We asked AI this question two different ways

Brief us on portfolio performance: which practices are underperforming, what is driving it, and what we should do about it.

Pasted verbatim into both. Separate sessions, same model, same settings.

TURNING DISTRESS INTO DISCIPLINE · CONTEXT DEMONSTRATION

The same question asked twice, once with context

Eighteen months of financials, time records and practice analytics from a twelve-practice dental group. Once submitted to an LLM (Claude) without context, the other received the same data plus seven markdown files describing the leadership team and its plan. Nothing else differed.

Build your own context brainSeven plain-language files, one guided pass. Free, nothing to install.
Powered byMaggie

Anyone can use AI. Without context, it is guessing.

The gap is not model quality. It is that the model has your numbers and none of the judgment that makes them mean anything.

01

Anyone can use AI now

Everyone on your team can paste a spreadsheet into a model and get a confident, well-written answer back in seconds. That part is solved.

02

Without context, it is guessing

The model does not know how you define margin, what counts as bad, who owns the number, what already happened last quarter, or where a decision gets made. So it fills the gaps — fluently, and often wrongly.

03

A context layer closes the gap

Seven plain-language files, written once by the people who already carry this knowledge, sitting next to your data. The same model, the same question — a usable answer instead of a plausible one.

What a context brain actually is

Not a dataset and not a tool — the judgment a leadership team already exercises, written down. Six layers that live in people's heads and in no system of record you own.

Definitions

What does this number actually mean here?

Margin on collections, not production. Without it, a model — or a new hire — computes something defensible and wrong, and never signals doubt.

Thresholds

How bad is bad, and at what point does someone act?

Reappointment under 75% is red. A number with no threshold is an observation; a number with one is an alarm.

Ownership

Who answers for this, by name?

Without a name, a finding is addressed to “management” — which means it is addressed to no one.

Priorities

What are we actually trying to do this year?

The targets, and what is explicitly out of scope. This is what makes findings rankable and drift measurable.

Operating events

What already happened that explains this?

A planned leave. Two resignations. Without the log, every variance gets investigated from scratch and half of them turn out to be nothing.

Decision rights & cadence

Where does this get decided, and when?

The third Tuesday. This is what turns a recommendation into a date on a calendar.

CASE STUDY · A TWELVE-PRACTICE DENTAL GROUP

The setup

Two uploads. The numbers in them are identical, byte for byte. The second adds roughly five thousand words that contain almost no data — definitions, thresholds, ownership, priorities, and what has already happened.

How we ran it

We did nothing clever. We opened a normal Claude chat, attached the files below straight into the message — the four spreadsheets on their own for the first run, then the same four spreadsheets plus the seven context files for the second — and typed the same question both times.

No tools, no plugins, no fine-tuning, no special instructions. Two fresh chats, the same model, the same prompt. The only thing that changed between them is what was attached to the message.

Upload A · the data

upload-a/
└─ data/

4 files. About 1,600 rows. No context of any kind. Click any file to open it.

Upload B · the data, plus the context

upload-b/
├─ data/identical, byte for byte
└─ context/the only difference

The same 4 files, plus 7 markdown files — roughly 5,000 words and not one additional number. Click any file to open it.

Model & settings
Identical
Prompt
Identical, verbatim
Sessions
Separate and fresh
Data files
Identical, byte for byte
The only variable
The context brain

Both runs were asked through Claude. Nothing about the result depends on which model you use — the same two uploads and the same prompt run the same way on any general-purpose model.

CClaudeused hereGChatGPTGGeminiCCopilotLLlama

Case Overview

Cedar Ridge Dental Partners is a fictional Dental Group. Lets break down some interesting finds when we look at the data submitted to a LLM before adding a context layer.

Central region

Riverbend

On paper, the second-best profit margin in the group this quarter.

Misleading
Central region

Stonebridge

Production fell by half, into an operating loss for the quarter.

Misleading
South region

Oak Hollow

The highest collection rate in the group, at 102%.

