Three research agents read the week. One report agent turns sensor data into a vet-readable verdict.
The crew runs inside WaterDoctor's backend on a weekly cadence. Three agents — research, fact-check, editor — sweep ten aquaculture journals, regional market feeds and government policy announcements; verify every item; and assemble a curated bilingual EN ⇌ 简体中文 brief. A second pipeline reads each pond's sensor stream — pH, DO, temperature, ORP, ammonia, nitrite, nitrate, turbidity, algae — folds in the week's research and the next seven days of weather, and produces a PDF the farm manager, the vet and the environmental regulator can all read off.
We built this for WaterDoctor. The same shape — a research desk that learns the customer's domain plus a report agent that turns operational data into auditable, regulator-readable output — is the thing we actually ship. The WD Crew is one of six sample crews on this site; the others sit one click away.
Two pipelines, one weekly cadence, one human reviewer.
Three agents — research, fact-check, editor — produce a curated week-in-review of journals, regional market news and policy alerts. Bilingual. Per-item verified / unverified / flagged. Reviewer overrides on the record.
Per pond, per week. Sensor stream → core judgment, diagnoses, disease checklist, aeration strategy, feeding schedule, FCR analysis, cost breakdown. Folded in: that week's research bundle and the next 7 days of weather.
Every fact-check verdict is overrideable. Every weekly report passes a reviewer before it leaves the system. The crew does the legwork; an operator owns the publish.
Research → fact-check → editor. Nothing reaches the report writer un-verified.
- research.agentFour parallel grounded searches
Two paper sweeps across ten aquaculture journals — Aquaculture, Fish & Shellfish Immunology, Aquaculture Reports, Reviews in Aquaculture, Frontiers in Marine Science, Journal of Fish Diseases, Aquacultural Engineering, Marine Biotechnology, Nature Communications, Water Research. Plus region-tuned market and policy sweeps for CN or SEA. Every paper carries a real DOI; every news item carries the publisher's exact date and URL — copied from the search grounding, not reconstructed.
- factcheck.agentVerify, corroborate, gate
Each item gets a verdict — verified, unverified, flagged. For corroboration, an independent grounded search runs per item and every candidate URL is HTTP-checked for liveness; we keep up to six live URLs per item. If more than 70% of items come back flagged on the first attempt, the batch retries once before the verdict is persisted — bad search calls don't get to set the truth.
- editor.agentBilingual cleanup
Tidies titles, harmonises EN ⇌ 简体中文 across every field, never invents new metadata. Flagged items pass through untouched so the reviewer sees exactly what fact-check saw.
- reviewer (human)Overrides on the record
Per-item Override and review notes attach to the run record. The bundle the report writer reads is the bundle the human signed off — there's no parallel version of the truth.
Sensor stream + research bundle + weather → one bilingual PDF.
Each Monday, for each pond, the report writer pulls seven days of sensor readings — pH, dissolved oxygen, temperature, ORP, ammonia, nitrite, nitrate, turbidity, algae — alongside the next seven days of weather for outdoor ponds and the week's region-tuned research bundle. Out comes a numbered report: overview, water quality (core judgment plus per-parameter sparkline and range), disease screening, weather risk and advice, aeration strategy, disease checklist, feeding schedule, FCR analysis, energy comparison, cost breakdown. Every section is rendered EN and 简体中文 side by side. Every diagnosis ties phenomenon to cause to remedy to a HIGH/MEDIUM/LOW risk level a vet can defend.
- No invented citations. The research agent's URLs are constrained to ones the search grounding actually returned; reconstructed-from-memory DOIs are dropped before fact-check ever sees them.
- No date-massaging. A paper outside the search window keeps its real date. The report records reality, not a tidy fiction that fits the week.
- No silent flags. Flagged items survive the editor untouched and surface in the reviewer panel. The human sees exactly what the agent saw.
- No publish without a human. Every weekly report passes a reviewer before EN/ZH PDFs go out. There is no auto-publish path.
- No single-agent demo. A "do-everything" agent is unevalable. Five narrow agents with one job each is what's running in production.
Swap aquaculture journals for clinical guidelines, sensor streams for telemetry, ponds for sites — the shape holds. A research desk that learns your domain on a weekly cadence; a report agent that turns your operational data into something your customer or your regulator can actually read; a human gate that signs every output. The WD Crew is one of six sample crews wGrow has built; the others on this site cover business development, long-form articles, image production, product selection and finance. We can build the seventh for you.
Brief us →