§ How it works

From manuscript to editorial decision in eight minutes.

An eight-stage pipeline that mirrors a journal's editorial committee. Here is exactly what happens to your paper, in order.

§ 01: The pipeline

Eight stages, end to end.

No black boxes. Every stage logs structured output that the next stage reads. You can trace any finding from the final report back to the page in your manuscript.

01

PDF extraction

~10 s

Custom multi-column parser. Recovers spacing from character positions. Strips running headers and page numbers.

02

Security scan

~5 s

Detects invisible Unicode, prompt injection phrases, hidden role markers. Strips them before any agent sees the text.

03

Section annotation

~15 s

Haiku 4.5 inserts inline section markers so each agent focuses on the parts of the paper relevant to its specialty.

04

Citation verification

~30 s

Each reference checked against CrossRef and Semantic Scholar. DOIs verified. Retracted papers and title mismatches flagged.

05

Independent review

~3 min

Five specialist agents review the paper in parallel. Each produces structured findings with page numbers and exact quotes.

06

Adversarial deliberation

~2 min

Each agent reads the others' findings. Must REBUT with paper evidence or ESCALATE missed findings. Silent disagreement is not allowed.

07

Editorial synthesis

~1 min

An independent editor weighs all 10 outputs (5 reviews × 2 rounds). Classifies findings as consensus, contested, or unique. Computes the score.

08

Report generation

~10 s

Interactive split-view with click-to-highlight. PDF export. Every finding traceable back to its source quote in your manuscript.

§ 02: The five specialists

Same foundation model. Five different mandates.

All five agents run on the same large language model. The specialisation comes from structured system prompts that define each agent's scope and, critically, its refusal scope. Dr. Stats does not comment on writing. Dr. Writing does not judge methodology. This constraint is what produces focused, non-overlapping feedback. Single-agent review cannot do this because a single prompt cannot simultaneously specialise in five directions.

Dr. Methods

The methodologist.

Audits experimental design, controls, sample selection, replicability. Surfaces unstated assumptions and missing comparison groups.

Focus sections
MethodsExperimental SetupProcedure
Will not review
Statistical detailProse qualityCitation completeness
Dr. Stats

The statistician.

Checks 18 named failure modes: confidence intervals, multiple-comparison correction, VIF omission, distribution assumptions, power, effect-size reporting.

Focus sections
ResultsTables & figuresStatistical analysis
Will not review
Methodology choiceWritingLiterature gaps
Dr. Literature

The reader.

Checks novelty claims against the literature. Flags missing seminal works, mis-cited papers, and overstated contributions relative to prior art.

Focus sections
IntroductionRelated workDiscussion
Will not review
MethodsStatisticsBaseline strength
Dr. Writing

The editor.

Checks clarity, structure, terminology consistency, claim-evidence alignment. Flags hedge inflation and unsupported “we show” assertions.

Focus sections
AbstractConclusionThroughout
Will not review
MethodologyStatistical correctnessCitation accuracy
Dr. Baseline

The skeptic.

Asks the uncomfortable question: did you compare against the right baseline? Flags weak comparators, ablations missing, and “no comparison” claims of state-of-the-art. Frequently the deciding voice in deliberation.

Focus sections
ExperimentsResultsComparison tables
Will not review
WritingLiterature breadthStatistical machinery
§ 03: The REBUT / ESCALATE protocol

What makes PeerPanel adversarial.

Most multi-agent AI reviews concatenate output. We do not. After the independent round, every agent reads every other agent's findings and must take a structured action on each: rebut, escalate, agree, or retract. Silent disagreement is forbidden.

The protocol is enforced at the schema level: an agent's deliberation output cannot be accepted unless it accounts for every cross-finding. This is what produces the “shifted in deliberation” indicators you see in the dashboard: an agent who started with seven findings and ended with five, because two were retracted under cross-examination.

ActionWhen usedRequirement
REBUTAnother agent's finding contradicts evidence in the paper.Must include an exact quote and page number that disproves the original finding.
ESCALATEAnother agent missed something within your specialty.Must include a quote, page number, and explanation of severity.
AGREEAnother agent's finding is consistent with your reading.Adds confidence weight. Does not duplicate the finding.
RETRACTYou are convinced your own finding was wrong by paper evidence.Must reference the contradicting passage. Editor logs the retraction.
Epistemic independence rule

“A peer disagreement is not evidence. Only a paper passage is. Do not retract unless another agent quotes a passage that contradicts your finding.”

§ 04: Editorial synthesis

The editor is not a vote-counter.

After deliberation, an independent editor agent reads all ten outputs (five initial reviews and five deliberation rounds), then re-reads the paper. The editor's job is not to tally agreement. It is to weigh each finding against the manuscript itself.

The editor has explicit override power. A finding can be rejected even if all five specialists agreed on it, if the editor's re-reading does not support it. Conversely, a finding raised by a single agent can be promoted to “major” if the paper evidence warrants it. Consensus is a useful prior, not a verdict.

Every override is logged. Every finding in the final report carries a confidence weight, a classification (consensus, contested, or unique), and a link to the exact source passage.

§ 05: Scoring formula

We show our work.

Scores start at 100 and are reduced by weighted findings. Confidence is a 0 to 1 multiplier set by the editor based on evidence strength. The formula is fixed and published: no hidden weights, no opaque adjustments.

Table 1: Finding type to point deduction

Finding typeDeduction
Major consensus−8 × confidence
Major unique−4 × confidence
Minor consensus−3 × confidence
Minor unique−1 × confidence
Retracted finding+2
Editor-rejected consensusno deduction

Table 2: Score to decision mapping

ScoreDecision
≥ 85ACCEPT
60 to 84MINOR REVISIONS
30 to 59MAJOR REVISIONS
< 30REJECT

Vibes-based scoring is not science. We show our work.

§ Try it

See it on your own paper.

Three free reviews per researcher during Research Preview. No credit card.

Start your first review →