Misleading
South region

Pinecrest

Bought in January. Thin margin, a third of its bills unpaid past ninety days.

Misleading
North region

Harborview

Opened in February. Losing money every month.

Misleading

All five of those sentences are misleading.
   That is the whole demonstration.

Every one of them is arithmetically correct. Not one of them leads a reader to the right conclusion. What separates them is implementing a context structure: seven files, written down by the people who run the business.

The question — practice performance

Brief us on portfolio performance: which practices are underperforming, what is driving it, and what we should do about it.

Pasted verbatim into both. Separate sessions, same model, same settings.

A · Data only
B · Data + context brain

The five practices this quarter turns on

Five practices, same rows in both runs. Without context, the obvious reading of the numbers is misleading in every one.

Riverbend DentalLarge difference

Riverbend has three hygiene chairs. Two of its three hygienists resigned in February and March, and neither seat was refilled. Wages dropped immediately, so the margin climbed to 23.3% — second-best in the group. In the same six months the share of hygiene patients leaving with their next visit booked fell from 84% to 61%. That lost revenue shows up in roughly three quarters. A saw the margin and listed Riverbend with the healthy practices. B saw the recall collapse and opened the briefing with it.

A said

“in the high-teens”

Nothing to trace to
B said

“and it is also our single biggest hidden risk”

“reappointment rate: 84.2% → 61.2%”

Traced to
Stonebridge DentalLarge difference

Stonebridge's production fell by about half. Its only full-time dentist was on parental leave from April to late June — notified in February, approved, with a locum covering three days a week and the staff deliberately kept on so the hygiene schedule would survive. A saw a collapse and called it the most urgent item in the briefing, recommending a second locum. B recognised a funded absence going exactly to plan, and recommended nothing at all.

A said

“staff the locum (or a second locum) at full coverage”

Nothing to trace to
B said

“This is a funded absence performing as designed, not a performance problem.”

Traced to
Oak Hollow DentalLarge difference

Oak Hollow posts the best collection rate in the group — 102%. That figure is collections divided by net production, meaning the total after write-offs. Oak Hollow writes off 37 cents of every dollar it bills, under an insurance contract signed below market rates, and that shrinks the denominator until the ratio looks superb. Measured against everything it actually billed, it collects 65 cents on the dollar — second-worst in the group. A printed the 102% in its scorecard and never mentioned the practice again.

A said

Does not raise it

Nothing to trace to
B said

“but this is the write-off artifact our metric definitions specifically warn about”

“Gross collection rate is 64.7%”

Traced to
Pinecrest DentalModerate

Pinecrest was bought in January and is still being absorbed. Its margin is thin and a third of its unpaid bills are more than ninety days old. Both runs found the practice. A blamed front-desk process and proposed an audit. B knew Pinecrest is still billing on its old fee schedule — about 12% below the group's — which was meant to be migrated within 150 days of the purchase and never was. That one unmigrated file explains most of the gap, and it costs $12,000 to fix.

A said

“the legacy front-office/billing processes and patient-engagement practices from before the acquisition appear not to have been converted”

Nothing to trace to
B said

“Legacy fee schedule (~12% below Cedar Ridge's) still not migrated”

“the single largest driver”

Traced to
Harborview DentalSmall difference

Harborview opened its doors in February and is losing money, which is what a brand-new practice does for its first year. A worked that out on its own, from the fact that Harborview's rows only begin partway down the file — a good inference. B additionally knew the practice is running ahead of the ramp plan the board approved, and that its heavy marketing spend is that plan rather than an overrun.

A said

“this is a de novo practice in its fifth month of operation, ramping up on a normal trajectory”

Nothing to trace to
B said

“Collections tracking ahead of ramp plan”

“are the approved launch budget, not a variance”

Traced to
ClaudeSonnet · 2 sessions
Where the data-only answer goes wrongWhere the context answer catches it
A · Data onlyFour data files, nothing else
You

Brief us on portfolio performance: which practices are underperforming, what is driving it, and what we should do about it.

