Over two days this week the firm researched, wrote, verified, and published thirty long-form articles on Minnesota law. Five drafting agents worked in parallel from written assignment briefs. Then independent verification agents — which hadn’t written a word of what they were checking — re-derived every citation, every quotation, and every pin cite from the primary source before anything went live.
The articles weren’t the most useful thing that run produced.
At least eight of the legal premises I handed down in those briefs were wrong. Not debatable. Not close calls. Wrong the way that publishes false law: a one-year bar described as two years, a modification standard pinned to a subdivision the legislature had repealed, a rule of decision stated exactly backwards, a statutory attorney-fee remedy that doesn’t exist. Every one got caught before publication by a subordinate who’d been told to verify the assignment instead of executing it — and who did.
So here’s my claim, plain enough to argue with: the instructions you hand down are hypotheses, not ground truth, and the system has to be built so the subordinate can prove the boss wrong. In any pipeline that touches primary law, the senior lawyer’s memory is the least reliable part of it.
Who’s “I” in that sentence? The briefs came off the top of the pipeline — from me, and from the coordinating agent that works from my direction and its own built-up familiarity with this body of law. For this essay you can’t tell the two apart, and that’s the point. Both were writing down what they were sure the law said. Neither had opened the statute.
The people who are surest haven’t read it lately
This isn’t about anybody’s competence. It’s built into the job.
The person assigning the work has the most experience with the subject and the least recent contact with its text. That’s what seniority is. You know the shape of chapter 518 because you’ve litigated inside it for years, and what you actually carry around is a compressed summary built from a hundred prior run-ins — most of them with a version of the statute that’s since been amended.
The subordinate has no summary at all. They have to go read it. So the least experienced person on the job is reliably the only one working from the current text.
Play that out and you get a specific, predictable failure: the confidence attaches to the memory, and the currency attaches to the reading, and they sit in different people. A senior lawyer will state a rule with all the fluency of fifteen years in practice and be describing a subdivision repealed in 2024. Nothing in the delivery tells you which. That’s why this failure hangs around: from the inside, it doesn’t feel like guessing.
It’s also why the AI angle is a red herring. I’ve been describing agents, but every sentence above applies just as well to a partner briefing an associate. The agents just made the failure rate measurable, because for once there was a written record of what the boss asserted and an auditable record of what the subordinate found.
The eight
Examples beat argument, so here’s the whole list: what I asserted and what the source actually says. Every item was re-checked against the primary source for this essay, not carried over from the run.
1. A “two-year moratorium” on custody modification. I described Minn. Stat. § 518.18 as having a two-year bar. It has two different clocks, and the first one is one year: paragraph (a) bars a modification motion “earlier than one year after the date of the entry of a decree,” and paragraph (b) bars a subsequent motion “within two years after disposition of the prior motion on its merits.” Mash those into one number in a family practice and you’ve made a malpractice-grade mistake. The brief also talked about the statute’s “subdivisions.” Section 518.18 doesn’t have any — it runs (a) through (f).
2. Maintenance modification under § 518A.39. I sent the drafter to chapter 518A for the spousal-maintenance modification standard. The Revisor’s page for § 518A.39 now shows, at subdivision 3, the line “MS 2022 [Repealed, 2024 c 101 art 2 s 11].” The 2024 act moved maintenance modification into § 518.552, subd. 5b, a new subdivision — the section’s history line ends “2024 c 101 art 2 s 1-8.” I was citing a subdivision that had been repealed out from under me two years earlier.
3. Promissory estoppel as a consideration substitute. I proposed the argument that promissory estoppel “substitutes for consideration, not for definiteness.” Minnesota holds the opposite. Constructors Supply Co. v. Bostrom Sheet Metal Works, Inc., 291 Minn. 113, 120, 190 N.W.2d 71 (1971): “Promissory estoppel is not a substitute for acceptance, consideration, or mutuality, but a doctrine based on reliance which courts may use in a proper case to prevent injustice.” I didn’t get a nuance slightly off. That’s the sentence saying my assigned argument is wrong, and the drafter refused to write it.
4. Part payment revives a time-barred debt. I handed down the old collection-defense chestnut — a small payment restarts the limitations clock — as the article’s main point. Minnesota abolished that for consumer debt in 2013. Minn. Stat. § 541.053: “After its expiration, the statute of limitations is not revived by the collection of a payment on an account, a discharge in a bankruptcy proceeding, or an oral or written reaffirmation of the debt.” History line: 2013 c 104 s 2. The article that ran says the reverse of the one I assigned.
