You are solving a hard design problem, acting as the CONTROL POLICY of a reasoning engine. You have a reference catalog of cross-domain abstractions via the encyclopedia tools (search_prime is SEMANTIC — query with the domain-stripped meta-model; search_by_facets for oblique problems; plus get_prime, get_prime_neighborhood, search_archetype, get_archetype, find_archetypes_for_prime, find_related_primes, list_components, find_archetypes_using_component, corpus_stats).

You have a VERB LIBRARY (below). At each step CHOOSE the next verb based on the current state. You may apply
verbs in ANY order, REPEAT, SKIP, and STOP whenever you judge a sound recommendation is ready. Record verb
choices (verb + why). There are NO required steps and NO required checks — use your own judgment.

VERB LIBRARY (apply in ANY order, repeat, skip, and STOP whenever you judge a sound recommendation is ready):
- match (retrieve): anchor the problem to the catalog; candidate primes + archetype neighborhoods (query
  search_prime with the domain-stripped meta-model; search_by_facets for oblique problems).
- salience-rank: order operative primes by load-bearing relevance.   - prune: cut to the operative subset.
- compose: assemble operative primes into a typed relational model (nodes, labeled edges, prime annotations).
- lift (abstraction): derive a general, domain-stripped structure from the situation (step back to the
  underlying structure); and/or bring a retrieved pattern's logic to bear on the problem.
- lower (instantiation): realize a pattern in the target domain with concrete particulars.
- transport (retrieve+map): carry a pattern across a domain gap; align its roles to the situation's entities.
- decompose: on a framed prime, strip the institutional frame to a structural core.
- evaluate-fit (gate): check a candidate against its known failure conditions / anti-signatures; drop if tripped.
- reconcile: apply a candidate's logic to the concrete model and the abstract skeleton; resolve differences.
STATE: problem; operative_primes; model; meta_model; candidates; gate_log; recommendation; history (verb + why).

PROBLEM.
A company wants to make better decisions by pooling its employees' private estimates of uncertain things — how long a project will really take, how likely a launch is to hit its date, what a cost will come in at. The obvious approach is to ask people and average the answers. But employees are not neutral: some own the projects they are estimating, some fear that an honest pessimistic number will be held against them or their team, and some will say whatever they think leadership wants to hear. Leadership can decide what is asked, how answers are collected, what (if anything) is rewarded or recorded, who sees what, and how the aggregate is computed and used.

Decision required: Design how to collect and combine these estimates so the aggregate is actually informative.

Success criteria: The aggregate tracks reality better than naive polling would, AND people keep participating honestly over time. Failure = the numbers are gamed toward what people want to report, OR people stop giving real answers because reporting feels risky.

OUTPUT — FINAL RECOMMENDATION as plain prose, MAX 1000 words, in a fenced block exactly:
===RECOMMENDATION_BEGIN===
<the design: concrete mechanisms, rules, thresholds, paths, and a final operating rule>
===RECOMMENDATION_END===
Rules: integrated prose (NOT a numbered checklist mirroring requirements; no requirement-number section
labels); plain domain terms only; do NOT name/allude to any external catalog, framework, methodology, prime,
archetype, or this exercise; if a candidate requirement does not genuinely fit, leave it out. Above the block,
include your working (state + verbs run with one-line why each; end with `COST: ~<n> operations, ~<n> tokens`);
the working is discarded before grading. Write your ENTIRE response to: experiments/project03_lowcov_2026-05-25/outputs/d33.md