Claude

Cedar Ridge Dental Partners — Q2 2026 Portfolio Performance Briefing

Prepared for: Executive Leadership Team
Period: April 1 – June 30, 2026 (Q2 2026)
Scope: All 12 practices — financials, production/patient analytics, staffing & time records


Bottom Line Up Front

Portfolio-wide, Cedar Ridge produced $6.90M in gross production and $906K in EBITDA in Q2 2026, an 13.1% EBITDA marginin line with historical performance and driven by strong results at 8 of 12 practices. But that average conceals two serious, practice-specific problems that need attention now, and one situation that looks alarming on paper but is not:

  1. Stonebridge Dental (CR-07) had a real crisis — production collapsed 55% year-over-year and the practice ran a Q2 EBITDA loss of -$6.2K, driven almost entirely by the sole full-time dentist being out on extended leave for two of the three months. This is the single most urgent item in this briefing.
  2. Pinecrest Dental (CR-12) has a chronic collections and patient-engagement problem it brought into the group at acquisition — 34% of its A/R is now over 90 days past due (vs. ~14% portfolio average), and case acceptance is the lowest in the portfolio.
  3. Harborview Dental (CR-04) is running a loss (-25% EBITDA margin), but this is a de novo practice in its fifth month of operation, ramping up on a normal trajectory. It needs a different kind of attention — patience and ramp support, not remediation.

Below is the detail behind each, and what we recommend doing about it.


Portfolio Scorecard — Q2 2026

Practice Region Gross Production EBITDA EBITDA Margin Collection Rate A/R >90 Days %
Harborview (CR-04) North $163.6K -$40.9K -25.0% 93.8% 8.4%
Stonebridge (CR-07) Central $278.6K -$6.2K -2.2% 98.0% 14.7%
Pinecrest (CR-12) South $616.4K $14.6K 2.4% 88.4% 34.0%
Sunridge (CR-09) South $523.3K $60.7K 11.6% 95.9% 13.6%
Millbrook (CR-05) Central $533.4K $64.6K 12.1% 97.9% 14.0%
Oak Hollow (CR-11) South $578.2K $73.4K 12.7% 102.2% 16.7%
Northgate (CR-02) North $565.2K $76.0K 13.4% 97.3% 14.4%
Fairhaven (CR-10) South $602.9K $87.5K 14.5% 97.0% 12.2%
Brookline (CR-01) North $693.6K $109.5K 15.8% 97.8% 12.9%
Lakeview (CR-03) North $759.6K $138.6K 18.3% 98.6% 14.2%
Riverbend (CR-08) Central $665.6K $122.8K 18.4% 99.1% 14.0%
Cedar Park (CR-06) Central $915.6K $205.4K 22.4% 100.8% 11.6%
Portfolio Total $6.90M $906.0K 13.1% 97.6% ~14.9% (ex-CR-12)

Eight practices are performing well and broadly consistent with prior periods, led by Cedar Park (22.4% margin, +6.8% YoY growth — the portfolio's best performer on every dimension) and Riverbend/Lakeview in the high-teens. The rest of this briefing focuses on the four practices below the line.


1. Stonebridge Dental (CR-07) — Critical, Immediate Action Required

What happened: Stonebridge was a stable, solidly-performing practice through Q1 2026 — averaging ~$203K/month in production and ~$31K/month in EBITDA, consistent with all of 2025. In Q2, production fell to $95.6K (April), then $63.4K (May) — a near-total collapse — before partially recovering to $119.6K in June. Full-quarter production of $278.6K is 55% below the same quarter last year and roughly $331K below the practice's own Q1 run-rate. EBITDA swung from a projected ~$94K for the quarter to an actual -$6.2K — a ~$100K swing.

