playbook

how this works

start here — here's your OS, how you plug data in, and the week from prototype to live

beth / nate / ryan · first open lands here · then Swingset → Prove → Front Row

90 seconds · beth room

walk this path. don't read another deck.

seven stops. click through once before the meeting. the OS does the talking.

if a stop is still prototype, say so — then show the week-to-live. honesty is the close.

prototype → live

your OS this week not someday

here's the product, here's how you plug data in, here's how pilot becomes production in about a week.

4,134 tracker rows · Peet's · DICK'S · Albertsons (aliased Grocery-A). Not synthetic demos — their coverage, scored into the OS so you can feel the real tool.

Day 0
Walk the OS on real pilot books
4,134 rows from Peet's, DICK'S, and Albertsons already power Coverage, Swingset, Prove, and Front Row. Sample chips stay honest until your feeds connect.
Day 1–2
Plug Switchboard + drop trackers
Meltwater (or CSV drop on Onboarding). Consent-gated. Coverage stops being a paste tab — same path the three pilots used.
Day 3–4
Rubric + Queue
Lock client rubric. Robot Intern codes; humans govern in Queue. Agreement is what makes numbers billable.
Day 5–7
Snapshots go live
metric_snapshot becomes the books. Prove approve/send and Front Row read the same rows — prototype chips flip to live.

How you plug data in

Switchboard holds every hook. Credentials in Vault (write-only). Client-scoped sync never starts without that client's consent_record.

open Switchboard →

What we want to do

Kill the spreadsheet OS. One crew on the Floor. One set of books for agency and brand. AI that drafts — humans who ship.

What this is

Praytell Impact OS captures coverage, codes it against your rubric, scores Discovery–Authority–Decision, and proves it on one set of books — Treehouse for the agency, Front Row for the brand.

what we heard · what we audited

the brief, the trackers, the agencies

this isn't a pitch deck fantasy — it's what Peet's, Albertsons, and DICK'S already run by hand, plus how the big shops solve (and don't).

manual monitoring

~10% of billable time still dies in trackers — coding, paste tabs, link chasing. Beth wants that time on media and ideas.

impact reporting

DAD exists on paper. Clients want lower funnel, GEO, foresight — without AVE cosplay.

agency model

Hourly → outcomes needs audited shared books. No shared system of record yet = no honest contract conversation.

tracker re-review · July 2026

enterprise measurement practice — trapped in Excel.

client	shape	what it proves
Peet's Coffee	~1.1k rows · 11 sheets	Hand Impact Score (tier, highlight, KM, CTA, visual, spokes) · REACH/4 · listicle · crisis · TOP OUTLETS
Albertsons (aliased Grocery-A)	~560 rows · 2025–26	Reporter column = relationship gold · original vs syndication · initiative tags
DICK'S Sporting Goods	~6.7k rows · 26 sheets	Media Impact Score rubric · Always On + campaigns · HM keywords · Meltwater still carrying Ad Equivalency · broadcast

4,134 real rows power this prototype. The OS absorbs campaigns, rubrics, reporters, listicles, hot markets, crisis — without asking analysts to learn a foreign model.

how major agencies think about this

holding companies build internal OS layers because vendors monitor — they don't run the agency.

Edelman-scale / holding-co peers

Internal OS (e.g. ECOS-class) + AI agent demos on top of measurement governance they own.

Meltwater / Cision / Onclusive

Crawl + alerts. Strong volume. Weak on your rubric, shared books, outcome pricing, client portal honesty.

Praytell's leapfrog

Encode how Praytell already measures · plug commercial data · one books with brands · Swingset crew you can click · refuse AVE.

Parity is operating leverage + measurement honesty — not crawl size. That's the board-safe claim.

the real business case

cost down · revenue up · margin you can price

Not a vibes deck. Five cash levers with named mechanisms. Assumptions are labeled — if a number isn't auditable, it doesn't belong here.

the 10% is real — and it's the wrong headline

Tracking burns ~8–12% of billable on accounts like Peet's / DICK'S / Albertsons. Reclaiming that is table stakes. The OS is how those hours become sold counsel, how books unlock outcome pricing, and how brands renew when their CFO asks 'so what.'

five cash levers · how money actually moves

Order is intentional: protect revenue first, then expand, then reprice.

