Blog
Notes from the workshop.
How we think about people and agents working together, data that stays where it belongs, and what shipped.
- AgricultureMeasure field acres from a shapefile in your browserHow to get true acres from a field boundary shapefile, why flat maps inflate area in the northern plains, and a free way to do it with nothing to install.
- ReleasesPrism Desktop 0.5.53: more Linux computers, and your agents foundPrism now opens on Ubuntu 22.04 and newer, Debian 12 and newer and Fedora, and finds agent programs you install from a terminal.
- CompanyFrom ocean drones to one engine: the Prism Labs journeyHow an ocean-plastic drone idea at NDSU became WeSentinels, then CleanSentinels, then Prism Labs, and what each step became today.
- Water risk$259 million in flood claims: what North Dakota's record shows13,307 flood insurance claims in North Dakota from 1978 to 2025 paid $259.5 million. Two years, 1997 and 2011, account for three quarters of it.
- Water risk18 North Dakota counties have no countywide digital flood mapAs of 27 September 2026, 18 of North Dakota's 53 counties have no countywide map in FEMA's digital flood layer, including Ward, home of Minot.
- Data custody38% of US workers have put company data into personal AIA July 2026 survey found 38% of US workers entered work information into personal AI accounts, and most did not know it can be illegal. What organisations can do.
- AgricultureA forecast we built, and do not show youPrism Microclimate shows a prediction only if it beats the simple guess on days it never saw. One of our own forecasts failed that test, so growers never see it.
- AgricultureFarmers want proof before autonomy. Start on their own field.Experts at Big Iron said autonomy on farms lags expectations: cost, repairs and data. Showing it on a farmer's own field, first, answers part of that.
- PolicyFEMA reform would hand states more of the work. And the data?A federal review council proposed shifting disaster and flood work toward states and private insurers. What it recommends, and why local flood data matters.
- Water riskFlood protection is being built. The flood map gap remains.Minot and Fargo are building major flood protection. Yet 18 North Dakota counties, Ward among them, still have no countywide digital flood map.
- PolicyNorth Dakota's $160 million bet on agricultural technologyThe NSF AgTech Engine at NDSU received $45 million in March for three more years, with up to $160 million over ten. What the programme is for.
- PolicyNorth Dakota's AI committee: what it is studying, and whyNorth Dakota formed an interim committee on AI and data centres in June 2026, with draft bills due by November. What it covers and the wider picture.
- PipelinesOur checks caught a common data tool quietly changing recordsA widely used conversion tool rounded long decimals and shifted plain dates while loading flood data. An independent re-count caught it before anyone relied on it.
- ReleasesPrism Desktop 0.5.52: Codex agents reach Prism againA Codex agent that is allowed to use the network can run Prism's own command line from its shell again, even with Codex's network proxy switched on.
- ReleasesPrism Map Studio: a map workspace in your browserPrism Map Studio opens today: add your own data, run more than a thousand analysis tools, ask your layers with SQL, and open files right in your browser.
- AgricultureThe 2026 drought: why the state average hides your fieldMore than half of North Dakota was in drought this August, yet the state yield forecast barely moved. Growers on the ground describe something very different.
- PolicyThe Deere repair settlement, and what it means for autonomyIn July the FTC and five states settled with Deere for ten years of repair access for farmers. Why it matters for the autonomous machines coming next.
- Water riskThe federal flood insurance deadline, explained for North DakotaThe National Flood Insurance Program now runs to 11 December 2026. What a lapse would mean for North Dakota homeowners, buyers and lenders.
- Data custodyWhen AI makes up sources: what the court cases teach everyoneCourts have now addressed more than 1,400 cases of AI errors such as invented citations. The lesson reaches far beyond law: an answer is only as good as its source.
- PolicyWho owns farm data? The new laws, explainedNebraska made producers the owners of their farm data in 2026, and a federal bill followed in September. What the laws say and what they would change.
- ReleasesPrism Desktop 0.5.51: a real calendarDay, week, month and agenda views across your synced calendars, meeting links and reminders, and editing only after you allow it and confirm each change.
- ReleasesPrism Desktop 0.5.50: an admin console for operatorsAn admin console for the people who run a Prism server: people and roles, server mode and activity. The bundled node now checks signatures.
- ReleasesPrism Desktop 0.5.49: unread, folders and one-click actionsMail gains unread state, all folders, faster background sync, one-click actions, paging through long lists, and forwarded mail that keeps its attachments.