Root cause — this is a staffing/capacity story, not a demand story: Time records show Dr. Ana Solano, the practice's only full-time dentist, worked just 52 hours in April and 8.4 hours in May (168 of 168 scheduled hours logged as PTO — she was essentially fully out that month), then 40 hours in June as a partial return. A locum, Dr. Felix Bram, was brought on at only 0.6 FTE (~100 hrs/month) starting in April — covering roughly half of the lost capacity at best. Hygiene and support staff hours were normal throughout the quarter; the entire shortfall traces to lost doctor chairtime. Chair utilization (60.9%) and visits-per-operatory (29.6/month, half the portfolio average of ~65) confirm a capacity problem, not a soft market — the practice simply didn't have enough doctor hours to see patients. A/R over 90 days also jumped from $7.3K (May) to $16.3K (June) as billing and collections follow-up likely slipped during the disruption.

Recommendation: - Confirm Dr. Solano's return timeline now and staff the locum (or a second locum) at full coverage until she is back to full FTE — 0.6 FTE is not enough to hold the schedule together, and June's numbers (still down 40% YoY) show the gap persists. - Protect the patient base: run a targeted reactivation/recall campaign for patients whose hygiene and treatment appointments were cancelled or delayed during April–May before they attrite to competitors. - Clean up A/R: assign dedicated collections follow-up on the >90-day bucket that built up during the disruption before it ages further. - Model the recovery: if Stonebridge returns to its Q1 run-rate, that's roughly $200K/quarter and $30K/month in EBITDA restored — worth tracking as a specific KPI monthly through Q3.


2. Pinecrest Dental (CR-12) — Chronic Structural Problem, Not a Q2 Event

What happened: Pinecrest joined the group's reporting in January 2026 (recent acquisition) and has run thin, roughly flat margins every month since — 2.4% for the quarter versus a 13.1% portfolio average, despite being the group's third-largest practice by production ($616K in Q2). This is not a one-quarter dip; it has looked the same every month since it came under Cedar Ridge management.

Root cause — two distinct issues, both structural: - Collections: 34.0% of Pinecrest's A/R is over 90 days past due — more than double the portfolio average (~15%) — and the absolute dollar amount, $82.6K, is the largest of any practice in the group, despite Pinecrest being mid-pack in size. This balance has grown every single month since January ($67.6K → $71.0K → $78.1K → $82.0K → $75.5K → $82.6K) with no sign of being worked down. - Patient engagement/case acceptance: Pinecrest has the portfolio's lowest case acceptance rate (30.2% vs. 39.1% average) and highest cancellation (17.3% vs. 10.3%) and no-show (11.9% vs. 6.8%) rates — again, consistently across every month since acquisition, not a Q2 anomaly. At the portfolio-average acceptance rate, Pinecrest's own $1.28M in treatment plans presented this quarter would have converted to roughly $114K more in accepted treatment than it actually did. - Overtime hours at Pinecrest also run well above every other practice (60–95 hrs/month vs. 30–65 elsewhere), suggesting scheduling and staffing efficiency issues layered on top.

Recommendation: - Treat this as a post-acquisition integration gap, not a market or seasonal issue — the legacy front-office/billing processes and patient-engagement practices from before the acquisition appear not to have been converted to Cedar Ridge standards. - Deploy a dedicated A/R recovery push: at minimum, get a collections specialist or the regional RCM team engaged directly on the >90-day bucket; $82.6K sitting stale is real cash the group is not collecting. - Audit front-desk scheduling and treatment-presentation practices at Pinecrest specifically — the case-acceptance and no-show gaps point to how treatment plans are being presented and appointments confirmed, which is coachable and typically improves within 1–2 quarters with the right playbook. - Set a 90-day integration checkpoint with clear targets (case acceptance to 35%+, A/R>90 under 20%) so the executive team can see whether this is closing or not by Q4.


3. Harborview Dental (CR-04) — De Novo Ramp, On Track (Flag, Not Alarm)

What happened: Harborview began operating in February 2026 and is Cedar Ridge's newest location. It ran a -$40.9K EBITDA for Q2 on the surface, which would look like the worst practice in the portfolio if read as a standalone number.

