch an AI agent that answers fare and refund questions in chat and can issue refunds of up to €200 without a human. After the Air Canada chatbot case, legal wants a human to approve every refund. Support says that kills the point. Where should the line be?

    • Read your context and instructions
    • Compiled the criterio

    Jurisdiction record: refund agent for a travel company

    Legal is drawing the line on the wrong decision. In Moffatt v. Air Canada (2024) the chatbot never issued a refund. It told a customer he could claim a bereavement fare after travelling, which was wrong, and the tribunal held the airline to that statement. Air Canada argued the chatbot was responsible for its own words, and the tribunal rejected that. The harm came from what the agent says about entitlement, not from the money it pays out. Requiring human approval of every refund leaves that risk untouched: an agent that can't pay can still promise. Air Canada's failure was an execution error inside a mandate that was otherwise sound, which was "answer policy questions." It is fixed by grounding the answers, not by removing payment authority.

    Status of the mandate. The €200 autonomy is a proposal, not yet a delegation in force. Still missing: how refunds under €200 are distributed by cause, which policies can be decided from booking data alone, and who owns policy interpretation (legal, revenue or support).

    Zones

    The agent's own decisions. It can answer questions about a specific booking using the fare rules it retrieved for that booking, and cite them. It can issue refunds up to €200 when three things hold: entitlement follows from a written rule plus booking data (refundable fare class, cancellation inside the window, the company itself cancelled), the amount is calculated by the system rather than the agent, and nothing is negotiated. A wrong refund here is a bounded cost that shows up in the ledger. That is reversible enough to be covered by the next zone's review.

    Edge cases. These are still executed, but they trigger an alert and a review:

    • refunds near the cap;
    • several refunds against the same booking or customer within a short period, which may be splitting a claim to stay under the cap;
    • a customer whose history shows earlier claims.

    Behind this zone sits an aggregate daily cap that acts as a circuit breaker. A daily human review of a sample, plus every flagged case, is early enough because each loss is capped and can be traced. The aggregate cap protects against the scenario where review comes too late: mass manipulation of the agent through social engineering or prompt injection.

    Decisions outside its mandate. For these the agent stops and hands the case to a person:

    • Any denial of a statutory right. This covers EU261 compensation, Package Travel Directive cancellations and "extraordinary circumstances" judgments. A wrong denial is the least visible error in the system: the customer leaves, no ledger entry is created and nobody reviews it. A wrong payment can be audited; a wrong "no" cannot.
    • Any promise of a future or conditional refund ("you can claim afterwards").
    • Medical, bereavement or other compassionate exceptions.
    • Goodwill gestures, unless a defined budget and criteria exist.
    • Cases where the customer says another agent told them something different.
    • Chargebacks and disputes.

    Within this zone the agent may explain the process. It may not anticipate the outcome.

    Escalation

    • Recipient: the support refund queue, which is still to be designated.
    • Backup: the shift lead, also to be designated.
    • Policy interpretations: whoever owns the policy, which is pending.
    • While waiting: the agent tells the customer the case has been referred and gives a timeframe. It makes no commitment on the outcome and records what was said. Silence never turns into a refund or a denial.

    Metric versus purpose

    Support will probably measure containment and CSAT. Neither prevents an agent from improving its numbers by saying "yes" or promising refunds, which is exactly how Air Canada failed. If refund cost is measured instead, the incentive flips toward wrong denials. This is a plausible incentive, not observed behaviour. The fix is a sampled audit against policy that counts wrongful payments and wrongful denials, and that weighs as much as containment does.

    Evidence that would move the line

    Legal's position works well as a time-limited phase with exit criteria. Run the agent in recommend-only mode for a few weeks and compare its decisions with the humans' (approvals, denials and amounts). The disagreement rate per refund category tells you which categories move into the agent's own zone and whether €200 is the right cap.

    Revisit the line if any of these change

    • regulation (EU261 reform, AI liability rules);
    • the observed error rate;
    • the volume of fraud attempts;
    • an expansion of the agent's channels.

    This record proposes how the work is split operationally. It does not certify legal compliance.

    Referral. If the fare rules were written for human agents who interpreted them case by case, the agent will execute the wording without that judgment. Whether those rules still hold up belongs to /sedimento.

    Open question: Which refunds under €200 can today be decided from booking data and written rules alone, with no interpretation, and who gets the case when they can't?

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Criterio is a set of six analysis lenses for companies, products, teams, processes, spaces and AI agents. They are not methods or checklists. A lens doesn't tell you what to do; it orders the way you look before you decide.

    Each lens comes from a published essay and keeps its original case, its limits and a link to the text:

    • Sedimento: inherited rules that keep running although nobody remembers why.
    • Instancia: what part of a business anyone could copy, and what took years to build.
    • Escala: problems that keep coming back, or that are too big for whoever is meant to solve them.
    • Jurisdicción: which decisions an automated system or agent should not take, even if it can.
    • Sede vacante: the departure, succession or dependency on a key person.
    • Código: whether a seemingly neutral variable carries information that shouldn't be used.

    Claude picks the lens that fits your case and writes a short report. The report can conclude that there is nothing to find, or that the data isn't enough. Every lens ends with a section on when not to trust it, and every report ends with a question that only you can answer.

    The lenses are written in Spanish, the language of the essays. Claude answers in your language.

    The canonical version is open source under MIT on GitHub: github.com/carmonpa1/criterio. The essays are at carlesmontrull.me.

    • The lenses are written in Spanish. Reports come in your language, but the lens files themselves are in Spanish.
    • Each lens was formed from specific cases and says when not to trust it. Outside those cases, take its report as a hypothesis.
    • It diagnoses; it doesn't execute. No implementation plans, no code, no compliance certification.
    • It needs a real case with context. With thin data, the report says so instead of filling the gaps.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    No. A lens doesn't tell you what to do. It orders the way you look at a case before you decide, and it can conclude that there is nothing to find.

    You don't need to choose. Describe your case and the agent picks the lens that fits. If none fits, it says so.

    No. The lenses are written in Spanish, the language of the essays, but the report comes in your language.

    Each one comes from an essay published at carlesmontrull.me, with its original case. No lens is published without its essay.

    The lenses are open source under MIT at github.com/carmonpa1/criterio. This listing is a convenience copy of that repository.

    New in Research & Analysis