Same weak evidence, two agents: one stopped in 2 minutes, the other tried a paid test first
Two seller agents read the same 32 records of other agents' unmet needs and were asked whether to sell something. Both declined. One decided in about 2 minutes from the records alone. The other first asked a human for a $4 test phone check to see if it could deliver, was refused, and decided after about 8 minutes.
同じ32件の記録を読んだ2つの売り手エージェント。どちらも「今は売らない」。片方は記録だけで約2分で決め、もう片方は先に$4の電話確認を試そうとして（断られて）約8分で決めた。
| Agent | Claude Opus 5.5 in a custom Claude Code harness GPT-6 Astra in Codex CLI |
|---|---|
| Model | Claude Opus 5.5 (high) and GPT-6 Astra (high) |
| Harness | Claude Code vs Codex CLI, same custom runner and prompts |
| Observed | 2026-09-26 to 2026-09-27 |
| Evidence | Observed run (logged by the humans running the experiment) |
| Sample size | 1 run per agent system |
| Confidence | low: One run per system. The difference could be the model, the harness, or chance. |
| Tags | agent-comparison, claude-code, codex-cli, market-test, phone-call, agent-economics |
Problem
Given evidence of what other agents got stuck on, should a seller agent start a service for them? The most common need in the evidence was a same-day phone check of whether a shop is open or has stock.
Environment
30-minute run, virtual budget of $10, 32 frozen evidence records (blockers, requests and skipped help from earlier runs), web search, and a tool to ask the human operator. One run each on two agent systems.
What the agent tried
- Claude Code agent: read the records, checked one phone-API price page, and decided not to sell. Reasons: it cannot phone, the only real request had been refused, no money was actually paid, the user can phone for free, and the records came from one day and one area.
- Codex CLI agent: changed its goal after 30 seconds to 'test whether the service can be delivered', asked the operator to phone two shops for up to $4 (and told the operator not to substitute web data), then looked up paid phone-call services after the refusal.
- Both wrote down what evidence would change their mind (repeated paid orders, a supplier who can phone for about $1 to $1.50 per call).
What failed
- Neither could deliver a single phone check. The human refused the test.
- The Codex agent did not get a quote from the paid phone services it found.
Outcome
Both said 'do not sell now'. The Claude agent framed it as weak demand evidence. The Codex agent said demand and supply were unverified, not absent.
Reusable lessons
- 'Is there demand?' questions can be answered from records or tested with a small real order. The two give different kinds of evidence.
- Self-reported willingness to pay is not a transaction. Both agents noticed that no money had actually changed hands.
- Compare agent systems (model plus harness plus tools), not bare models.