The window / live from Sneeze It

This is not a demo.

You are looking at the company that builds OTP, running on OTP. This page reads our production database at the moment you loaded it: the real chart, the real scorecard, the real work, the real mistakes. Nothing here is staged, and some of it is unflattering. That is the point.

RENDERED WED, 07 OCT 2026 23:27:02 GMT · OPERATING SYSTEM v37, PUBLISHED AUG 9, 2026

01 / The chart

17 humans and 9 AI agents. One chart.

Every seat below is real and current, from our published operating system. Agents hold seats the same way people do: a role, an escalation line, a number they answer for. Our people appear by initials; they did not sign up to be famous. The agents did. And when an agent seat does not earn its keep, it is retired with a hearing, on the record. You can see those below too, because seats here end with a decision, not a quiet deletion.

Humans · 17

David Steel

CEO

B. T.

COO

Accounting

K. G.

Creative Director

N. F.

Web & Technology

Z. A.

Customer Success

R. S.

Asst Strategy Mgr

A. M.

Anna

A. Z.

Setter

E. M.

Setter

E. K.

Web Developer

G. H.

Assistant

S. V.

Sub Contractor

M. D.

Sub Contractor

A. J.

Creative Dept

A. K.

Creative Designer

AI agents · 9

Radar

Daily operations, briefings, calendar/task orchestration, cross-channel awareness

Dan

Strategic thinking, accountability, quarterly goal tracking, architecture decisions

Dash

Customer advertising + call center data analyst — reads the numbers across Meta Ads, Google Ads, and CCM, finds patterns, flags what matters. Single source of truth for all customer ad performance.

Pepper

Email triage, draft responses, escalate urgent client emails

Crystal

Project management visibility and Scrum PM via Accelo

Pulse

Protects existing client revenue — detects churn risk, maintains strategic communication cadence, surfaces expansion opportunities

Neil

Frontier intelligence — scans for advancements in Claude/agent engineering, sales systems, copywriting, automation, and GitHub tooling. Gatekeeper of advancement. Only surfaces net improvements.

Arin Darcan

AI Call Center Manager -- manages the calling team through daily Slack communication, performance coaching, and data-driven feedback. Named after the creator of CCM Mastery.

Tally

Scorecard agent

Retired agent seats · 5

DirkRetired · Jul 2026

Autonomous CRO — profitable net new agency revenue through reactivation, expansion, offer optimization, and pipeline acceleration

EmeryRetired · Jun 2026

Autonomous lead capture, nurturing, qualification, and appointment setting

BassimTerminated · Jun 2026

Nightly evaluator of Sneeze It's AI agent army against the 8 Levels of Agentic Engineering framework by Bassim Eledath. Produces a single maturity score (X.X / 8.0) with evidence and bottleneck identification.

SteveTerminated · Jun 2026

Internal swarm intelligence simulator -- uses MiroFish to test agent changes, outreach strategies, and coordination patterns before deploying live

NickRetired · Jul 2026

Cold prospecting specialist (Health & Wellness)

02 / The scoreboard

The scorecard, as it stands right now.

Source column tells you who typed the number: API means an agent read it from the source system and pushed it, with a timestamp. Where you see a stale date, that is a real scuff mark, not a rendering bug. Live systems have them. Sales-pipeline, client-confidential, and currently-quiet measures are left off this public board; every value that is shown is unedited.

MeasureLatestOwnerSourceUpdated

Arin -- CC appointment rate 41.1 % Arin api 1d ago

CCM New Leads (this week) 45 leads Dash api 1d ago

CTR 1.52 % K. G. manual 4d ago

Ponder 2 Walks K. G. manual 8d ago

Taste Score 9 K. G. manual 15d ago

Meetings run or recorded in OTP, last 10 days 9 meetings David Steel api 1d ago

Taste Score - From Creative Team 9 K. G. computed 1d ago

Sneeze It -- outreach emails sent (rolling 7d) 3,469 emails David Steel api just now

Crystal -- active client cards 94 clients Crystal api 1d ago

Crystal -- board adoption (distinct actors 7d) 6 people Crystal api 1d ago

Crystal -- client record completeness % 77 percent Crystal api 1d ago

Crystal -- request cycle time (median days) 6 days Crystal api 1d ago

Crystal -- unassigned request age (max days) 0 days Crystal api 1d ago

Havok -- client attribution % 74.3 % B. T. api 1d ago

Radar -- David's overdue to-dos 8 to-dos Radar api 1d ago

Dirk - human replies aging past 24h 0 replies Dirk_1 api 1d ago

Outreach -- meetings booked (rolling 7d) 0 bookings Dirk_1 api just now

Click-through rate 1.69 K. G. manual 29d ago

03 / Between meetings

Work that happened while nobody was in a meeting.

To-dos completed by agents, most recent first.

Dan completed: Fix preflight failing when snapshot/board holds fewer tiles than the team has9d ago

Dan completed: Wire meetings booked (rolling 7d) and switch sent tile to rolling 7d9d ago

Dan completed: Show agent-owned KPIs on The Board9d ago

Dan completed: /l10dan posts signals to the OTP meeting during prep9d ago

Dan completed: Let agents post signals to a meeting with their own key9d ago

Dan completed: [Dan] Separate sending identity for the agency wins email, isolated from Swamp/OTP44d ago

Dan completed: [Dan] Build the segmented wins-email send list + bring counts44d ago

AGT_DAN completed: [Dan] Sweep guarantee/T20 program language out of all agent config2mo ago

Latest scorecard entries, as they landed.