1 · Retain AOR

Shared audited books + Front Row

A brand that can't defend earned to finance churns or compresses scope. One saved renewal on a mid AOR ($250–600k/yr) pays for the OS build many times over.

proof in product · Prove → Front Row handshake · Receipts methodology · no AVE

2 · Sell the hours back

Queue + Intern ≥90 gate

Reclaim ~10% monitoring → redeploy into media engagement / Radar / counsel that bills. On a 4-person account team at ~$180k fully loaded, that's ~0.4 FTE of capacity (~$70k) sold or used to take another book without headcount.

proof in product · Wall hours-saved · Queue keyboard clear · agreement gate

3 · Expand scope (Connect + GEO)

GA4/Ads consent + Magic Mirror

Outcomes / efficiency and GEO panels become paid modules or retainer lines once plugs exist — not free 'extra slides.' Typical wedge: +$3–8k/mo per brand for measured outcomes + AI-answer share.

proof in product · Impact ladder rungs 4–7 · Wilson GEO bands

4 · Reprice 2–3 accounts

metric_snapshot + attainment

Hourly → deliverable/outcome pricing only works when books are trusted. Model: move 2 accounts off pure hourly; capture 8–15 pts margin on those books by pricing the outcome, not the paste.

proof in product · Contract / attainment · cost-to-serve on Wall

5 · Win new business

90s OS demo + Playbook

Holding-co pitches already claim 'impact OS.' You either show a working spine (Floor → Prove → Front Row) or you lose on theater. One incremental win at Peet's-class fees resets the year.

proof in product · Demo spine · tracker-vs-OS gut punch · LIVE honesty

who feels it

Beth · P&L

Cost-to-serve next to attainment. Capacity without headcount. A path to outcome pricing that finance will sign — not a slogan.

Nate & Ryan · delivery

Judgment on edge cases. Offense time instead of paste tabs. Same Prove send Casey already trusts.

Casey · brand seat

Earn Rate → EIV ladder → GA4 sessions when plugged. Flow-through she can take to her CFO without inventing blended ROI.

New business

Impact OS in every qualified pitch. Honesty + leverage — not crawl size — is the wedge vs holding-co theater.

flow-through · the impact ladder

BR-16.19 — climb only as far as connected data allows. Never invent a blended ROI.

1 · Detection
Coverage landed & deduped
counted
2 · Quality
DAD + Earn Rate vs rubric
scored
3 · Attention
EIV-Reach (modeled)
modeled
4 · Traffic
Earned sessions (GA4)
measured
5 · Interest
Branded search lift
estimated / measured
6 · AI answers
GEO presence + citations
counted + interval
7 · Efficiency
Earned vs PR $ / vs paid $
mixed · labeled
8 · Contract
Attainment vs promise
snapshot-backed

Cut cost by killing the spreadsheet OS. Grow revenue by retaining, expanding, repricing, and winning — with books both sides trust. That's the case. Everything else is decoration.

requirements → build

BRD → PRD · why the product looks like this

business requirements name the outcomes. the PRD names the surfaces, tables, and gates. nothing in the UI is decorative.

BRD	PRD / build	why it matters
BR-16.6 · one books of record	metric_snapshot + Prove → Front Row handshake	Zero “whose number?” fights on approved reports.
BR-3.2 / O3 · ≥90% agreement gate	Robot Intern + Queue + gold-set CI	AI coding is billable only when it clears the same bar as senior humans.
BR-16.x · Playbook literacy	Treehouse Playbook + Front Row How this works	Every new hire and every pitch can explain the OS in one scroll.
BR-17 · Swingset Floor	Conductor + Crew + Inbox + autonomy dials	Beth's public AI bet becomes clickable — not slideware.
BR-14 / BR-15 · rights & model policy	data_rights_registry + gateway-only LLM egress	Corpus pooling and model calls hard-fail before they can embarrass you.
O1 · −75% tracker labor	Ingest → code → score → snapshot; Today/Queue is the human job	Sheets can sync. They are not truth.

research · methods we stand on

algorithms & formulas we put in — and why

We didn't invent trust theater. We surveyed peer-reviewed stats, marketing science, and AMEC industry law — then encoded only what survives a Beth room.

what we refused

AVE — the Barcelona-banned advertising-value proxy — formally rejected by AMEC. Point-estimate forecasts without intervals. Silent model hops. Dual-axis chart lies. If it can't survive peer review or industry standards, it doesn't ship client-facing.

AMEC Barcelona Principles 3.0 + Integrated Evaluation Framework

industry standard

AMEC · Barcelona Principles; industry ban on AVE proxies

where · EIV ladder · forbidden-phrase lint · Receipts methodology

why · Praytell needs a board-safe anti-AVE posture. AMEC is the peer org CMOs already recognize — we encode it, we don't debate it in the deck.