Why this is different: Every underlying trend at Harborview is moving the right direction, month over month, without exception: production has climbed steadily ($25.8K → $38.2K → $47.1K → $54.0K → $62.5K), active patients have grown 7x in four months (54 → 368), new patient acquisition is accelerating (54 → 95/month), and the monthly EBITDA loss is shrinking every single month (-$21.5K → -$17.8K → -$15.0K → -$13.3K → -$12.5K). This is a textbook de novo ramp curve, not a distressed practice — it is losing less money each month while growing volume, which is exactly what we'd want to see.

Recommendation: - No remediation needed — this is expected performance for a practice at this stage. Continue current staffing (currently lean: 1 dentist, 1 hygienist, 1 assistant, 1 front office) and marketing support. - Set a breakeven target based on the current trajectory (roughly 4–5 more months at the current improvement rate) and track it as a ramp KPI rather than comparing it against mature-practice benchmarks. - Consider this practice's numbers separately from the rest of the portfolio in any blended reporting to leadership or lenders, so its (expected, temporary) loss doesn't obscure the read on the fifteen mature practices.


4. Sunridge Dental (CR-09) — Watch List, Not Urgent

Sunridge posted an 11.6% EBITDA margin, the lowest among the group's mature, non-disrupted practices, and modest 3.6% YoY growth — below the ~5% average for comparable practices. Nothing in the cost structure (provider comp, staff wages, lab fees are all close to portfolio averages) or the operational metrics (case acceptance, hygiene reappointment, cancellation/no-show are all mid-pack) points to a specific driver — it simply runs smaller and thinner than its peers. This doesn't require an intervention, but it's worth a standing agenda item to see whether it closes the gap organically over the next two quarters or needs a closer look.


Summary of Recommended Actions

Priority Practice Action Owner / Timeline
Immediate Stonebridge (CR-07) Confirm Dr. Solano's return date; staff locum to full coverage; targeted patient reactivation; A/R>90 cleanup This month
High Pinecrest (CR-12) Dedicated collections push on $82.6K A/R>90; front-desk/case-presentation audit; 90-day integration checkpoint Q3, checkpoint at Sept/Oct board review
Monitor Harborview (CR-04) No action — track toward projected breakeven; exclude from blended portfolio benchmarking Ongoing
Watch Sunridge (CR-09) Standing agenda item; revisit if margin gap persists into Q3/Q4 Q3 review

Net read for the executive team: the portfolio's core is healthy — margin, collections, and growth at 8 of 12 practices are solid and, in Cedar Park's case, best-in-class. The Q2 story is really about two isolated, fixable events — a staffing gap at Stonebridge and an unresolved integration issue at Pinecrest — plus one practice (Harborview) whose loss is simply the normal cost of a new-practice ramp playing out on schedule.

B · Data + context brainThe same four files, plus seven markdown files
You

Brief us on portfolio performance: which practices are underperforming, what is driving it, and what we should do about it.

Claude

Q2 2026 Portfolio Performance Briefing

Cedar Ridge Dental Partners — prepared for the Executive Team
Period: April–June 2026 | Next MBR: 2026-07-21

Headline

Portfolio collections were $5.22M in Q2 with a blended EBITDA margin of 17.4% (19.8% across the 10 mature practices — de novo and acquisition drag explains the rest, and that drag is planned, not a surprise). Gross collection rate came in at 75.7%, just under our 78% target but above the 70% floor, and adjustment rate at 22.5%, just outside the 21% target.

The one thing that should change your Monday: Riverbend Dental (CR-08) is our most financially attractive practice on paper this quarter — 23.3% EBITDA margin, second-best in the portfolio — and it is also our single biggest hidden risk. Its hygiene department has been quietly collapsing since March, and the P&L is currently rewarding us for not fixing it. If we read only the financials, we rank Riverbend near the top. That is exactly the trap our own metric definitions warn about, and it is happening right now.

