Francisco MinguezData & AI

Compare / Model Decision Space

Method demonstration for model / configuration choice

Which model or configuration actually makes sense for our workload?

What you are looking at

One Model Decision Space instrument. Same synthetic workload, same evaluation protocol, explicit hard constraints, then eligibility before any trade-off.

What you can do

Set the quality bar and latency constraint, see which candidates survive hard requirements, compare survivors without a magic score, and read the Decision Record, including NO RECOMMENDATION when none clear the bar.

What it means

There is no universally best model. There is a defensible candidate, or no acceptable candidate, for this workload and these constraints.

Mental model

  1. SAME WORKLOAD
  2. SAME PROTOCOL
  3. EXPLICIT CONSTRAINTS

Workload under evaluation

Support-ticket answer assist (synthetic scenario)

Frozen synthetic tickets. Protocol scores grounded usefulness, harmful overconfidence, and deferral discipline before cost. Cost never overrides a failed quality bar.

Decision sequence

  1. Define workload, quality bar, and operational constraints
  2. Evaluate every candidate with the same protocol
  3. Reject candidates that fail hard requirements
  4. If several remain, examine trade-offs / Pareto with no magic weighted score
  5. Inspect failure behaviour (light)
  6. Choose, reject, retest, or issue NO RECOMMENDATION

Hard constraints first

Discrete categorical controls. Eligibility is evaluated before any trade-off view.

Quality bar
Latency constraint

Candidates under the same protocol

SYNTHETIC / ILLUSTRATIVE METHOD DEMO. Invented for teaching.

Eligibility after hard constraints

  • Candidate Alpha

    Compact-fast configuration

    ELIGIBLE

    Clears a moderate bar on common tickets.

    Overconfident on rare policy edge cases.

  • Candidate Beta

    Balanced mid configuration

    ELIGIBLE

    Holds a high bar under the shared protocol.

    Occasionally slow on multi-step tickets; rarely invents policy.

  • Candidate Gamma

    Careful large configuration

    ELIGIBLE

    Best grounded usefulness and deferral discipline in this set.

    Misses interactive latency; cost dominates if unconstrained.

  • Candidate Delta

    Cheap draft configuration

    ELIGIBLE

    Fast and cheap; only a moderate bar is honest.

    Grounding collapses under adversarial paraphrases.

Trade-off / pair comparison

Several candidates remain. Compare categorical trade-offs, not a single weighted score presented as truth.

  • Candidate Alpha

    Compact-fast configuration

    Quality ceiling
    Moderate
    Latency class
    Strict
    Cost class
    Low
    Failure behaviour
    Overconfident on rare policy edge cases.
  • Candidate Beta

    Balanced mid configuration

    Quality ceiling
    High
    Latency class
    Tight
    Cost class
    Mid
    Failure behaviour
    Occasionally slow on multi-step tickets; rarely invents policy.
  • Candidate Gamma

    Careful large configuration

    Quality ceiling
    Very high
    Latency class
    Relaxed
    Cost class
    High
    Failure behaviour
    Misses interactive latency; cost dominates if unconstrained.
  • Candidate Delta

    Cheap draft configuration

    Quality ceiling
    Moderate
    Latency class
    Strict
    Cost class
    Low
    Failure behaviour
    Grounding collapses under adversarial paraphrases.
Trade-off / pair comparison
CandidateQuality ceilingLatency classCost classFailure behaviour
Candidate AlphaModerateStrictLowOverconfident on rare policy edge cases.
Candidate BetaHighTightMidOccasionally slow on multi-step tickets; rarely invents policy.
Candidate GammaVery highRelaxedHighMisses interactive latency; cost dominates if unconstrained.
Candidate DeltaModerateStrictLowGrounding collapses under adversarial paraphrases.

Active record: compare survivors; no automatic CHOOSE

Eligibility after hard constraints

  • Candidate Alpha

    Compact-fast configuration

    ELIGIBLE

    Clears a moderate bar on common tickets.

    Overconfident on rare policy edge cases.

  • Candidate Beta

    Balanced mid configuration

    ELIGIBLE

    Holds a high bar under the shared protocol.

    Occasionally slow on multi-step tickets; rarely invents policy.

  • Candidate Gamma

    Careful large configuration

    REJECTED

    Best grounded usefulness and deferral discipline in this set.

    Fails latency constraint

  • Candidate Delta

    Cheap draft configuration

    ELIGIBLE

    Fast and cheap; only a moderate bar is honest.

    Grounding collapses under adversarial paraphrases.

Trade-off / pair comparison

Several candidates remain. Compare categorical trade-offs, not a single weighted score presented as truth.

