One AI toolkit forbusiness analysts
Turn elicitation notes into requirements. Legacy screens into specs. An analysis session your AI tools can read. One menu-bar app, one shortcut, on your Mac.
Your job is turning conversations into requirements,
your tools weren't built for that
A BA's day is the same loop: elicit, document, keep the thread, hand off. A chat tab in the browser doesn't see the workshop you just ran, the legacy screen on your other monitor, or the requirement you clarified an hour ago, so you re-explain everything, every prompt.
Khint puts the analysis loop behind one shortcut. Select text anywhere and run an AI Action on it in place: a rough note becomes a structured requirement, a story gets its acceptance criteria, a spec paragraph tightens up. Capture a legacy screen or mockup to text without retyping it. Keep a work session running so every step knows what the last one did. And when the requirement is ready, create the Confluence page or Jira issue without leaving the palette: the integrations write into your tools, they don't replace them.
An analysis pass,
workshop to published spec
Every step below is a shipped feature, not a roadmap slide.
- 09:00Open a Memory session for the analysisBefore an elicitation workshop, press Start on a session called 'Claims module: requirements'. From now on, everything you capture, pull, and run gets compacted into a short context that every later Action sees.
- 09:20Capture the legacy screen nobody documentedA stakeholder shares an old admin screen you have to replace. Palette → Extract text pulls the labels and field names off it; Capture & ask lets you question the screenshot directly instead of retyping the UI by hand.
- 10:45Workshop notes → structured requirementsSelect your raw notes in any app, hit Cmd+Shift+K, and run a 'Draft requirement' Action. Because the session is active, the draft already knows which module you captured and what the stakeholder asked for, no re-explaining.
- 11:30Add the acceptance criteriaSelect the story and run an Action that returns Given/When/Then acceptance criteria a developer can build against: consistent format, every time, without hand-writing each one.
- 14:00Publish the spec to ConfluenceWith Atlassian connected, the palette can create a Confluence page from your refined requirements, so the doc lands where your team reads it. One page per run, so every write is explicit.
- 15:30Hand the analysis to your AI clientClaude Desktop or Codex reads the same live session over the bundled MCP server. Ask 'what did we decide about the claims module?' The context is already there, no pasted transcripts.
Start from packs,
not a blank prompt
Khint ships a starter-pack gallery you can browse and clone from the Agents page. For analysis work, Doc Polish tightens spec prose, Meeting → Ticket turns discussion into trackable items, and Backlog Refiner upgrades half-baked stories to a Definition of Ready. Add one, edit the prompts to match your requirements template, or describe a workflow in plain English and let the AI generator assemble the steps into a chain. When a set of Actions works, share the pack: teammates join with a link and clone it read-only, so a whole practice writes requirements the same way.
The four pieces of the toolkit
Analysis workflows, one page each
The parts of the loop, in depth: how each one works with real Khint features.
Common questions from business analysts
What can a business analyst actually do with Khint?
Select any text (workshop notes, a stakeholder email, a Slack thread), hit Cmd+Shift+K, and run an AI Action on it in place: turn rough notes into a structured requirement, draft acceptance criteria, or tighten a spec paragraph. The same palette captures any region of your screen to text, pulls and creates Jira issues, and creates Confluence pages once you connect an Atlassian API token. You work where the requirement already lives, not in a separate chat tab.
Can Khint write a requirements document or BRD for me?
Khint drafts from what you give it, not from nothing. Select your raw elicitation notes and run a reusable Action: it returns a clean problem statement, functional requirements, and open questions in your format. You keep authorship and review; Khint removes the blank-page work. When the section is ready, create a Confluence page from the palette so the doc lands where your stakeholders read it.
How does Khint help with requirements traceability?
Start a Memory session for an analysis pass. Everything you capture, pull, and run gets compacted into a short running context, so the decision you clarified at 10am is still attached when you draft acceptance criteria at 2pm. The session is a local record of the thread of decisions behind a requirement. See how Khint keeps requirements traceability in your notes, and expose the same live context to Claude Desktop or Codex over the bundled MCP server.
Does my requirements data leave my machine?
Only what you explicitly act on. An Action sees the text you selected plus, optionally, the active Memory session's compact summary, nothing else. Memory sessions live in a local SQLite file on your Mac and are never synced to a server. Atlassian and Linear credentials stay in your OS keychain.
Is there a free plan?
Yes. The free tier includes 10 AI actions per day and 5 screen captures per day, no credit card. Paid plans start at €7/month: Pro at €29/month gives 100 AI actions a day, and every plan includes all the work integrations. Khint runs on macOS 13+ and Windows 10 22H2+.
Run your next elicitation with it
Free with 10 AI actions and 5 captures per day. No credit card. Connect Atlassian when you're ready: it takes an API token, not an admin.