- ReleasesPrism Desktop 0.5.48: mail keeps syncing after renewalA fix for mail and calendar sync failing after the provider renewed its access token. The step that re-registers the account now works as intended.
- ReleasesPrism Desktop 0.5.47: a three-pane mail clientMail becomes a three-pane client, and mail and calendar now sync on their own, every ten minutes, with a clear message when you need to reconnect.
- ReleasesPrism Desktop 0.5.46: Gmail sign-in fixed, agent mail toolsA fix for Gmail sign-ins that Google approved but Prism refused, plus mail and calendar tools for agents. A person still confirms every send.
- ReleasesPrism Desktop 0.5.45: sign in with GmailThe first Prism Desktop release with Gmail sign-in. Outlook sign-in is not configured in this build and follows later.
- ReleasesPrism Desktop 0.5.44: a card for every agent's runtimeEach agent publishes a card with its runtime, model, skills, plugins and limits, and the card updates when you switch the agent to another model.
- ReleasesPrism Desktop 0.5.42: no duplicate tasks, cleaner repliesThe task board refuses a task that is already on it, and replies from Claude Code and Codex agents keep each new block of text on its own paragraph.
- ReleasesPrism Desktop 0.5.41: agents check themselves at the startWhen a conversation starts, each agent checks that it can reach Prism. If it cannot, its first reply says so, with the reason, instead of failing quietly later.
- ReleasesPrism Desktop 0.5.40: Claude Code and Codex reach PrismClaude Code and Codex agents now receive their Prism connection, so they can use the task board and Prism's own commands from inside a conversation.
- ReleasesPrism Desktop 0.5.39: a shared task board for agentsAgents split a request into tasks on one shared board. Each task can be claimed by one agent at a time, and a stalled claim can be picked up by another.
- ReleasesPrism Desktop 0.5.38: faster Claude repliesClaude Code agents keep one live process for each conversation, so follow-up replies start sooner. In testing, the third reply came in about half the time.
- ReleasesPrism Desktop 0.5.37: your own agents on your own loginYour personal Claude Code login can serve your own agents working together, and a refused agent start is now logged and shown on the agent's card.
- ReleasesPrism Desktop 0.5.36: a merged inbox and a long fix passOne Inbox with Email and Meetings filters and a single search, plus a long pass of reliability fixes to agents, reconnects, mail and huddles.
- ReleasesPrism Desktop 0.5.35: agents shared with the channelChannel members can carry on a thread with the same agent, and agents owned by different people can work on one problem in the same channel.
- AgentsBring your own AI subscription: what it means and why it mattersBring your own AI subscription means a tool uses the AI account you already pay for instead of reselling model access. Here is how it works and why.
- PipelinesChange detection: asking "what changed since last time?How change detection works in data: stable keys, snapshots, checksums, separating noise from real change, and turning differences into a report.
- Data custodyData provenance: keeping receipts for every recordData provenance records where each record came from, how it was fetched and whether it has changed. What to store, and why it pays off later.
- PipelinesEntity resolution: working out which records are the same thingHow entity resolution works, from cleaning and blocking to scoring, clustering and human review, and how to handle false and missed matches.
- AgricultureFrost risk explained: radiative and advective frostThe two kinds of frost, why low spots freeze first, what makes a frost night likely, and why the type of frost decides which protection methods can work.
- AgricultureGrowing degree days explainedGrowing degree days measure accumulated heat to estimate crop and pest development. Here is the formula, worked examples, and the limits of the method.
- Data custodyHow this website counts visits without cookiesWe wanted to know which pages are useful without tracking anyone. This site counts visits and clicks with no cookies, no stored IP addresses and no third party.
- PatentsHow to read a patent claimLearn to read a patent claim: preamble, transitional phrase and body, independent and dependent claims, and why every element matters.
- AgentsHuman in the loop: designing approvals people do not skipHuman-in-the-loop approvals only work if people read them. Here is how to decide what needs approval and design prompts that get real attention.
- ProgrammesImpact reporting for funders: numbers you can defendHow to build impact figures a funder can check: clear definitions, counting rules, evidence for each record, honest gaps and careful wording.
- Data custodyLocal-first AI explainedLocal-first AI keeps your files, notes and keys on your own device and sends out only what a task needs. How it works and what it costs.
- TeamsMeeting prep briefs and follow-ups: what good looks likeWhat a good meeting prep brief and follow-up contain, how to write them quickly, and where AI summaries help and where a person still needs to check.
- AgricultureMicroclimate: why the nearest weather station is not your fieldWhy conditions in your field differ from the nearest weather station, which variables differ most, and practical ways to get closer to field-level weather.