  • Candidate Alpha

    Compact-fast configuration

    Quality ceiling
    Moderate
    Latency class
    Strict
    Cost class
    Low
    Failure behaviour
    Overconfident on rare policy edge cases.
  • Candidate Beta

    Balanced mid configuration

    Quality ceiling
    High
    Latency class
    Tight
    Cost class
    Mid
    Failure behaviour
    Occasionally slow on multi-step tickets; rarely invents policy.
  • Candidate Delta

    Cheap draft configuration

    Quality ceiling
    Moderate
    Latency class
    Strict
    Cost class
    Low
    Failure behaviour
    Grounding collapses under adversarial paraphrases.
Trade-off / pair comparison
CandidateQuality ceilingLatency classCost classFailure behaviour
Candidate AlphaModerateStrictLowOverconfident on rare policy edge cases.
Candidate BetaHighTightMidOccasionally slow on multi-step tickets; rarely invents policy.
Candidate DeltaModerateStrictLowGrounding collapses under adversarial paraphrases.

Active record: compare survivors; no automatic CHOOSE

Eligibility after hard constraints

  • Candidate Alpha

    Compact-fast configuration

    ELIGIBLE

    Clears a moderate bar on common tickets.

    Overconfident on rare policy edge cases.

  • Candidate Beta

    Balanced mid configuration

    REJECTED

    Holds a high bar under the shared protocol.

    Fails latency constraint

  • Candidate Gamma

    Careful large configuration

    REJECTED

    Best grounded usefulness and deferral discipline in this set.

    Fails latency constraint

  • Candidate Delta

    Cheap draft configuration

    ELIGIBLE

    Fast and cheap; only a moderate bar is honest.

    Grounding collapses under adversarial paraphrases.

Trade-off / pair comparison

Several candidates remain. Compare categorical trade-offs, not a single weighted score presented as truth.

  • Candidate Alpha

    Compact-fast configuration

    Quality ceiling
    Moderate
    Latency class
    Strict
    Cost class
    Low
    Failure behaviour
    Overconfident on rare policy edge cases.
  • Candidate Delta

    Cheap draft configuration

    Quality ceiling
    Moderate
    Latency class
    Strict
    Cost class
    Low
    Failure behaviour
    Grounding collapses under adversarial paraphrases.
Trade-off / pair comparison
CandidateQuality ceilingLatency classCost classFailure behaviour
Candidate AlphaModerateStrictLowOverconfident on rare policy edge cases.
Candidate DeltaModerateStrictLowGrounding collapses under adversarial paraphrases.

Active record: compare survivors; no automatic CHOOSE

Eligibility after hard constraints

  • Candidate Alpha

    Compact-fast configuration

    REJECTED

    Clears a moderate bar on common tickets.

    Fails quality bar

  • Candidate Beta

    Balanced mid configuration

    ELIGIBLE

    Holds a high bar under the shared protocol.

    Occasionally slow on multi-step tickets; rarely invents policy.

  • Candidate Gamma

    Careful large configuration

    ELIGIBLE

    Best grounded usefulness and deferral discipline in this set.

    Misses interactive latency; cost dominates if unconstrained.

  • Candidate Delta

    Cheap draft configuration

    REJECTED

    Fast and cheap; only a moderate bar is honest.

    Fails quality bar

Trade-off / pair comparison

Several candidates remain. Compare categorical trade-offs, not a single weighted score presented as truth.

  • Candidate Beta

    Balanced mid configuration

    Quality ceiling
    High
    Latency class
    Tight
    Cost class
    Mid
    Failure behaviour
    Occasionally slow on multi-step tickets; rarely invents policy.
  • Candidate Gamma

    Careful large configuration

    Quality ceiling
    Very high
    Latency class
    Relaxed
    Cost class
    High
    Failure behaviour
    Misses interactive latency; cost dominates if unconstrained.
Trade-off / pair comparison
CandidateQuality ceilingLatency classCost classFailure behaviour
Candidate BetaHighTightMidOccasionally slow on multi-step tickets; rarely invents policy.
Candidate GammaVery highRelaxedHighMisses interactive latency; cost dominates if unconstrained.

Active record: compare survivors; no automatic CHOOSE

Eligibility after hard constraints

  • Candidate Alpha

    Compact-fast configuration

    REJECTED

    Clears a moderate bar on common tickets.

    Fails quality bar

  • Candidate Beta

    Balanced mid configuration

    ELIGIBLE

    Holds a high bar under the shared protocol.

    Occasionally slow on multi-step tickets; rarely invents policy.

  • Candidate Gamma

    Careful large configuration

    REJECTED

    Best grounded usefulness and deferral discipline in this set.