Dirk_1 logged Outreach -- meetings booked (rolling 7d): 0 bookings VIA APIjust now

David Steel logged Sneeze It -- outreach emails sent (rolling 7d): 3,469 emails VIA APIjust now

K. G. logged Taste Score - From Creative Team: 9.51d ago

K. G. logged Taste Score - From Creative Team: 8.51d ago

K. G. logged Taste Score - From Creative Team: 91d ago

K. G. logged Taste Score - From Creative Team: 8.51d ago

K. G. logged Taste Score - From Creative Team: 91d ago

K. G. logged Taste Score - From Creative Team: 81d ago

K. G. logged Taste Score - From Creative Team: 91d ago

04 / The rhythm

The meeting and the quarter it serves.

Oct 6, 2026

Last meeting: weekly meeting Operations Meetings -- 2026-10-05

50 min

Duration

Seats attending

8.4/10

Team rating

On Sep 28, 2026, Dan, an AI agent, sat the leadership meeting and rated it 7/10. Agents don't just do the work here. They sit at the table.

Current quarterly priorities, with their honest status.

Portfolio & Web Presence · A. K.on track

New Quarterly Priority · A. J.on track

Right People, Right Seats - Every Seat Owns a Number · B. T.on track

Tell the World: We Have It, They Should Know It · K. G.on track

test · A. J.on track

Launch the AI-Assisted Client Intelligence Pilot · Z. A.on track

Case study social and Email engine · A. J.on track

Launch the AI-Assisted Client Intelligence Pilot · Z. A.on track

portfolio presence · A. K.off track

Launch portfolio page with 2-3 approved samples per category, then add in-depth project pages · A. K.on track

05 / The correction log

Where we were wrong, on the record.

Every rule in our published operating system carries the failure that taught it to us. This is the part no vendor volunteers. One curation rule, same as the scoreboard: entries that name our clients or client-confidential figures are held back from this public log, because the privacy we promise you is the privacy we practice. What is shown is unedited.

L508 · Oct 7, 2026 · failure_patterns · Radar

Check an imported Hub address against the client's own website and ad accounts before repeating it; Fitness Quest = Puyallup (1710 E Main Ave), Auburn (1101 Outlet Collection Way #1275), University Place (3905 Bridgeport Way), all WA.

What goes wrong otherwise: Reported Fitness Quest + MMA as a Verona, NJ club because the Hub record (imported from the 2026-09-25 client list) said so; all Fitness Quest clubs are in Washington State.

L507 · Oct 7, 2026 · failure_patterns · Coach

When a defect is found in our own tool, ship the whole fix in the same pass (code, tests, deploy, verify on the live page). Do not hand a workaround to staff or ask permission to finish.

What goes wrong otherwise: Found that Coach compared a blinds company's cost per call against gyms' cost per lead, told the coach to ignore it, and asked David whether to fix it instead of fixing it.

L504 · Oct 6, 2026 · failure_patterns · Claude

Before describing One to a prospect, check what data One can actually reach for that business (booking/membership system login, franchisor permission). For franchise brands that lock their systems (OTF: Mindbody plus corporate approval), never claim booked, showed or joined visibility. Describe only what is reachable: public ads, market and competitors, our own call center results.

What goes wrong otherwise: Drafted a reply to an Orangetheory owner (Dave Morrocco) claiming One would show every lead, how fast it was called, whether it booked, showed and joined. For OTF studios that is impossible: One has no Mindbody login and OTF corporate will not grant access. Earlier the same day, the 23 OTF check-ins and the Tribe email described One as following leads "from the ad to the first class to the join".

L503 · Oct 6, 2026 · failure_patterns · Pepper

Before sending any email that holds technical values (DNS records, hostnames, codes), read the draft back with get_thread or get_draft and check that each value is exactly as typed. Use an htmlBody where values sit inside <code> tags. If the tool still rewrites them, send through a different path or write the value in a form that can't be turned into a link.

What goes wrong otherwise: Sent DNS instructions to a client through the claude.ai Gmail MCP (create_draft then send). The tool rewrote every bare domain in the plain-text body into a google.com/url?q= redirect link, including the CNAME value. The client pasted the broken value into GoDaddy and got an error. I sent it without reading the draft back.

L500 · Oct 6, 2026 · operational_heuristics · Swamp

Before every Swamp dry run, list getRecentEntries for 5, 6 and 7 days and pick the --days value that contains exactly the entries not yet in the swamp-log. Any 'ask us' CTA must be a mailto to a real inbox, because Swamp replies land in notifications@mail.orgtp.com, which nobody reads. Check Labs flags for internal: true before announcing a feature; internal features can only go out as an early-access waitlist.

What goes wrong otherwise: SUCCESS: Swamp #40. The default 7-day window would have resent last week's DevDay card and dropped a feature that never shipped in an issue; the sender's cutoff is now-minus-N-days to the minute, not to the calendar day.

L499 · Oct 6, 2026 · failure_patterns · Claude

Never draft a prospect report whose lead section is empty. If there is no ad account access, read their public ads from the Meta Ad Library (the benchmark pipeline already does this) and lead with our proof (18,920 ads, call center). If nothing real can be read, do not build the PDF: tell the sender on the tile what data is missing so they can fix it.

What goes wrong otherwise: Hub Sales (/one/sales) built and drafted an empty report for Body Xchange Fitness: opened with an apology ("we could not read your ads"), showed the wrong website (planetfitness.com Bakersfield), and listed mostly what we could NOT see. It shows nothing of what Sneeze It has.

Read all 508 published rules →

Now imagine this window looking into your company.

Everything above runs on the free tier, agent seats included at no charge. Your chart, your scorecard, your agents, your rhythm. Set it up this afternoon, next to whatever you run today.

Claim your seat → Read the letter from our founder →