5. An eleven-element fraud claim. I asked the drafter to verify “the eleven-ish fraud elements as Minnesota actually states them,” pointing at Hoyt Properties. Hoyt Props., Inc. v. Production Res. Grp., L.L.C., 736 N.W.2d 313, 318 (Minn. 2007), states five, quoting Specialized Tours, Inc. v. Hagen, 392 N.W.2d 520, 532 (Minn. 1986). The eleven-factor version is real, but it’s older and comes from a different line — the Court of Appeals collects all three formulations in TCI Business Capital, Inc. v. Five Star American Die Casting, LLC, 890 N.W.2d 423, 432 (Minn. App. 2017), which cites Davis v. Re-Trac Mfg. Corp. for the “similar eleven-factor test.” The published article reports all three instead of adopting my premise. It’s a better article for it.
6. An attorney-fee provision in the civil theft statute. I asked the drafter to “verify the punitive multiplier, who can recover, attorney-fee language” in Minn. Stat. § 604.14. There’s no attorney-fee language. The section has six subdivisions — liability, notice, parent-or-guardian liability, criminal action, recovery of property, right to demand payment — and not one of them mentions fees. The remedy is value plus “punitive damages of either $50 or up to 100 percent of its value when stolen, whichever is greater.” That missing fee provision ended up carrying real weight in the published piece, because a plaintiff who assumes fee-shifting here has mispriced the case.
7. A total-loss rule in the wrong rule chapter. I pointed at “Minn. R. ch. 2767 unfair claims settlement” for auto total-loss valuation. Chapter 2767 is titled INSURANCE PLAN ADMINISTRATORS. The auto chapter is 2770, AUTOMOBILE INSURANCE, and the standard the drafter was really after is a statute, not a rule: Minn. Stat. § 72A.201, subd. 6, “Standards for automobile insurance claims handling, settlement offers, and agreements.”
8. An eviction-expungement recodification that never happened. I flagged a “possible recodification into ch. 504B.” It never happened. Minn. Stat. § 484.014 is live, titled “HOUSING RECORDS; EXPUNGEMENT OF EVICTION INFORMATION,” with a history line running through “2024 c 118 s 1.” The drafter had to prove a negative here, and the article now says flat out that the law wasn’t moved.
Take them together and those aren’t typos. Two would have flipped an article’s central holding. Four would have sent a reader to a provision that doesn’t say what the brief claimed — and one of those doesn’t exist anymore. I stated all eight in the assignment with no hedge at all, because I believed them.
Why associates don’t correct partners
Now think about how this usually goes in a law office.
A partner tells an associate the rule. The associate reads the statute an hour later and finds something that doesn’t match. What happens next has almost nothing to do with the law and almost everything to do with economics.
Correcting upward is expensive. It costs social capital, it costs time the associate is being judged on, and there’s a real chance of being wrong in front of the person who writes the review. Deferring is free. So the associate does what the incentives say: assumes the partner knows something they haven’t read yet, writes around the discrepancy, and softens the sentence until it’s true of both versions. The brief goes out with a hedge where a holding should be, and nobody ever learns the partner’s recollection was two amendments stale.
That isn’t a character flaw in associates. Any hierarchy where raising a correction costs more than swallowing an error is built to produce exactly that. If you want the correction, you have to change the price.
And the partner never gets the update. A lawyer whose people route around his mistakes instead of reporting them gets more confident over time, because the mistakes keep not surfacing. Deference cuts the one feedback loop that would fix the memory.
Say “lead” in the brief
The first fix is the cheapest: one sentence. The 2026-08-18 brief opened with this, above everything else:
Nothing below is verified. Every statute, subdivision, case, and holding named in an assignment is a lead, not a fact. Verify against the primary source before writing it; several section numbers handed to drafters on this project have turned out not to exist.
The next day’s brief turned it up, because by then there was evidence:
…section numbers handed to drafters on this project have turned out not to exist, and three assignment theses in the last batch were wrong and had to be reversed by the drafter.
Those sentences move the burden. “Verify against the primary source before writing it” turns the assignment from an order into a research question, and it makes writing down an unverified premise — even mine — a violation of the brief.
The second sentence does more than the first. Citing the earlier failures is what makes the permission believable. Standing permission to contradict the boss is a formality until the boss writes down that he got contradicted and liked it. Three reversals last batch isn’t modesty. It’s a base rate, and a base rate tells the subordinate how many corrections are expected of them.
Permission is worthless if checking is a chore
Permission to verify means nothing if verifying is a pain. Most of the reason associates defer isn’t a lack of nerve. It’s that checking the partner’s rule properly takes forty minutes and the deadline is tonight.
