What CHIRP gets
Stretch goal
Taken on if time allows, or funded on top, which brings Diamond to £53,425.
Where the days go
| Work | Days | Cost |
|---|---|---|
| Build | 61 | £30,500 |
| Contingency | 12.2 | £6,100 |
| Project management (not on the 6 new countries) | 13.8 | £6,900 |
| ZigZag product management, including a Maritime Safety Senior Stakeholder Workshop to decide the future direction of CHIRPdb | 12.2 | £6,100 |
| Total | 99.2 | £49,600 |
Not included
- A CHIRP-branded chat screen. Users ask through their own AI, such as claude.ai.
- Learning from user questions. Recurring patterns are found from each report’s metadata and text on every question, but not saved for next time. Questions are logged, which is the starting point.
- Full ingestion of the 6 new countries. These use fast ingestion, which is quicker but gives less reliable data.
- Causal AI.
Hosting and AI usage are paid by CHIRP. Costs come from the full menu.
Glossary
- Connector. A small new service that users add to the Claude harness. It holds no data: it turns the AI’s requests into calls to CHIRPdb, which does the searching and counting. Users sign in with a CHIRPdb account before it works. This page uses the Claude harness in its diagrams and examples, but the connector is a standard MCP server, so it also works with other AI chat services that support MCP, such as ChatGPT.
- Shared vocabulary. Each country describes the same thing in its own words: one says “fishing vessel”, another “fishing”, another “trawler”; severity and accident type vary in the same way. We map every country’s terms onto one list for each field, building on the IMO classifications we already use for accident type and severity. We also capture more fields from every report, so a report from any country carries close to the detail the MAIB spreadsheets give. The result: ask about fishing vessel groundings and the answer draws on the matching reports from every country, with counts that compare like with like.
- Review tool. The part of the CHIRPdb frontend that CHIRP staff use to check reports.
- Fast ingestion. 2.5 days per country instead of 5. Only some of each country’s reporting rules are built in, so the data is less reliable.
- Validated test set. A fixed list of questions with known right answers, re-run after every change to catch answers getting worse.
- Pattern finding and learning from user questions. Asking what keeps recurring across all reports, for example what keeps causing enclosed-space deaths, and seeing the supporting cases. Included in Diamond Finding what recurs across every report. Claude uses a CHIRPdb tool that searches every report in the database, both its metadata and its plain text, not just a handful of top matches. Claude decides what to look for, for example enclosed-space deaths by SHIELD code, vessel type and country, or a phrase such as “double shift” in the text, then compares the results and writes up the lessons. Counts from the metadata are exact, so every number traces back to its reports. Not included in Diamond Patterns in the plain text, and learning. Patterns that appear only in the text are harder: the system has to read the reports to spot them. For example, many reports may mention that the crew had just finished a double shift, but no field records it, so Diamond cannot count it. With learning, the system would spot it in the text and save “crew had just worked a double shift” against each report it applies to, in effect a new piece of metadata. The next time anyone asks something similar, the system checks the metadata first, then the saved findings, and only then goes back to the plain text, so answers get faster and more consistent with every question. Diamond logs every question, which is the starting point for this.
- Causal AI. Working out which factors actually cause accidents, not just which ones appear together. CHIRP’s experts propose a cause, for example that fatigue leads to groundings, and the system tests it against the reports, showing how strong the effect is; nothing is cited until CHIRP signs it off. It also tests whether a regulation or recommendation worked. Diamond shows what recurs, not what causes what.
- Log. A record of each question asked and which reports the AI used to answer it.
Questions Diamond can answer
-
“How many fishing vessels have sunk in the last ten years, and in which countries?”
A typical answer 112 fishing vessels sank across the 8 countries since 2016. The UK had the most (38), then the US (27) and Norway (14). Most capsized after flooding or losing stability. Each count links to the reports behind it.
How Claude asks CHIRPdb
count_reports(vessel_type="fishing vessel", vessel_sank=true, accident_date_from="2016-01-01", group_by="country")In plain English Count the reports about fishing vessels that sank since 2016, split by country. -
“What keeps causing deaths in enclosed spaces?”
A typical answer Across 46 fatal enclosed-space accidents, two factors recur most: poor planning of the task (29 reports) and procedures not followed (24). A common sequence: the atmosphere was not tested, and a second person died going in to help. Each point links to the report page it comes from.