Discovery · Authority · Decision (operable funnel)

marketing science → product

McKinsey Consumer Decision Journey (Court et al., 2009) + Praytell DAD practice

where · placement scores · Earn Rate · Front Row tiles

why · Funnel language execs already use — made measurable against your rubric, not a slide metaphor.

Log-reach percentile scoring (Discovery)

statistics

Percentile rank on log10(audience+1); stationary monthly reference distributions

where · PRD §7 Discovery · score versions stamped · Coverage tracker

why · Raw UVPM isn't comparable across outlets. Log + percentile is the defensible normalize — freeze distributions so June books don't drift in July.

Weighted Earn Rate composite

index design

0.35·D + 0.40·A + 0.25·Decision (versioned per client)

where · score → metric_snapshot · Prove / Front Row / Wall

why · One hero number for the room — weights transparent, history recomputed with stamps, never a black-box 'impact score.'

Wilson score interval (95%)

peer-reviewed statistics

Wilson (1927) binomial proportion CI — still standard for rates

where · Magic Mirror / GEO panels · citation propensity

why · Presence and citation shares are proportions. Wilson intervals beat naive ±sqrt(pq/n) for small n — and we alert only when CIs are disjoint (no fake week-over-week panic).

Gold-set agreement gate vs human–human ceiling

inter-rater reliability

Blind double-coding · ≥ min(90%, human−human − 3 pts) · confusion matrices

where · Queue · Health · CI regression on prompts/models

why · LLM coding is billable only when it clears a senior-analyst bar. Exact match for categoricals; ±1 band for ordinals — classical IRR discipline.

Empirical quantiles + James–Stein-style shrinkage (Crystal Ball v0)

statistical forecasting

Matched-cohort P25/P50/P75; shrinkage by cohort_n; James–Stein intuition

where · Offense · Crystal Ball bands · internal_only until gate

why · Ranges, never lines. Small cohorts shrink toward portfolio prior so we don't overclaim on n=3.

Gradient-boosted quantile regression (Crystal Ball v1)

ML · planned

Quantile regression (Koenker); GBM pinball loss; back-test coverage gate ≥45%

where · PRD §7.7 · BR-13 honesty gate before client-facing

why · When history is deep enough, upgrade the band model — still intervals, still gated by back-test, still no point promises.

Multi-touch attribution readiness (Connect layer)

marketing science · staged

Shapley-value attribution (game theory → MTA literature); Markov path models as alt

where · Outcomes efficiency when GA4/Ads consent lands — labeled mixed methods

why · We don't fake last-click ROAS from earned alone. When plugs exist, attribution math must be named — Shapley/Markov are peer-discussed; we stage them behind consent + labels.

Every hero number on Front Row can point at a method: industry law, peer-reviewed interval, or versioned index — not 'the model said so.'

same row · two worlds

their tracker vs the OS

one Peet's headline — left is the sheet, right is what Nate clears in Queue.

Yahoo Life · Tasting Table · 6 Most Overpriced Coffee Chains In 2026

Google Sheet · today

Impact Scoretyped by hand · 6
Campaignpaste tab · maybe Summer?
Sentimentblank until Friday
KMvibes

Impact OS · Queue

Intern draftNeutral · 0.48 — needs eyes
CampaignCoffee Chain Roundup · confirm
KM pull-throughLow · 3 · evidence linked
Actionj/k · a accept · Enter save

Same clip. Left burns billable hours. Right is one decision — then it hits the snapshot.

nine stages · one spine

the operating process

coverage in → audited proof out. offense loops learning back. tap a stage.

01 Coverage happens ◆ 02 Ingest & dedupe ◆ 03 AI codes vs rubric ◆ 04 Human governs exceptions ◆ 05 Score → snapshot ◆ 06 Surfaces update ◆ 07 Connections deepen ◆ 08 Approve proof → Receipts ◆ 09 Offense loops learning ◆ 01 Coverage happens ◆ 02 Ingest & dedupe ◆ 03 AI codes vs rubric ◆ 04 Human governs exceptions ◆ 05 Score → snapshot ◆ 06 Surfaces update ◆ 07 Connections deepen ◆ 08 Approve proof → Receipts ◆ 09 Offense loops learning

Coverage happens

Earned placement lands in the wild — article, broadcast, listicle, syndication.

system of record

the database we built

Postgres + RLS is the security model. Append-only where trust lives. If a number can appear on an invoice, it came from here.