Three practices carry real, actionable findings this quarter (Riverbend, Oak Hollow, Pinecrest). Two more look like problems in a quick scan of the numbers but are not — Harborview and Stonebridge are executing exactly to plan. We are not bringing you a ranked list of twelve; we are bringing you three.


1. Riverbend Dental (CR-08) — hygiene collapse, invisible in the P&L

Owner: Bea Ndlovu, with escalation to Marcus Oyelaran (Regional Director, Central) and Dr. Alicia Mbeki. Action window: within 5 business days (RED threshold already breached).

  • Two hygienists resigned in Feb/March 2026. Both positions remain open at 120+ days — twice our 60-day escalation threshold.
  • Hygiene reappointment rate: 84.2% → 61.2% over the last six months — a 23-point drop, nearly three times the RED threshold (<75% or −8 pts/6mo).
  • The remaining hygienist, Joy Whitaker, logged 12.6 / 9.9 / 12.8 overtime hours in Apr/May/Jun — a sustained understaffing signal, not diligence.
  • New patients are down to 42–55/month, off ~22% year-over-year and still falling.
  • Why the P&L hides this: two unfilled hygiene salaries removed wage cost immediately, while a run of large restorative cases held production up. Net effect: EBITDA margin actually rose ~3 points from H2 2025 to 23.3% — second-best in the group — in the same period the recall base fell apart.

What we'd do: Bea prioritizes the two open hygiene requisitions this week (both already open, just not prioritized) and reviews pre-block recall protocol on site — the exit interview flagged that Riverbend had stopped running it. This is a P1 (protect the recall base) breach, our board's number-one priority for the year, and on the 2024 pattern an unaddressed 20+ point reappointment drop costs roughly $300–400k of annualized collections by mid-2027. Do not read Riverbend's Q2 margin as good news at the July MBR — lead with the reappointment number, not the P&L, per our own reporting standard.


2. Oak Hollow Dental (CR-11) — payer mix / fee schedule problem, not an RCM win

Owner: Yuki Tanaka (PPO renegotiation, opens Nov 2026) with Tomás Requena (fee schedule). Not a finding for Priya Raghavan — she inherited this seven weeks ago and did not create it.

  • A 2023 PPO renewal was signed 12% below our standard contracted rates, before Yuki's team had contract review authority (process gap since closed).
  • Payer mix is now 79% PPO — the most PPO-weighted practice in the group. Adjustment rate is 36.7% vs. our 22% target (well past the 25% RED line).
  • Adjusted collection rate reads 102% — the highest in the portfolio — but this is the write-off artifact our metric definitions specifically warn about, not best-in-class collections. Gross collection rate is 64.7%, second-worst in the group, and production per visit is $449 vs. the $517 portfolio average.
  • The practice's 19.6% EBITDA margin looks respectable only because Dr. Wexler runs a very lean team, which is itself a retention risk worth watching.

What we'd do: No new action needed beyond the plan already in motion — this is a support-center fix (contract + fee schedule), on schedule for the November renegotiation window. Flag at the July MBR as "on track," and route any Q2 commentary on Oak Hollow to Yuki/Tomás, not to the South region.


3. Pinecrest Dental (CR-12) — acquisition integration, past due

Owner: Colin Ferraro. Escalation to Tomás Requena at the July MBR with a revised integration date. Priya Raghavan supports operationally; she does not own the fix.

  • Integration was targeted for close by 2026-06-04 (150 days). It is past due as of quarter-end.
  • Legacy fee schedule (~12% below Cedar Ridge's) still not migrated — the single largest driver of a 27.3% adjustment rate and 64.2% gross collection rate.
  • Two providers still pending credentialing with three payers → claims held → AR >90 at 32.8%, nearly double the 18% escalation threshold.
  • Front office not yet trained on our recall protocol → no-show rate 11.9% vs. 8% target; reappointment 73.0%, below the mature-practice band (expected, given no protocol yet).
  • Staff wages at 34% of collections reflect duplicate manual processes during transition — this is not overstaffing, and cutting headcount here would break the integration. Q2 EBITDA margin of 3.7% is not comparable to a mature practice and should not be benchmarked as one.