So the same briefs that granted the permission handed over the tools and named the traps, in the same breath:
Verify statutes with
python3 drafts/mnstat.py <cite>(run from repo root), court rules withdrafts/mnrule.py, cases withdrafts/findcase.py/ static.case.law / MN Judicial Branch slip-opinion archive. NOT WebFetch on revisor.mn.gov.
That last prohibition is there because a summarizing fetch layer quietly truncates long statutory text and has produced wrong quotes on this project — which is why I wrote a scraper instead. With the extractor, checking whether § 604.14 has an attorney-fee provision takes about four seconds. At four seconds, nobody rationalizes. At forty minutes, everybody does.
That holds well beyond agents: verification has to be cheaper than deference, or deference wins every time. If you want associates who check you, skip the speech about intellectual courage at the retreat. Spend the money on whatever makes the check take a minute.
Make “the assignment was wrong” something people report
Here’s the part I didn’t design, and should have.
The brief told drafters to write a manifest for each article listing every authority, the proposition it supports, and the URL it was verified at. It said nothing about reporting mistakes in the assignment. So the drafters made up the channel themselves. Three separate agents, working independently, added sections to their manifests I never asked for:
- “Correction to the assignment lead — flagged for the coordinator”
- “Deliberate corrections to the assignment’s leads — flag for the gate”
- “Assignment leads that did not check out — reported to the coordinator”
That’s what it looks like when the permission is real. Handed a brief that called its own contents leads, three subordinates decided on their own that contradicting the boss was part of the job, and built a place to put it.
But the fact that they had to build the place is my design failure, and it’s the kind that quietly cuts the yield. When there’s no field for a correction, some never get written down — the drafter fixes the article, moves on, and the senior’s wrong belief survives to get handed to the next person. If the correction has nowhere to go in the output format, you’re counting on initiative to do your quality control. Every assignment brief I write from here on has a section for it, empty by default and expected to be filled.
Same goes for associates, and it’s the cheaper half of the fix. Put “assignment premises that did not check out” on the research memo template. Not as a courtesy. As a line item, like the question presented.
Never let the author of a claim check it
This last piece is structural, and it’s the one I’d never give up.
The drafters wrote manifests saying every citation had been verified. Those manifests are claims to be tested, not proof — that’s the whole reason the citation gate exists. So the verification agents got a different brief and were told, in so many words:
Assume at least one error exists in every article and go find it. An article that comes back clean on the first pass has usually not been read adversarially.
And checking runs both ways. The same run that caught eight of my errors caught this one of a drafter’s. An article quoted a Minnesota Supreme Court opinion as describing conduct amounting to “nothing other than routine accounting services.” What Witzman v. Lehrman, Lehrman & Flom, 601 N.W.2d 179, 189 (Minn. 1999), actually says is that the plaintiff failed to allege that the firm “provided anything other than routine accounting services” — a negated clause. One flipped word turned a court’s statement about a pleading failure into the court’s own description of what the defendant did. The phrase as quoted appears nowhere in the opinion.
That got caught for the same reason the gate is a separate agent: the drafter’s own manifest didn’t flag it. It couldn’t. The manifest came out of the same process that made the error, and it logged the page the material came from without re-reading the sentence. An author checking his own quotations re-reads what he meant to write. The whole value of the verifier is that it has no idea what you meant.
So here’s the rule in one line: the author of a claim is disqualified as its verifier — and that runs up the ladder, not just down. I don’t get to certify my own briefs either.
How I’d know I’m wrong about this
Two ways, and I’d want to hear about either one.
If the corrections were mostly false alarms. An over-eager checking culture breeds its own kind of error: subordinates who “correct” a senior who was right, and a pipeline that burns hours re-arguing settled points. I tested for that here by re-deriving all eight for this essay from the Revisor and from archival opinion text, and all eight held. But eight-for-eight in one run doesn’t prove much about the world. If a later run turned up ten corrections and six were the subordinate’s mistake, the design would need a different balance.
If a more careful senior just wouldn’t make these mistakes. Maybe the real lesson is that I should write better briefs instead of building a system that tolerates bad ones. I don’t buy it, and here’s a version you can test: any experienced lawyer who writes down thirty confident statements of law from memory will be wrong on something like a quarter of them. The test is free and you can run it this afternoon. Write down the ten rules you’re surest of in your own practice area — subdivision numbers, deadlines, elements, the operative sentence. Then open the statute. My bet is two or three wrong, and my bet is they’ll be the ones you’ve said out loud to a client most recently, because saying a rule often is exactly what keeps you from re-reading it.
If you keep coming back with zero, I’m wrong about why this happens, and you should write it up.
