High-precision evidence infrastructure.
Search for evidence, mine entire sources, and find the best responses. Turn what you find into debate evidence, organized in Notebooks and shared with your team through Workspaces.
[01] Search
A search engine built for debate.
Hand Search a claim and it finds the strongest sources on the open web. Browse the ranked results like you would any search engine, tuned to your claim.
01
From a claim to evidence worth cutting.
Traditional search engines return a list of links and leave the search to you. Tagma Search reads each candidate article against your claim and returns a debate-focused ranking with the source context to judge it.
02
Search by claim, question, or target words.
Use Tagma like any search engine: search a claim, ask a question, or enter a set of target words. It handles all three formats and finds debate evidence to match.
03
Native citations and author qualifications.
Citation extraction is suprisingly hard. It requires turning messy, unstructured data into clean, structured cites. Our system does it reliably and matches the best dedicated extractors.
04
Over-engineered to never miss a source.
Built to handle the toughest sites: IP bans, geoblocks, anti-bot systems, proxies, lazy-loading, popups, clickthroughs, and endless scroll. We recover nearly any URL on the open web, so search engine limits are never a reason to miss a source.
[02] Mine
Mine any source for arguments.
Point Mine at a PDF or a URL and it finds every extractable argument on its own, with no claim steering which spans matter. Mine reads the source the way a debater would, noticing where reasoning shifts and where one argument ends and another begins.
01
Built to cut books in minutes.
Point Mine at a 300-page book and it comes back with an entire file in minutes. Feed it a large batch of URLs instead and it runs the same way.
02
Tuned for K debate.
Mine works on any type of content, but dense K literature, the kind that punishes a skim, is what it's built for.
03
Assisted reading built in.
Mine returns PDFs in a built-in viewer with a highlight overlay, suggested cards in the margin, and a breakdown of each argument's warrants. Reading turns into a guided pass instead of a hunt.
04
High-precision PDF extraction.
Mine runs on state-of-the-art PDF extraction, pulling text with word-for-word confidence on every token. Built to handle the messiest documents.
[03] Crawl
A web crawler for the 1NC.
Crawl finds strategic openings in the affirmative’s argument map, then builds a coordinated negative strategy across topicality, disadvantages, counterplans, and case responses. Its agentic loop develops each position, researches and curates supporting evidence, and reshapes the 1NC as new findings change which arguments are worth advancing.
01
Branch out. Every line of attack, explored at once.
One case opens dozens of arguments, and each one splits into the routes it could take. Crawl follows all of them in parallel, further than a squad could chase in a week.
02
Loop until it holds.
Search, read, decide what's missing, search again. Crawl keeps working each argument until every step has evidence behind it, reroutes around dead ends, and keeps only what survives for the 1NC.
[04] TAGMA-1
The evidence engine behind Tagma.
Finding the source is the start. Tagma turns it into a card your team can use: a clear tag, the context that matters, and the lines that make the argument land.
Start with a built-in style or tune one for your team. Save it once and use it across every Tagma pipeline and your AI assistant.
01
Quality labels make reliable cards.
Instead of training a model on a million cards, we focus on quality data and consistent labels. Styles as a primitive gives the cutting engine a clear standard for classifying evidence and cutting cards.
02
Create your own style.
Upload at least 30 cards labeled in one consistent style. Tagma uses them to capture your team's approach to tags and highlighting, so new cards follow the conventions you already use.
03
Classification, not generation.
Tagma never invents, inserts, or hallucinates text into your quoted evidence. Every word comes from the original source.
04
Built on our own data.
Our built-in styles use reference data created and labeled in house. Your uploaded examples are used for your custom style.
[05] Notebooks
A text editor for debate evidence.
Notebooks is a free Word + Verbatim alternative for cases and speeches. Pull cards from Graph Search or any Tagma pipeline, retag or recut them in place, and inspect warrants as you write. Each card keeps its tags, citations, highlights, and source link across Notebooks and Workspaces.
[06] Workspaces
Dropbox for debate, graphed by arguments.
Start with 5 GB free. Tagma maps every file into a graph of cards, authors, citations, and arguments, so you can find evidence by what it says and trace its connections across your library.
[07] MCP
Bring Tagma into your AI assistant.
Connect Tagma to Claude or any other MCP-compatible assistant and ask for evidence in plain language. Your assistant runs the same Search, Mine, and Crawl as the app, gets back the same cut cards, and can save them straight to your workspace.
[08] Start
Start a notebook.
Free to start. No credit card.