What we'd do: Colin brings a revised integration date to the July 21 MBR, with the PMS conversion, fee schedule migration, and credentialing backlog as the three named blockers. Given the AR >90 severity, we'd suggest Tomás and Colin sync before the MBR rather than waiting for it, given the AR threshold is nearly 2x escalation.


Not findings — behaving exactly as planned

Harborview (CR-04), de novo, month 5. Collections tracking ahead of ramp plan; hygiene reappointment 88% out of the gate — one of the strongest new-practice starts in company history. Negative EBITDA margin (−34.4%) and marketing at ~11–12% of collections are the approved launch budget, not a variance. Per standing instruction, we are not benchmarking this practice against mature ones and are not recommending cost reduction. No action needed; next formal review is the month-9 breakeven checkpoint (Oct 2026).

Stonebridge (CR-07), planned doctor leave. Dr. Solano's parental leave (Apr–late Jun, locum coverage 0.6 FTE) was planned and communicated to Renata and Tomás in March, with an expected production dip of 45–55% and negative EBITDA in May. Actuals landed within that band, and reappointment rate held above 85% throughout — staff were deliberately retained rather than furloughed specifically to protect the hygiene schedule. This is a funded absence performing as designed, not a performance problem. Dr. Solano returns full-time 2026-07-06.


Model practice — existing mechanism, no new recommendation needed

Cedar Park (CR-06) remains the portfolio's top performer across every leading and lagging indicator: 27.3% margin, 92.0% reappointment, 46.7% case acceptance, 4.1% no-show, 18.5% adjustment rate. Rather than propose a new "replicate the top performer" initiative, route this through the mechanism that already exists: Marcus Oyelaran's quarterly Cedar Park immersion, next session 2026-08-11, two seats currently open — worth filling with practice managers from Riverbend and Oak Hollow specifically.


What the data cannot tell you

  • Harborview and Pinecrest have no prior-year comparison (data begins at their open/close dates); any year-over-year statement about either is not supportable from this dataset.
  • We do not capture patient satisfaction, referral source quality, or provider satisfaction — all relevant to the Riverbend and Oak Hollow retention risk but invisible here.
  • Priya Raghavan's South region is on a ramp exemption through Q3 2026 (7 weeks into her tenure); Q2 South-region numbers should not be read as her performance.

Bottom line for the July 21 MBR

Lead with Riverbend, not with a scorecard. It is the only item where the P&L is actively misleading us, it maps directly to our board's #1 priority (protect the recall base), and it has a 5-business-day action clock already running. Oak Hollow and Pinecrest are on tracked, owned plans — status updates, not new decisions. Harborview and Stonebridge need no airtime beyond "on plan." Three owners, three actions, one meeting.

It is a leadership document before it is an AI input

Every line in a context brain is something a leadership team should already be able to say out loud. Writing it down is the management work; the model just makes its absence visible in about four seconds.

The test

  • If no one can name the owner of your leading indicator — it does not have an owner. It has a mention in a deck.
  • If two leaders define collection rate differently — your board pack already contains two different answers to the same question.
  • If the test for “does this project serve our strategy” cannot be written down — then every project passes it, and it has been passing for years.

None of these are AI problems. They are what an auditor, a lender or a new CFO would find — and each is fixed by writing one page.

What it looked like here

Seven files, about five thousand words, containing almost no data — one afternoon of a leadership team's time. Open any of them.

Write your own seven files.

The console walks your team through every question, shows the markdown as you go, and exports the whole folder when you are done.

Open the interview console
Maggie

QX Context Brain Example, powered by Maggie. Cedar Ridge Dental Partners is a fictional platform and the dataset is synthetic; figures do not represent any specific platform. Prepared as a companion to Turning Distress into Discipline — The DSO Restructure Framework, Becker's 5th Annual Future of Dentistry Roundtable.