beitdin.dev

> what_is_this

three specialists read your brief at the same time and hand you one document with all three outputs.

each lane holds a model and a role: a title and a system prompt. the same brief reaches lane one as a technical architect and lane two as a security expert, so the answers diverge because the framing differs, not because you asked three different things.

this is not a model comparison tool, but you can use it like that too if you want. it is not asking which model wrote the better answer to one question. the lanes ask different questions of the same brief.

every lane is configured on its own, so you can put openai beside gemini beside a local ollama.

shuffle_roles deals the roles out to different lanes. run the same brief again and the security role lands on a model that did not hold it last time. every run appends to the same markdown document, so the angles stack up in one file that you can hand onward.

bring your own key. there is no server, no account and no queue: the page is static and your browser talks straight to whichever api you point it at.

> architecture_and_data

no backend: the app is a fully static html/js page. your brief, data, and api keys go directly from your browser to your chosen ai provider. data never routes through beitdin's servers.

keys are not saved to disk: api keys are stored only in the browser's session storage. they disappear completely as soon as you close the tab. they are never written to your hard drive or sent anywhere else.

open source: the code is public and open source on github.

> why_it_exists

built for getting multi-angle responses from different models and role combinations.

built to replace the copy-paste round trip: three tabs open, the same brief pasted three times, three answers stitched together by hand afterwards.

the useful part is not that three models answer. it is that they answer as different specialists, so the output stacks into something you can hand onward rather than three versions of the same paragraph.

currently this supports running 3 apis at once, but try also shuffle roles when you have run once and get more perspectives.

all runs will be stored in this session in the download .md file located in the bottom right corner.

> privacy_and_safety

zero tracking: the app has no analytics, cookies, third-party scripts, or telemetry. no one is monitoring what you write.

no xss risk: ai-generated responses are injected using the textcontent method instead of innerhtml, meaning the ai cannot accidentally inject executable code into the page.

strict csp: the page enforces a strict content security policy (script-src 'self'), blocking any external scripts from loading.

> user_responsibility

keys in memory: as long as the tab is open, your api keys live in the browser's memory in plain text. a malicious browser extension reading page data could theoretically capture them.

endpoint responsibility: since you configure the target url, you are responsible for knowing where your keys are sent.

> summary_and_recommendation

beitdin is inherently more secure than most ai wrappers or saas platforms because it removes the middleman. you communicate directly with the ai's api.

recommendation: highly recommended. to eliminate all risk, generate dedicated api keys for this app in your provider's dashboard and set a strict monthly spending limit.

> disclaimer

this tool is provided "as is", without warranty of any kind. the author takes no responsibility for any misuse, data leaks, api costs, or any other consequences resulting from the use of this software. use at your own risk.