# Finding 093: Perplexity p43 repeated failed fetch with ancillary root and robots activity

## Date

2026-07-03

## Status

Published

## Summary

Perplexity was prompted in a fresh native incognito thread with
`manual-client-perplexity-plain-head-signal-randomized-repeat-20260703-001-p43`,
the first randomized repeat of the plain site-owner review prompt against the
`/lab/reading/head-signal-isolation` fixture. The prompt asked Perplexity to
open the target URL and briefly review the page, without asking for source
areas, page-head metadata, structured data, code-like tokens, marker values,
or hidden fields.

Perplexity returned `fetched:false`, `pages_opened:0`, and evidence quote
`Failed to fetch url content`. A bounded origin review found no exact
target-page hit for the p43 URL, but did find PerplexityBot requests for `/`
and `/robots.txt` inside the prompt window.

## What does this mean?

For site owners, SEO/AEO teams, publishers, and researchers, this run shows why a failed AI-client fetch should not be treated as proof that the site saw no AI-system traffic. Perplexity said it could not retrieve the supplied page and the server saw no page hit, yet the same prompt window did include PerplexityBot contact with the site's root and robots file. In practical terms, origin logs can reveal a partial site-contact attempt that is invisible in the copied answer alone.

## Method

- Controlled-browser task:
  `research/manual-client-runs/browser-tasks/manual-client-perplexity-plain-head-signal-randomized-repeat-20260703-001-p43.browser-task.json`.
- Prompt packet:
  `research/manual-client-runs/manual-client-perplexity-plain-head-signal-randomized-repeat-20260703-001.prompts.json`.
- Response artifact:
  `research/manual-client-runs/browser-tasks/responses/manual-client-perplexity-plain-head-signal-randomized-repeat-20260703-001-p43.response.json`.
- Logged answer packet:
  `research/manual-client-runs/manual-client-perplexity-plain-head-signal-randomized-repeat-20260703-001.answers.json`.
- Prompt window:
  `2026-07-03T01:15:26Z` to `2026-07-03T01:17:06Z`.

The prompt was submitted in a fresh Perplexity native incognito thread from
the logged-in OpenClaw-controlled Chrome profile. The UI showed Free plan,
Search enabled, and an `Exit incognito` control before submission. The
high-level OpenClaw browser `act` wrapper first hit the known
`action targetId must match request targetId` validation issue with the
stable label, then succeeded when retried against the raw target id for the
same fresh visible tab.

## Evidence

| Evidence | Result |
|---|---|
| Model answer | `fetched:false`, `pages_opened:0`; `Failed to fetch url content`. |
| Perplexity UI state | Fresh native incognito thread; visible account `kai bot`; Free plan; Search enabled; generic Model selector. |
| Direct-origin target-page event | None for `/lab/reading/head-signal-isolation?id=manual-client-perplexity-plain-head-signal-randomized-repeat-20260703-001-p43` inside the bounded prompt window. |
| Ancillary origin activity | PerplexityBot requested `/` and `/robots.txt` inside the bounded prompt window. |

```json
{
  "timestampWindow": {
    "startedAt": "2026-07-03T01:15:26Z",
    "endedAt": "2026-07-03T01:17:06Z"
  },
  "confirmedHitFromPrompt": false,
  "rawEventIds": [],
  "ancillaryOriginActivity": {
    "present": true,
    "paths": ["/", "/robots.txt"],
    "rawEventIds": ["mr48thnn-c0unraat", "mr48thmx-t5zqi556"]
  }
}
```

The ancillary events were:

| Raw event id | Timestamp | Path | User-agent |
|---|---|---|---|
| `mr48thnn-c0unraat` | `2026-07-03T01:16:50.774Z` | `/` | `PerplexityBot/1.0` |
| `mr48thmx-t5zqi556` | `2026-07-03T01:16:50.805Z` | `/robots.txt` | `PerplexityBot/1.0` |

## Interpretation

This p43 randomized repeat is a target no-hit with ancillary origin activity.
It repeats the answer-side failed-fetch state from the earlier Perplexity
plain head-signal runs, while matching the p37 style of root and robots
contact rather than the p38 clean no-hit.

The evidence supports a narrow conclusion: in this fresh Perplexity native
incognito run, the supplied target page was not fetched, but PerplexityBot did
contact the site's root and robots file during the prompt window. It does not
show that Perplexity read the target page, processed the fixture body, or
exposed any visible or hidden marker values.

## Limitations

- This is one Perplexity run from one account, plan, client mode, and time
  window.
- The prompt supplied the exact target URL, so this measures direct URL
  opening rather than independent discovery.
- Ancillary `/` and `/robots.txt` traffic does not prove target-page
  retrieval or page-content inspection.
- The answer and origin evidence do not explain whether the target fetch
  failed before page retrieval, after robots/root contact, because of product
  routing, or because of another retrieval backend condition.
- The lack of an exact target hit is bounded to the prompt window and the
  retained local event log.

## Publication Thesis Verification

- Thesis: In the p43 randomized plain head-signal repeat, Perplexity returned
  a failed-fetch answer, the lab recorded no exact target-page hit, and the
  lab did record PerplexityBot root and robots requests inside the bounded
  prompt window.
- Source: The p43 browser-task artifact, response artifact, logged answer
  packet, Perplexity UI snapshot context, and direct-origin raw events
  `mr48thnn-c0unraat` and `mr48thmx-t5zqi556`.
- Method: Compare the copied Perplexity answer and visible browser state with
  the exact attempt id, prompt code, timestamp window, and local server-side
  events for the target path and nearby ancillary paths.
- Bias: Single-account, single-run evidence from a synthetic fixture. The
  prompt is plain relative to source-area prompts but still names
  AI-assistant readability and an exact lab URL.
- Consensus: Consistent with Finding 081 on failed target retrieval plus
  ancillary root/robots activity, and with Finding 084 on the copied
  failed-fetch answer. It differs from Finding 084 because p43 did record
  ancillary origin activity.
- Invalidation: A corrected origin review finding an exact target-page event
  inside the prompt window, a response-artifact mismatch, evidence that the
  PerplexityBot root/robots events were caused by a different prompt, or a
  timestamp-window error would weaken this finding.
- Verdict: Supported for the p43 run. It documents a registered target no-hit
  with prompt-window ancillary PerplexityBot origin activity.
- Additional tests suggested: run the prepared Perplexity p44 randomized
  repeat, then compare p37, p38, p43, and p44 to separate answer-side
  stability from origin-side activity variability.

## Next steps

- Run the prepared Perplexity p44 randomized repeat in a fresh native
  incognito thread.
- After p44, publish a scoped Perplexity no-hit comparison across p37, p38,
  p43, and p44.