- Data custodyOn-device meeting transcription: how it works and trade-offsOn-device transcription turns speech into text on your own computer, so meeting audio never leaves it. How it works, and what you give up.
- TeamsOne workspace, any AI, your data: why Prism Labs existsAI can do real work now, yet most organisations cannot hand it the work: scattered tools, data that cannot leave, answers nobody can defend.
- PatentsPrior art search basics for inventorsWhat prior art is, how novelty and obviousness work in general terms, and how to search patents by keyword, classification and citation.
- AgentsRunning more than one AI coding agent: why and howRunning several AI coding agents lets you work in parallel and cross-check results. Here is when it helps, how to set it up and what to watch for.
- AgentsSkills, plugins and tool servers (MCP) in plain EnglishSkills teach an agent how to do a task, tool servers give it new abilities through MCP, and plugins bundle them. Here is how each works and the risks.
- AgricultureSoil moisture sensors explainedThe two families of soil moisture sensor, volumetric and tension, how each works, what field capacity and wilting point mean, and how to read the data.
- AgricultureSpray windows explained: wind, humidity and inversionsA spray window is a period when weather lets a spray reach its target. How wind, temperature, humidity, Delta T and inversions affect spray drift.
- TeamsToo many work tools: what consolidation really takesWhy adding work apps makes the day harder, what real consolidation involves beyond cancelling subscriptions, and a practical way to audit your tools.
- ProgrammesTracking startup outcomes after an accelerator or programmeHow accelerators and university programmes can track what happens to startup teams afterwards: definitions, evidence, cadence and honest gaps.
- Data custodyTwelve questions to ask an AI vendor about your dataTwelve plain questions to put to any AI vendor about where your data goes, who can read it, how long it is kept and how you get it back.
- AgricultureWhat a digital twin of a farm looks likeA farm digital twin is a living model of fields, soil, weather, crops and machines. Here are its layers, how it differs from a map, and how to start.
- Data custodyWhat actually gets sent to an AI provider when you ask?A question to an AI model carries more than the words you typed. Here is what a request usually contains, and how to keep it small.
- PipelinesWhat is a data pipeline? Seven steps from raw records to answersA plain-English guide to data pipelines, from gathering raw records and keeping receipts to linking, review, sourced answers and delivery.
- PipelinesWhat is a digital twin?A digital twin is a digital copy of a specific real thing, kept current with data from it. Learn the parts, the uses and the common pitfalls.
- AgentsWhat is an AI agent workspace?An AI agent workspace is one place where people and AI agents share conversations, files, tools and approvals. Here is what it contains and why.
- AgentsWhat is an AI agent, and how is it different from a chatbot?An AI agent is a language model that can take actions with tools in a loop, not just reply. Here is how that differs from a chatbot and why it matters.
- Data custodyWhat is data custody in AI?Data custody in AI means knowing who holds your data, where it sits, who can read it and how you get it back. A plain guide to the idea.
- AgentsWhen agents owned by different people work in one roomWhen several people bring their own AI agents into one shared space, ownership, access and approval need clear rules. Here is a practical way to set them.
- Data custodyWhere your AI keys and logins should liveAI keys and logins belong in your operating system's keychain or a secrets manager, not in code, chat or a vendor's database. A practical guide.
- Data custodyWhy AI answers need sources: grounding and citations explainedLanguage models write fluent text whether or not it is true. Grounding and citations tie each claim to evidence you can check. Here is how.
- AgentsWhy coding agents should work on a copy of your repoA coding agent should work on an isolated copy of your repository so you can review one diff before anything merges. Here is how git worktrees help.
- ReleasesPrism Desktop 0.5.33: every agent gets its own setupEach agent now picks its own model and account, with a private configuration of its own. Your native command-line logins are left untouched.
- ReleasesPrism Desktop 0.5.32: agents that reply reliablyA reliability release. A brief connection problem no longer makes a Codex agent abandon its turn or answer the same message again and again.
- ReleasesPrism Desktop 0.5.31: a truthful agent runtime checkPrism now recognises its own bundled Codex bridge correctly, restores the ready state and model list, and checks all thirteen agent programs it supports.
- ReleasesPrism Desktop 0.5.30: personal logins stay personalYour personal Claude Code login stays on your device even inside an organisation, and the desktop app now talks only to the public Prism API.
- ReleasesThe first public Linux builds of Prism DesktopPrism Desktop's first public Linux builds went out in early August, with signed automatic updates. Here is what that first month of releases covered.