How Claude asks CHIRPdb
search_text(text="enclosed space", deaths_min=1) count_reports(text="enclosed space", deaths_min=1, group_by="shield_code")In plain English Find passages that mention enclosed spaces in reports where someone died, then count those reports by SHIELD code. -
“Compare collisions in the UK and the US since 2015.”
A typical answer A table of collisions by country and vessel type, 212 in UK reports and 184 in US reports, with the biggest differences called out: fishing vessels feature far more often in UK reports, towing vessels in US reports.
How Claude asks CHIRPdb
count_reports(accident_type="collision", country=["UK", "US"], accident_date_from="2015-01-01", group_by=["country", "vessel_type"])In plain English Count collisions in UK and US reports since 2015, split by country and vessel type. -
“Has anything like this happened before? A bulk carrier grounded at night with one person on watch.”
A typical answer 6 similar groundings, closest first: the bulk carrier Ocean Venture, Australia, 2018, grounded at night with the officer of the watch alone on the bridge; and so on, each with a one-line summary and a link to the report.
How Claude asks CHIRPdb
find_similar(description="bulk carrier grounded at night, single watchkeeper")In plain English Find past incidents that read most like this description. -
“Write me a toolbox talk on mooring line injuries, from real cases.”
A typical answer A one-page toolbox talk in plain English: what went wrong in 14 real cases, the warning signs, and what to do differently, each point linked to the report it comes from.
How Claude asks CHIRPdb
search_text(text="mooring line", injuries_min=1) get_report_pages(report_ids=[…], pages="matching passages")In plain English Find passages about mooring lines in reports where someone was injured, then fetch those report pages.
Illustrative: the tool names and fields are settled during the build, and the figures and vessel names in the answers are made up for illustration.
How CHIRP’s users get answers
What happens when someone asks a question
How it fits together
Scope status after CHIRP’s update
| Deliverable | Done when | In Diamond |
|---|---|---|
| Must | ||
| A broad and validated data set “The real Must is a broad and validated data-set.” (CHIRP’s update) | In Reports from the UK, the US and up to 6 more countries, Compare incidents across countries like with like, SHIELD matching, A validated test set, and logging. The 6 new countries use fast ingestion; the validated test set checks the answers drawn from them. | |
| 3a Pattern analysis “As a CHIRP analyst, I want to ask questions across all reports and datasets, so that I can unearth patterns and publish insight that raises awareness and encourages improvement.” CHIRP’s top priority. | “An analyst query returns pathways with supporting cases, and drafting support produces a reviewable outline.” | In Compare incidents, find recurring patterns and draw lessons, Every conclusion traceable to its source report. Claude shows the recurring sequences with their supporting cases, and drafts an outline from the cited results for an analyst to review. |
| 1a Task briefing “As a seafarer or supervisor about to start a task, I want to know what has gone wrong during similar work, so that I recognise the critical hazards before I start.” | “A member of the public asks a task question and receives a briefing in which every claim is cited to a verified report.” | In Asked through an AI, Compare incidents, find recurring patterns and draw lessons, Every conclusion traceable to its source report. For invited users; opening it to the public is the stretch goal. |
| 2a Near miss “As a seafarer who has just had a near miss, I want to describe what happened, so that I can see whether others have experienced the same thing and what they learned.” | “A typed description returns related verified incidents, their shared factors and a link to CHIRP’s reporting form.” | In Compare incidents, find recurring patterns and draw lessons (find similar incidents). The AI is instructed to point near misses to CHIRP’s reporting form. |
| All marine accident investigation bodies publishing in English “Full investigation reports from flag and coastal states. The core corpus. MAIB reports are already ingested (P1).” | In Reports from the UK, the US and up to 6 more countries, the breadth CHIRP set for Tranche 2. | |
| Should | ||
| CHIRP Maritime published reports “De-identified confidential reports and commentary. Closest to seafarer experience. Roadmap step 13.” | In CHIRP’s own reports. | |
| Citation integrity “Every public answer cites verified records and links to the source report (step 10).” | In Every conclusion traceable to its source report. Still a fixed constraint in the scope. | |
| 1b Toolbox talk “As an onboard supervisor, I want the briefing produced as a toolbox talk, so that I can brief the crew from real incidents.” | “A request for a named task returns a printable toolbox talk with sources.” | In Asked through an AI, see the example questions. |
