--- title: "EcoHack London: the evidence base for your build" description: "Amass is the evidence base at Nucleate's EcoHack in London, 20 to 22 November 2026. $300 in API credits per team and the Amass Prize for biodiversity and public health." url: https://amass.tech/ecohack-london --- # EcoHack London: the evidence base for your build EcoHack, Nucleate UK, London, 20 to 22 November 2026 # Show how a change in an ecosystem becomes a change in human health. Every team gets **$300 in Amass API credits**. To start without code, add Amass to Claude, ask what is known about an ecosystem change and its effect on health, and check the record behind each answer. [Get started →](https://amass.tech/onboarding/ecohack-london)[Start here ↓](#start) Nucleate runs the weekend in London. The schedule, the venue and the rules are on the [EcoHack page](https://www.ecohack.co.uk/). Amass is a partner and joins remotely. An Amass team member answers questions in the EcoHack Slack over the weekend. Setup ## Start here, no code needed These four steps take you from a laptop to a first answer with its records. None of them needs an ecology background. The walkthrough shows every click. 1. 01 ### Make an Amass account Sign up with the email you registered with. A free account is enough to start. [Create your account](https://platform.amass.tech/api/auth/sign-up) 2. 02 ### Claim your team's $300 One person per team claims the credits on the claim page. The credits pay for API calls from code, so asking in Claude doesn't use them. [Open the claim page](https://platform.amass.tech/event/uk-eco-hack) 3. 03 ### Add Amass to Claude Add the Amass connector in Claude and sign in once. There is no key and nothing to configure. [The Claude setup guide](https://amass.tech/how-to-do-scientific-work-in-claude) 4. 04 ### Ask what is already known Type a question in plain language, then open the records Claude cites. Which studies link land-use change to zoonotic spillover, and how strong is the evidence? [See the records](#evidence) [Open the walkthrough →](https://amass.tech/onboarding/ecohack-london) If you get stuck, ask in the EcoHack Slack, or in the [Amass Discord](https://discord.gg/sEGaBHMhWa). Words on this page \*Core One of six Amass databases, such as papers (BioMedCore) or clinical trials (TrialCore). MCP (Model Context Protocol) How Claude and other assistants connect to Amass. API How code asks Amass for records, and each call uses your team's credits. API key A private key your code sends with each call, made on platform.amass.tech. If you code ## Hand your agent the Amass skill Paste one prompt into Claude Code, Cursor, Codex, or any agent that reads skills. It installs the amass-api skill, which teaches the agent the six \*Cores, their filters, and the response envelope before it writes a single call. The skill reads your key from `AMASS_API_KEY`. Agent prompt [Agent setup](https://platform.amass.tech/documentation/for-ai-agents/llm-quick-reference) Install the Amass API skill. Run \`npx skills add amass-technologies/public-skills --skill amass-api\` and select the agent you are running in. You can read the skill directly at https://github.com/amass-technologies/public-skills/blob/main/skills/amass-api/SKILL.md (raw: https://raw.githubusercontent.com/amass-technologies/public-skills/main/skills/amass-api/SKILL.md), with the full API reference next to it in AMASS.md. The skill reads my key from AMASS\_API\_KEY. If it is not set, tell me to create a key at https://platform.amass.tech and export it. Then use the Amass API skill when working on this project. [SKILL.md](https://github.com/amass-technologies/public-skills/blob/main/skills/amass-api/SKILL.md)[View on GitHub](https://github.com/amass-technologies/public-skills/tree/main/skills/amass-api) The evidence base ## What is already known about ecosystem change and disease Before you model spillover or health, read what has been published. These are real BiomedCore records. Check the full text before you cite a number from one. BioMedCore · primary studies ### Two studies that measured the link Long data series from two regions. Read them before you choose a driver to model. - Pathogen spillover driven by rapid changes in bat ecologyNature 2022PMID 36384167 25 years of Hendra virus data. Land-use change and climate keep bats in farmland, and spillover to horses comes in clusters. - Spillover risk for yellow fever virus is amplified by forest-urban interface in the AmazonBiology Letters 2025PMID 41537805 Two decades of case data from Brazil, Peru and Colombia. Forest fragmentation did not predict spillover. Forest next to towns did. BioMedCore · reviews ### Two reviews, for what has not been studied yet Use them to find the gaps. In the first review, urbanisation was the most-studied land-use change. - Emerging zoonotic diseases originating in mammals: a systematic review of effects of anthropogenic land-use changeMammal Review 2020PMID 32836691 Most studies were global reviews. Urbanisation was the most-studied land-use change, and bats were mostly studied with deforestation. - Human-mediated impacts on biodiversity and the consequences for zoonotic disease spilloverCurrent Biology 2021PMID 34637744 Asks where biodiversity change is mechanistically linked to spillover, and where the mechanism is still unclear. Where to start ## Two AI tracks, and a prompt to paste The brief has two AI tracks, and you can pick one or mix them. The first idea in each track is the organisers' example. The second is ours, built on the same records. AI track: Biodiversity and public health ### Therapeutic gap map Rank viruses and bacteria by how likely habitat loss is to push them from wildlife into people. Then flag the ones with no vaccine or treatment yet, using pathogen genomes and the drug and trial records. DrugCore and TrialCore, plus your own genomes ### Who is most at risk Pick one region or one pathogen. Use the spillover papers to choose the