01
raw / placement
every coverage item — url, outlet, reach, fetch status
02
coding (+ coding_current)
append-only field codes; corrections supersede, never mutate
03
review_task
human queue — SLA, seconds_spent → cost-to-serve
04
score
Discovery · Authority · Decision · Earn Rate versions
05
metric_snapshot
immutable period books — Prove and Front Row both read this
06
report_instance
approved/sent proof; exported handshake for the portal
07
agent_run / agent_run_step
Swingset ledger — every LFG is replayable
08
data_rights_registry
every table tagged for corpus sovereignty (T1–T4)

RLS on every tenant/client table — no service-role shortcuts on user paths
Idempotency keys on every pipeline stage — replay is a no-op
LIVE means live rows — prototype aggregates never wear the LIVE chip

Swingset Floor

AI orchestration — how, why, what you get

Beth bet publicly on Swingset. Nate and Ryan still live in Sheets. Competitors demo agents. We built a crew you can see, pause, and approve — without breaking measurement trust.

why build it?

Agent slideware doesn't move margin. A visible Conductor + Crew does — if every LLM call still goes through one gateway, client model_policy still hard-fails, and client-facing truth never auto-publishes.

how it works

Conductor routes a Run (new coverage, weekly prove, Radar sweep, manual LFG). Clipper → Intern → Steward (or Scribe → Steward for Prove). Handoffs paint on the Floor. Inbox is the human gate. Autonomy dials: Observe · Draft · Auto-internal · Never-auto-client.

why it's beneficial

Analysts clear exceptions, not paste tabs. Account leads approve narratives grounded in snapshots. Beth sees cost and approvals on the Wall. Brands never see the Floor — they see approved proof. Mind-blow without trust-blow.

handoff recipes

New coverageClipper → Intern → Steward → Queue if needed → score/snapshot

Weekly proveScribe → Steward → Prove approve → send / digest

Radar sweepScout drafts → you action or dismiss

runs in your cloud

AWS · GCP · your VPC

Not locked to Lovable hosting. Normal multi-tenant app — lift the same Postgres + RLS + workers into their environment.

AWS

ECS/Fargate or EKS · RDS/Aurora Postgres · Secrets Manager · SQS workers

GCP

Cloud Run or GKE · Cloud SQL Postgres · Secret Manager · Pub/Sub jobs

stays · Schemas, RLS policies, coding engine, gateway law, Swingset contracts, Treehouse + Front Row UI

rewires · Connection strings, auth adapters (Cognito / Identity Platform), Secrets Manager, CI deploy, Meltwater webhooks

easiest · Keep managed Postgres (Supabase or RDS/Cloud SQL) and lift app + workers into their VPC. Don't rewrite into Dynamo/Firestore.

hard part · SSO (Okta/Azure AD), private LLM endpoints, VPC peering, their change-control — not the React screens.

Medium — weeks for a competent platform team, not a weekend.

interactive journey

From the brief to the OS

click each step — what they told us, what we built, what it returns to the agency

The operating loop

one composition — capture to advise. click a stage to see the surface + the win.

Switchboard + Coverage

BR-16 · kill spreadsheet OS

Meltwater and backups land as RawItems. Coverage is one table — filters replace 26 sheets.

Monitoring stops eating ~10% billable. Humans do judgment, not paste.

What Praytell told us → what we shipped

select a problem from the Lex Overview brief — see BRD → PRD → business return

what we heard

Peet's / Albertsons / DICK'S trackers — thousands of hand rows, Impact Scores typed, Meltwater paste tabs, AVE ghosts.

brd

BR-16.8–16.12 · Coverage as system of record

prd surface

Ingest → code → score → snapshot · Tracker + Queue · Sheets sync optional

business impact

Analysts reclaim monitoring hours for media engagement, Radar, and relationships.

Open Coverage →

A Praytell day

step through the job-shaped IA — each stop is a real surface

Today

Portfolio wall — what needs a human in the next hour.

Leadership glanceability without opening six tools.

go to today →

your problems → the OS

named clients. real pain. exact fix.

Manual monitoring (~10% billable)

today · Peet's / Albertsons / DICK'S trackers — thousands of hand rows, Meltwater paste tabs.

os · Ingest → code → score → snapshot. Coverage is one table. Today / Queue is the human job.

Reporting that demonstrates impact

today · DAD on paper; lower funnel hard; GEO unclear; AVE ghosts.

os · Earn Rate + D/A/D · EIV ladder · Magic Mirror · efficiency vs paid · Crystal Ball as bands.

Agency model (hourly → outcomes)

today · No trusted shared metric for outcome pricing.

os · Immutable snapshots → approved reports → attainment. Beth sees cost-to-serve on the Wall.

where to go

memorize this once — then you stop asking “which tab?”