| 2b Code incoming reports “As a CHIRP analyst, I want each report we receive coded and set against similar cases, so that I can assess it quickly and consistently and respond with context.” | “A submitted report returns proposed coding and similar cases, and nothing enters the database until verified in the review tool.” | Partly SHIELD matching and Compare incidents, find recurring patterns and draw lessons (find similar incidents), for published reports only. |
| Production hardening “Logins and role-based access for CHIRP staff and partners; anonymous public access kept separate from the review tool and drafting features.” | Partly sign-in and user management in Asked through an AI. | |
| Public usage controls “Rate limiting per user, a spending cap on question-answering costs, and protection against abuse, scraping and prompt injection.” | Partly rate limits and abuse protection in the stretch goal. | |
| Monitoring and correction “Usage and error monitoring with alerts, and a route to correct or withdraw a published answer or record.” | Partly monitoring in Asked through an AI. No correction route. | |
| MAIB Safety Digests and bulletins “Short-form learning. Roadmap step 13.” | Future scope | |
| Duplicate and derivative tracking “Many sources republish or edit the same event (MARS, SAFETY4SEA, IMO GISIS and national bodies). Each derivative account links to its source report, and pattern analysis counts the event once.” | Future scope | |
| 3b Dashboards “As a shore-side manager or commercial operator, I want to explore trends across the evidence base, so that I can find vulnerabilities and decide where to invest.” | “Dashboards filter by vessel type, date, outcome and country, and every figure traces to verified records.” | Future scope The same counts can be asked for through Asked through an AI. |
| 3c Legislation links “As CHIRP, I want to see where incidents recur because regulation is absent, unclear or poorly implemented, so that I can put evidence to flag states and encourage change.” | “Findings carry AI-proposed legislation links, clearly caveated for the user to verify, and an analyst can list recurring findings by instrument.” | Future scope |
| IMO GISIS Marine Casualties and Incidents module “Investigation reports submitted to IMO, filling gaps for states without their own publication site.” | Future scope | |
| IMO Lessons Learned from casualty investigations “Short anonymised lessons drawn from member-state investigations.” | Future scope | |
| Nautical Institute MARS “Free-text narratives of the kind third parties will submit. Mostly edited from regulators’ reports, so depends on duplicate tracking.” | Future scope | |
| SAFETY4SEA “Incident news and safety articles, often derived from investigation reports, so depends on duplicate tracking.” | Future scope | |
| IMCA safety flashes “Offshore and marine contracting incidents with lessons.” | Future scope | |
| USCG Marine Safety Alerts and lessons learned “Short-form alerts linked to US investigations.” | Future scope | |
| UK legislation and MCA notices “Instruments to link findings against, starting with the UK flag.” | Future scope | |
| ILO Maritime Labour Convention “Hours of rest, manning and welfare requirements.” | Future scope | |
| IMO conventions and codes “The core international instruments.” | Future scope | |
| Could | ||
| 1c Upload a risk assessment, permit or plan “As an onboard supervisor, I want to upload a draft risk assessment, permit or plan, so that it is challenged against previous incidents before authorisation.” | “An uploaded document returns missing hazards and controls with sources, and is deleted after the session.” | Future scope |
| 2c Upload your own report “As an organisation or onboard investigator, I want to upload our own report or event narrative, so that I can find comparable cases and lines of enquiry, knowing the document itself is not kept.” | “An upload returns comparable cases and factors. At session end the document is deleted and a pattern record (SHIELD codes, vessel type, operation, outcome, no narrative) is stored, flagged as contributor-derived and used in aggregate analysis only.” | Future scope |
| Upload terms “Terms stating where uploaded files are processed, that documents are deleted after the session, and that a de-identified pattern record is kept from 2c uploads.” | Future scope | |
| Scanned pre-2005 reports “Historic depth. Requires OCR, excluded from P1.” | Future scope | |
| P&I club loss prevention publications “Claims-led trend analysis and case studies.” | Future scope | |
| Copernicus metocean data “Historical wind, wave and sea state at the time and position of each incident, enriching reports that omit or understate conditions. Needs incident position and time from extraction (step 6).” | Future scope | |
Every deliverable in the Tranche 2 Development Scope, with its description quoted from that document, grouped by its priority after CHIRP moved 2b and all Musts except 1a, 2a and 3a to Should. Won’t items are left out.