drivers, such as land-use change, the forest edge next to towns, or climate. Map who lives near that change, and show where the evidence is thin. BioMedCore and your own data, a day AI track: Closing the data gap ### Health evidence agent An AI tool that pulls evidence linking ecosystem change to human health from papers and databases. It shows what is known and where the gaps are, with a record id behind each claim. BioMedCore, a few hours ### Forecast a health outcome Bring one ecosystem measure, such as land cover, and one health outcome from a public dataset. Test whether the link holds on the cases your model did not see. Your own data, a few hours Paste this into Claude or Cursor to start prompt ``` Map the evidence on how land-use change affects zoonotic spillover. Use the Amass connector to search BioMedCore for systematic reviews and primary studies from 2019 onward. Give me one row per paper: the pathogen or host, the land-use change studied, the region, and the main finding. Mark any claim that comes from the abstract only, not the full text. Then tell me which two papers would make the strongest baseline for a model of spillover risk, and say why. Say clearly where the evidence is thin, because a gap in the records is not the same as no effect. ``` The offer ## $300 in API credits per team, and the Amass Prize Sign up on the platform, then claim your team's credits on the claim page. Create your API key before the weekend so the first morning goes on building. [Claim your team’s $300 →](https://platform.amass.tech/event/uk-eco-hack)[Open the build assistant](https://platform.amass.tech/assistant) What $300 buys Roughly **6,000 searches** or **30,000 record fetches**. Search costs $0.05 per 20 results; get-by-id and lookup are $0.01 each. That is plenty for a weekend, so query freely and cache what you re-run. The Amass Prize **Biodiversity and Public Health.** For the team that best uses human, genetic or molecular data to show how a change in an ecosystem becomes a change in human health, and what we could do about it. Show which records your tool read and what it did with them. \[What the prize includes: to confirm with Nucleate before this goes live.\] Apps to fork ## You do not have to start from an empty file Every app in the gallery runs on the same API, the same key, and the same cited records as the examples above. Fork one, point it at your key, and change the question it asks. [Browse the app gallery →](https://platform.amass.tech/app-gallery)[No-code recipes](https://amass.tech/life-science-api) platform.amass.tech/app-gallery Research #### From Gene to Approval One gene → every drug, trial, and FDA/EMA approval behind it. Research #### Graveyard & Garden 25 years of late-stage trials, halted or still alive. Research #### Clinical Trial Atlas Where a drug is tested, and which regions are enrolling. Research #### Indication Timeline A drug across its Phase-3 indications and approvals. Regulatory #### Transatlantic Divergence Desk FDA versus EMA outcomes, side by side. Clinical #### Pipeline Monitor A weekly digest of new Phase 2/3 trials by sponsor. Find us ## We are remote, and in the EcoHack Slack Amass is not at the venue. An Amass team member answers questions in the EcoHack Slack over the weekend, so ask there, even if the build is still a sketch. The EcoHack Slack Questions about credits, endpoints, or which \*Core holds what are all fair game. Post the query you tried and what came back, and we will help from there. Join from the link on the EcoHack page. [Open the EcoHack page →](https://www.ecohack.co.uk/) Before the weekend Create your account and API key on the platform, and try the prompt above, so the first morning goes on building. The build assistant can write your first call with you. Playbook ## Six things worth knowing before the weekend These are what separate an entry that lands from one that spends the weekend fighting its own plumbing. 01 ### Narrow until it feels too small. You have about a weekend of building. A finished small tool beats an unfinished large one, and the judges can tell. 02 ### Read the prior art in the first hour. Ecology and public health both have a long literature. Twenty minutes with BioMedCore saves you from rediscovering a known result on Sunday afternoon. 03 ### Build the baseline first. A random score, a simple rule, the manual version of the workflow. It turns your number into a result instead of a claim. 04 ### Show where it fails. A demo that names its own failure mode reads as principled work, and it is the part judges remember. 05 ### Cite it or drop it. Every Amass record carries a stable id and a route back to its source, so there are no invented PMIDs in your pitch. 06 ### Test the link, not just the model. A correlation between land use and disease is a claim to test, not a finding. Say whether your tool shows a link or a cause. Prototype in Claude ## Sketch it in a chat before you write any app code. Connect the Amass MCP in Claude, Cursor, ChatGPT, or Codex and query all six \*Cores in natural language. Look up what is already known about a driver or a pathogen, find the filters that work, and only then drop the same queries into your build. On the Sunday it doubles as the demo: the answers come back cited in the chat, with nothing to deploy. [Connect the MCP](https://amass.tech/mcp)[Or install the Amass skill](#quickstart) ## Build something a judge can check Set up your key before the weekend, and let the API do the reading. Narrow it until it feels too small, build the baseline, and show where it breaks. [Create your Amass account →](https://platform.amass.tech)[The EcoHack page](https://www.ecohack.co.uk/)[Connect the MCP](https://amass.tech/mcp) We are remote. Find us in the EcoHack Slack, or on the [Amass Discord](https://discord.gg/sEGaBHMhWa). Data No training on your data Hosting EU-hosted, enterprise Isolation Tenant-isolated by architecture Certification ISO 27001, SOC 2, NIS2: in motion