    Fails latency constraint

  • Candidate Delta

    Cheap draft configuration

    REJECTED

    Fast and cheap; only a moderate bar is honest.

    Fails quality bar

Trade-off / pair comparison

One candidate clears the hard constraints. Inspect failure behaviour before treating CHOOSE as automatic.

Candidate Beta

Balanced mid configuration

Occasionally slow on multi-step tickets; rarely invents policy.

Quality ceiling
High
Latency class
Tight
Cost class
Mid

Active record: CHOOSE is possible after failure inspection; REJECT / RETEST remain valid

Eligibility after hard constraints

  • Candidate Alpha

    Compact-fast configuration

    REJECTED

    Clears a moderate bar on common tickets.

    Fails quality bar

  • Candidate Beta

    Balanced mid configuration

    REJECTED

    Holds a high bar under the shared protocol.

    Fails latency constraint

  • Candidate Gamma

    Careful large configuration

    REJECTED

    Best grounded usefulness and deferral discipline in this set.

    Fails latency constraint

  • Candidate Delta

    Cheap draft configuration

    REJECTED

    Fast and cheap; only a moderate bar is honest.

    Fails quality bar

NO CANDIDATE MEETS THE BAR → NO RECOMMENDATION

No winner is manufactured. Retest with a revised bar, different configurations, or accept that none of these candidates fit this workload.

Active record: NO RECOMMENDATION

Eligibility after hard constraints

  • Candidate Alpha

    Compact-fast configuration

    REJECTED

    Clears a moderate bar on common tickets.

    Fails quality bar

  • Candidate Beta

    Balanced mid configuration

    REJECTED

    Holds a high bar under the shared protocol.

    Fails quality bar

  • Candidate Gamma

    Careful large configuration

    ELIGIBLE

    Best grounded usefulness and deferral discipline in this set.

    Misses interactive latency; cost dominates if unconstrained.

  • Candidate Delta

    Cheap draft configuration

    REJECTED

    Fast and cheap; only a moderate bar is honest.

    Fails quality bar

Trade-off / pair comparison

One candidate clears the hard constraints. Inspect failure behaviour before treating CHOOSE as automatic.

Candidate Gamma

Careful large configuration

Misses interactive latency; cost dominates if unconstrained.

Quality ceiling
Very high
Latency class
Relaxed
Cost class
High

Active record: CHOOSE is possible after failure inspection; REJECT / RETEST remain valid

Eligibility after hard constraints

  • Candidate Alpha

    Compact-fast configuration

    REJECTED

    Clears a moderate bar on common tickets.

    Fails quality bar

  • Candidate Beta

    Balanced mid configuration

    REJECTED

    Holds a high bar under the shared protocol.

    Fails quality bar

  • Candidate Gamma

    Careful large configuration

    REJECTED

    Best grounded usefulness and deferral discipline in this set.

    Fails latency constraint

  • Candidate Delta

    Cheap draft configuration

    REJECTED

    Fast and cheap; only a moderate bar is honest.

    Fails quality bar

NO CANDIDATE MEETS THE BAR → NO RECOMMENDATION

No winner is manufactured. Retest with a revised bar, different configurations, or accept that none of these candidates fit this workload.

Active record: NO RECOMMENDATION

Eligibility after hard constraints

  • Candidate Alpha

    Compact-fast configuration

    REJECTED

    Clears a moderate bar on common tickets.

    Fails quality bar

  • Candidate Beta

    Balanced mid configuration

    REJECTED

    Holds a high bar under the shared protocol.

    Fails quality bar

  • Candidate Gamma

    Careful large configuration

    REJECTED

    Best grounded usefulness and deferral discipline in this set.

    Fails latency constraint

  • Candidate Delta

    Cheap draft configuration

    REJECTED

    Fast and cheap; only a moderate bar is honest.

    Fails quality bar

NO CANDIDATE MEETS THE BAR → NO RECOMMENDATION

No winner is manufactured. Retest with a revised bar, different configurations, or accept that none of these candidates fit this workload.

Active record: NO RECOMMENDATION

Decision Record

How this work resolves: CHOOSE, REJECT, RETEST, or NO RECOMMENDATION.

  • CHOOSE

    A surviving candidate is defensible for this bar and constraints.

  • REJECT

    A candidate fails hard requirements or an unacceptable failure mode.

  • RETEST

    Revise workload, bar, protocol, or configuration and run again.

  • NO RECOMMENDATION

    No eligible candidate: a valid first-class outcome.

Natural next step

If this is your live decision, discuss the real workload and constraints. You can also inspect published synthetic model-selection evidence (method evidence only).