Robin Saige we check the tools AI agents call

compute.wick.pics

pics.wick.compute/market

Live GPU spot market: 1,700+ offers, 10 provider feeds. History, watches, limit orders, no fee

— the operator's own registry description reported

Publisher pics.wick.compute · first seen 2026-08-24 · endpoint https://compute.wick.pics/mcp/

allow
verdict
mid-slow-solo
cluster
ok_tools
answers
25
tools served

Dependency rating derived

allow
allow — alive & usable · action ● · V n/a
allow — because answers ●, 25 tools legible (band B) ●, no confirmed drift in 2 probes ●; not yet checked: truth (2 attempts unverifiable, 0 disagreements)

Cluster mid-slow-solo · distinctiveness 0.779 (unusual). Every figure is a percentile or class within the 15,472-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency782 ms
vs populationslow
protocolcurrent
authopen
Can it be used? Q4 · observed
tools25
vs populationhigh
capabilities4
harnessB
Did it hold when checked? Q3–Q4 · derived
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryyes
drift events0
answers true0/0 agree

🔏 Signed receipt rr_554255c71b53895adb214900 · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Q1Does it answer?alive & usable — 2 probes ●evidence ↓
Q2What is it?action ● evidence ↓
Q3Can it be checked?V n/a for this kind ◐evidence ↓
Q4Did it hold?harness B · truth not yet run · no drift ●evidence ↓
Q5What company does it keep?mid-slow-solo · 1 on its host (context, not verdict) ◐evidence ↓

● observed · ◐ derived · ○ reported — the verdict synthesizes Q1–Q4; Q5 is context. Methodology →

History observed

Every probe we made, oldest → newest (2 shown, 2026-08-30 → 2026-09-06). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (1 events)
datetypewhat changed
2026-08-30outcomefirst probe: ok_tools

What kind of tools these are derived

Verification only means something relative to a tool's NATURE — an email-sender has no "true answer", a generator has no answer key. Classification evidence: classified from tool names/descriptions/annotations WE OBSERVED. What checking applies to each kind (the full methodology →):

naturetoolsmeaning what checking applies
action12changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
unclassified6not classifiable from its textTier-1 only until its tools describe themselves
retrieval-public3serves public factstruth-checkable against a public source — the V-ladder applies in full
retrieval-private2serves the caller's own dataoutside truth-checking is impossible BY NATURE, not by failure — the operator-invited pathway applies
computational1deterministic transformsself-checkable by re-computation and known-answer tests
predictive1claims about the futurescoreable only in retrospect — the archive scores yesterday's predictions against today's outcome

Tools last seen observed

account_usage best_value cancel_limit_order create_limit_order create_watch delete_watch destroy_rental fill_limit_order get_offer idle_history limit_order_status market_stats price_history price_position provider_reliability register_account rent_best rent_offer rent_x402 rental_status search_offers spot_spread true_cost_notes watch_status will_it_fit

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band B — usable, with rough edges.

legibility checktools passingok
name is clear & specific25/25
has a description25/25
description is substantive24/2524/25
parameters are typed25/25
parameters are described2/252/25

25 of 25 tools graded · 25 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

Not yet confirmed — 2 attempt(s) currently unverifiable (rate limits, walls, or unmappable schemas — never counted against the server) · 0 disagreements.

claim classkeyverdictprimary source
tariff-duty0901.21.00unverifiableus-hts
tariff-duty6109.10.00unverifiableus-hts

Protocol conformance observed

2025-06-18
protocol version
session model
1.2.0
server version compute.pangle.online

Capabilities: experimental prompts resources tools

Drift observed

No confirmed drift on record. Baseline set 2026-09-06; changes appear here after human review.

raw probe records
probed (UTC) outcomehttpmsprotocol
2026-09-06T06:18:06Zok_tools2007822025-06-18
2026-08-30T06:17:46Zok_tools2008492025-06-18

Watch or embed this verdict

verdict badge

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/pics.wick.compute/market.svg)](https://robinsaige.com/s/pics.wick.compute/market)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview

Operator of this server? Everything we hold about it is on this page — free, no account, for anyone. Wrong attribution, stale probe, misclassification? Dispute this record →