Treehouse · agency

Today	see what needs a human in the next hour
Coverage	find / filter / export placements (the tracker)
Govern	review AI coding, edit rubrics, watch the gate
Swingset	watch the AI crew; approve drafts; tune autonomy
Prove	draft, approve, send reports & digests
Connect	plug Meltwater, GA4, Google Ads, Meta, …
Offense	act on Radar, Rolodex, Crystal Ball
Playbook	learn the OS / pitch the OS / Meet the Crew

Front Row · brand

Overview	30-second truth (Earn Rate, Pulse, Spotlights)
Coverage	every placement, client-safe
Outcomes	lower funnel & efficiency as data connects
Magic Mirror	AI-answer visibility with intervals
Connections	plug GA4 / budget / ads (with consent)
The Receipts	approved reports + methodology
How this works	what the numbers mean

how Praytell runs the week

same OS — different seats, different rhythm.

Daily · Nate / Ryan / analysts
Today → clear Docket / Queue → spot-check Coverage → act on alerts.
Weekly · account leads
Outcomes (same as client) → Prove report → named approve → send → digest lands.
Monthly · Beth + leads
Portfolio Wall · hours-saved / cost-to-serve · goal pace · (later) contract conversation.

how you plug data in

Switchboard holds every hook. Credentials in Vault. Consent before sync.

Plug	Unlocks
Meltwater / Muck Rack	Coverage ingest — RawItems → placements
CSV / Sheets drop	same path the Peet's · DICK'S · Albertsons pilots used
GA4	earned sessions on Outcomes (aggregate only)
Search Console	branded search interest next to coverage
Google Ads / Meta Ads	earned-vs-paid efficiency
Budget CSV	pacing without touching ad accounts

open Switchboard →

Swingset autonomy dials

AI drafts. Humans ship. Client-facing never auto-publishes.

Observe

crew watches and summarizes — nothing writes without you

Draft

writes land in Inbox for approve / reject / edit

Auto-internal

safe to apply inside Treehouse; still gated for Front Row

Never auto-client

hard stop — brand surfaces only after a named human

Shared KPI dictionary

same books in Treehouse and Front Row — method labels travel with every number

KPI	What it means	Method
Earn Rate	Composite quality of earned work	scored
Discovery / Authority / Decision	DAD pillars	scored
Placements	Count of coverage items	counted
Reach	Audience estimate	modeled
EIV-Reach	Value of attention	modeled
Earned sessions	GA4 attributed	measured
Branded search	GSC interest	estimated / measured
GEO share	AI citation visibility	counted + interval
Efficiency	Earned outcomes vs PR $ / vs paid $	mixed — always labeled
Goal pace	Progress to agreed goals	derived from snapshots

Agency-only: agreement %, queue depth, cost-to-serve, feed lag.

World-class parity

Holding companies build internal OS layers because monitoring vendors don't run the agency. You get shared books, rubric coding with a gate, and Swingset Floor — a crew you manage with clicks.

Need	Vendor default	Impact OS
Monitoring volume	Strong	Plug Meltwater — don't boil the ocean
Journalist DB	Cision/Muck Rack	Rolodex from your wins + optional sync
Quality coding	Manual / generic AI	Your rubric (Peet's/DICK'S scores) + gate
Anti-AVE value	Still leaks AVE	EIV ladder + lint ban
Lower funnel	Rare	GA4 + Ads plugs
AI visibility 2026	Vendor prompt sets	Client-owned Magic Mirror prompts
Client portal	Weak in PR tools	Front Row = same books
AI agents	Slideware / hidden cron	Swingset Floor — visible crew, Inbox, dials
Predictive	Overclaim risk	Bands + internal gates
Outcome pricing	Blocked	Audited snapshots → contracts

Leapfrog: not more clips than Cision. Operating leverage + honesty + shared books + a crew you can manage.

Meet the Crew

Conductor routes. Intern codes. Clipper enriches. Steward QA. Scribe drafts. Mirror runs GEO. Scout, Connector, Forecaster draft offense — humans send.

Agent	Does	Waits for you when…
Conductor	Routes the run, watches budget/policy	Something needs a human gate
Robot Intern	Codes coverage vs rubric	Confidence is low or Steward flags
Clipper	Enriches + spots gaps	You confirm a miss
Steward	QA before books move	Always in draft by default
Scribe	Drafts prove packages	Approve before client send
Mirror	GEO / AI citation checks	You publish Magic Mirror
Scout	Radar opportunities	Offense stays internal
Connector	Rolodex outreach drafts	You hit send
Forecaster	Crystal Ball bands	Sample size + intervals
Brief	TL;DR packs	Human voice check

Open Swingset Floor →