zeno

00 / overview - research program

The cognition research behind the instrument.

AI throughput compounds. Human deliberate attention is a fixed-capacity channel. Everything zeno measures sits in that gap - and every number on this site traces back to a peer-reviewed or pre-registered source.

The papers ↓ The 14 foundations ↓

Pre-registered & frozen

The RTLX-S validation and SCED field study were pre-registered before data collection. The design is frozen; the analysis plan is fixed.

Claims are mapped

Every research claim on this site is enumerated in claims-map.json, and updates ship via feed.xml.

Local-first & auditable

Capture runs on your machine by default - local-first and auditable, your cognition never leaves your control. Report issues via security.txt.

01 / papers - the program

Three papers. One thesis.

Everything below feeds one argument: the bottleneck in AI-assisted work is the human supervising it. The thesis paper states the case; the two protocols put it under pre-registered test.

02 / concurrency - the curve

Attention peaks near four.

Effective output rises with parallelism, then the cost of holding it all in your head takes over. Across domains that look unrelated - supervised agents, monitored screens, working-memory chunks, live conversations - the peak clusters at a small, strikingly similar number. Pick a domain and watch the shape hold.

Cognitive throughput versus number of parallel streams An inverted-U curve. Output rises with added parallel streams to a peak near four, then declines. PEAK parallel streams (N) effective cognitive output
Domain
AI agents under supervision
Peak at
N = 4measuring
Signal
RTLX-S supervision load climbs steeply once you pass ~4 parallel agents.

Curve data lives in one shared file, grounded in the R1-R6 evidence review; agents and conversations are evidence-shaped and per-user calibrated.

Our working hypothesis: the peak is a property of human attention, not of the thing being supervised. zeno's job is to measure where your peak sits, on your real workload, instead of guessing.

Full research page →  ·  The Bandwidth Gap: preview above ↑

03 / prosoche - protocol v1.0 preview

A four-week attention trial, pre-registered.

4-arm
RCT: prosoche, mindfulness, productivity, waitlist
N=180
Standard-tier target sample, with attrition padding
18 wks
Total participant commitment, baseline to final follow-up

The protocol tests whether prosoche, a Stoic attention discipline centered on impression-checking and deliberate assent during action, performs differently from matched mindfulness and productivity controls in AI-supervisor work. The pre-specified primary contrast: prosoche vs mindfulness on NASA-TLX change during a standardized AI-mediated task.

Read the full protocol →  ·  All papers ↑

04 / sclt - theory v1.0 preview

Cognitive load theory, extended to agent crews.

SCL(t) = TIL + IEL + TCL + OL + IL + IDL
16-cell
Within-subject 2x2x2x2 validation design
N=80+20
Main sample plus in-lab physiological subset

SCLT argues that classical cognitive load theory under-specifies the reality of supervising AI agent crews. Supervisors are not primarily learning domain schemas: they are calibrating trust, sampling outputs, integrating heterogenous deliverables, and deciding intervention timing under uncertainty. Four new load constructs carry that work - trust calibration, oversight, integration, and intervention decision load.

Read the full brief →  ·  All papers ↑

05 / method - how we do research

Method before data.

Four rules govern every study in the program. They are boring on purpose: rigor is the product.

R1 Pre-register before data Hypotheses, contrasts, and analysis plans are registered before the first participant is enrolled.
R2 Freeze designs Registered protocol wording does not move after registration. Apparatus wraps around it; it never touches it.
R3 Publish the claims map Every public claim is enumerated in claims-map.json with its source. If a number is on the site, it is in the map.
R4 Report nulls Results publish whether or not they flatter the thesis. A null on our own instrument is a result, not a failure.

06 / foundations - evidence base

Fourteen foundations. Every claim sourced.

zeno's model is not a metaphor. It stands on six decades of workload, attention, and automation research - from the workload scale NASA validated in 1988 to a 2025 randomized controlled trial of AI-assisted experts.

5 claims 5 sourced
Site-wide research claims, enumerated in claims-map.json
  1. 01

    NASA-TLX workload scale

    The validated workload standard zeno adapts. Hart & Staveland 1988

    cited in: Whitepaper V · SCLT 4 · Prosoche 5

  2. 02

    Raw-TLX validity

    License to drop pairwise weighting. Byers, Bittner & Hill 1989

  3. 03

    Cognitive load theory

    Working memory is capacity-limited. Sweller 1988

    cited in: Whitepaper VI · SCLT 1

  4. 04

    Yerkes-Dodson law

    The inverted-U; the concurrency curve's ancestor. Yerkes & Dodson 1908

  5. 05

    Multiple Resource Theory

    Parallel tasks interfere super-additively. Wickens 2008

    cited in: SCLT 2 · SCLT refs

  6. 06

    Supervisory control

    Managing agents is supervisory control. Sheridan & Verplank 1978

    cited in: SCLT 2

  7. 07

    Levels of automation

    Automation transforms work and adds coordination demands. Parasuraman, Sheridan & Wickens 2000

    cited in: SCLT 2 · SCLT refs

  8. 08

    Ironies of Automation

    Automating the easy parts leaves the hardest residual. Bainbridge 1983

  9. 09

    Vigilance is hard work

    Monitoring is not free attention. Warm, Parasuraman & Matthews 2008

  10. 10

    The lumberjack effect

    More automation, worse failure recovery. Onnasch et al. 2014

  11. 11

    Automation complacency

    Emerges under multi-task load; afflicts experts. Parasuraman & Manzey 2010

  12. 12

    Interruption recovery cost

    ~10-15 min to resume programming after a break. Parnin & Rugaber 2009

  13. 13

    AI made experts 19% slower

    A randomized controlled trial - while developers felt faster. Becker et al. 2025, arXiv:2507.09089

    cited in: Whitepaper IV · Prosoche refs

  14. 14

    Human-AI combos often underperform

    Meta-analysis: combinations are frequently worse than the best alone. Vaccaro, Almaatouq & Malone 2024, Nature Human Behaviour

07 / pre-release - waitlist

Every claim sourced. Waves are opening.

This instrument is in pre-release. Waves exist because the instrument is calibrated per cohort, and every early user gets direct access to the researcher.

waitlist - first 250 lock a 30-day trial + founding price
Join the waitlist - 30-day Pro trial See the live demo →