What it costs, and who it’s for
None of this is expensive. It’s a sentence in the brief calling the assignment a lead, a base rate that shows the permission is real, tooling that makes checking take seconds, a field in the output where the correction goes, and a verifier who didn’t write the thing.
What you get is a firm where mistakes get found inside, early, by someone who reports them — instead of outside, late, by opposing counsel in a responsive brief or by a client who relied on it. That’s not a technology outcome. It’s the ordinary duty to supervise, met by design instead of by hope.
And it matters most at the small end. A big firm can absorb a stale-subdivision error because there are three more lawyers between the assumption and the filing. A solo has none of that, and until very recently had no realistic way to buy it. That’s why I’m writing this in a section that gives everything away: the correction layer — what used to be a senior associate you couldn’t afford — is now a brief, a scraper, and a standing instruction. Any lawyer serving people who couldn’t otherwise afford one can have it by Friday.
The first sentence of every assignment I write now is the same. Nothing below is verified. Go find out.
Sources
- Minn. Stat. § 518.18 — paragraph (a) one-year bar on custody modification motions; paragraph (b) two-year bar on a subsequent motion after disposition on the merits; section is organized in paragraphs (a)–(f), not subdivisions
- Minn. Stat. § 518A.39 — subd. 3 shown as “MS 2022 [Repealed, 2024 c 101 art 2 s 11]”
- Minn. Stat. § 518.552, subd. 5b — “Modification”; history line ending “2024 c 101 art 2 s 1-8”
- Minn. Stat. § 541.053 — consumer-debt limitations period; revival by payment, bankruptcy discharge, or reaffirmation abolished; enacted 2013 c 104 s 2
- Minn. Stat. § 604.14 — civil liability for theft, subds. 1–6; punitive damages of “$50 or up to 100 percent of its value when stolen, whichever is greater”; no attorney-fee provision in any subdivision
- Minn. Stat. § 72A.201, subd. 6 — “Standards for automobile insurance claims handling, settlement offers, and agreements”
- Minn. Stat. § 484.014 — “HOUSING RECORDS; EXPUNGEMENT OF EVICTION INFORMATION,” history through 2024 c 118 s 1
- Minn. R. ch. 2767 — “CHAPTER 2767, INSURANCE PLAN ADMINISTRATORS”; Minn. R. ch. 2770 — “CHAPTER 2770, AUTOMOBILE INSURANCE”
- Constructors Supply Co. v. Bostrom Sheet Metal Works, Inc., 291 Minn. 113, 120, 190 N.W.2d 71 (1971) (No. 42562) — quoted sentence read at star page 120 of the Caselaw Access Project archive, static.case.law/minn/291/html/0113-01.html
- Hoyt Props., Inc. v. Production Res. Grp., L.L.C., 736 N.W.2d 313, 318 (Minn. 2007) (No. A05-1293) — five-element fraudulent-misrepresentation statement quoting Specialized Tours, Inc. v. Hagen, 392 N.W.2d 520, 532 (Minn. 1986); read at static.case.law/nw2d/736/html/0313-01.html
- TCI Business Capital, Inc. v. Five Star American Die Casting, LLC, 890 N.W.2d 423, 432 (Minn. App. 2017) (No. A16-0741) — collecting the Hoyt five-element, Martens seven-factor, and Davis v. Re-Trac Mfg. Corp. eleven-factor formulations; read at static.case.law/nw2d/890/html/0423-01.html
- Witzman v. Lehrman, Lehrman & Flom, 601 N.W.2d 179, 189 (Minn. 1999) (No. C6-98-555) — “provided anything other than routine accounting services”; the phrase “nothing other than routine” appears nowhere in the opinion; read at static.case.law/nw2d/601/html/0179-01.html
- Reporter citations above are taken from the Caselaw Access Project’s structured case metadata rather than from opinion body text. The Caselaw Access Project has no citator; nothing here should be treated as a subsequent-treatment check.
- The assignment briefs, per-article manifests, and independent gate reports quoted in this article are this firm’s own working files from the 2026-08-18 and 2026-08-19 publishing runs, maintained in the site repository. Thirty articles carry those two publication dates.
Commentary on practice management and supervision — the opinions and the predictions are the author’s. Not legal advice, not ethics advice, and not a statement of the law for any reader’s situation: the statutes and cases above are cited only as examples of a delegation failure and were current as of the date of this article. No client information appears in this piece; every example comes from the firm’s own published work on its own website. Everything in this section is free, and the only ask is that you use it to serve someone who could not otherwise afford a lawyer. Questions about anything here: Send us a message or 612-470-6529.