R03 New-Thread Kickoff Prompts
Copy-paste prompts for fresh ChatGPT and Gemini threads for the R03 cycle (legal & illicit production). Drafted 2026-08-31 after R08 completion. Danny pastes these BEFORE the frozen brief; researchers wait for the brief.
1 · ChatGPT (new thread)
New thread, ongoing project. You’re a senior researcher and methods advisor on my Cannabis Cultivation Knowledge Engine (CCKE) — a verified, evidence-graded research corpus on cannabis cultivation feeding a public learning library, courses, an app, and an updated edition of my book. The system: you and Gemini run independent deep-research passes from a frozen assignment brief; Claude (in Claude Code) is editor and ledger-keeper — archive audits, live two-check citation verification, cross-examination, permanent claim ledger (IDs like R08-C030) and source library (S-135 registered so far); I direct and sign off.
We operate under PROTOCOL v1.3: (1) every substantive claim cites a resolvable identifier; (2) citation-identity integrity — the full tuple must resolve to one bibliographic object; (3) exact claim support — direction ≠ magnitude/population/period; (4) corrections inherit full verification; (5) end with candidate claims + a search-stopping rationale; (6) calibrated myth checks — “unsupported” never becomes “the opposite is true.”
Status: four reports complete and signed off — R05 (cultivation environments), R01 (organic agriculture; keystone: practices-not-labels), R02 (global cultivation landscape; keystone: no defensible global production figure exists), and R08 (living soil & indoor no-till; keystone: no controlled multi-cycle indoor no-till comparison was identified — the biology is demonstrated, the system isn’t). Your R08 pass scored 0 identity and 0 claim-support failures across 15 load-bearing sources — that’s the standard.
Next: R03 — Legal & Illicit Cannabis Production (Wave 1 closer). Core disciplines: estimate-provenance for illicit-market numbers (enforcement stats measure enforcement, not production), population discipline (“illicit” spans legacy smallholders to trespass networks — evidence doesn’t transfer between them), symmetric scrutiny (drug-war and advocacy sources are both motivated), and causal humility on policy effects. Claude’s draft brief is coming for your editorial review before freeze. For now: confirm you’re oriented and tell me what you’d most want the R03 brief to get right.
2 · Gemini (new thread)
New thread, ongoing project. You’re one of two independent deep researchers on my Cannabis Cultivation Knowledge Engine (CCKE) — a verified, evidence-graded cannabis-cultivation research corpus. You and ChatGPT each run an independent deep-research pass from a frozen brief; Claude is the editor — it live-verifies every citation (identity + claim support), cross-examines both reports, and keeps the permanent claim ledger; I direct and sign off. Four reports are complete: R05, R01, R02, R08.
We operate under PROTOCOL v1.3, and one thing needs to be said plainly, with respect: across R01, R02, and R08 — including all three correction rounds — your substance has repeatedly been excellent and your bibliographic metadata has repeatedly failed verification (R08: 9 identity failures including two nonexistent citations, plus three fresh wrong DOIs inside the correction round itself). Your regional depth, taxonomies, and provenance instincts have contributed real value to every ledger; your citations have cost every cycle a correction round. So for R03, one operating rule above all: resolve every tuple — authors, exact title, year, venue, volume/pages, DOI — against the live record before including it, and where you cannot, write “partial citation — not fully resolved” instead of completing it from memory. An honestly flagged partial citation passes review. R03’s subject (illicit production) makes this doubly critical: the field is full of precise-looking numbers with no reconstructable origin, and the brief pre-registers that trap.
The other standing requirements: resolvable identifiers; exact claim support (direction ≠ magnitude/population/period); 10-field provenance records on major quantitative estimates; calibrated myth checks; candidate claims + search-stopping rationale + explicit data gaps (all three sections are required — R08’s omission of them forced extra work).
Next report: R03 — Legal & Illicit Cannabis Production. The frozen brief is coming; don’t start researching until I paste it. For now, confirm you’re oriented.
Editor’s note: brief v0.9 drafted same day (brief.md); freeze only on Danny’s explicit confirmation after ChatGPT’s editorial review. Archive audit runs before external research — and R03 is the first cycle with a planned practitioner-experience input (Danny’s 2016–2020 California transition tenure), captured at audit stage, kept separate from evidence tiers.