How is Vantage different from ChatGPT or Claude?

ChatGPT and Claude write you a document. Vantage keeps the document, prototype, tickets and roadmap connected to the feedback and decisions behind them, and tells you when one of them changes. You can also bring your Vantage context into Claude or ChatGPT, so you don’t have to choose.

Do I have to move off Notion or Linear?

No. Keep the tools you use and connect them to Vantage. Tickets push to Linear with two-way sync, and you approve every change that comes back.

What can I do in the first ten minutes?

Paste customer feedback or describe a problem, and get a PRD with every requirement linked to its source. You can try the demo on this page without signing up. Connect your tools whenever you’re ready.

I own several projects. What does Vantage do across them?

It briefs you every morning on what needs your call, catches specs that contradict each other, and flags anything that went stale after a decision changed. It works for a single project and earns its keep at two or more.

What if the AI gets something wrong?

Nothing updates silently. Every requirement cites the quote, call or metric behind it, and every change arrives as a diff you accept or reject before it touches your docs, tickets or Linear.

Can I use Vantage from Claude or ChatGPT?

Yes. Connect Vantage’s MCP server to Claude, add the GPT Action in ChatGPT, or use an API key. Then ask about your projects, search your specs, or create tickets from wherever you work.

Start on your own for free. When teammates join, they work from the same context, with admin, editor and viewer roles and private drafts that stay invite-only until you publish.

What does fair use mean on the unlimited features?

Unlimited features are meant for real day-to-day work by one person: up to 50 questions a day on Pro and Business, and on Business up to 10 PRDs, journeys or ticket batches a day. Very few people get close. If your team regularly needs more, talk to us.

Your data is encrypted in transit, and we never train on it. The AI providers we use are contractually barred from training on it too. You can disconnect any integration or delete your account at any time. We’re pursuing SOC 2 Type II.

How much does it cost?

Vantage is free to start with 300 credits and no credit card. Projects are unlimited on every plan, and AI work like generating a PRD or a ticket batch uses credits. Pro is $19 per seat a month billed annually ($25 monthly) with 1,500 credits a month, unlimited questions and prototypes. Business adds a shared team workspace and 4,000 credits per seat a month.

What is the difference between status and statusCategory in JQL?

status matches a specific workflow status name. statusCategory groups statuses into To Do, In Progress, and Done, so it works across projects with different workflows.

Can JQL show what changed in the last week?

Yes. Use history operators such as CHANGED, WAS, and CHANGED TO with DURING or AFTER, for example status CHANGED TO Done DURING (startOfWeek(), now()).

How do I get a Jira filter emailed to me automatically?

Save the filter, then add a subscription from the filter's details. You can choose the schedule and who receives it, subject to your site's permissions.

How-To2026-10-0710 min read

How to Write JQL Filters in Jira: A Practical Guide for PMs

Jira's basic search is fine for finding a single ticket. For anything a PM actually needs, such as every customer-reported bug in the current sprint or every story that moved to Done last week, you need Jira Query Language. JQL looks intimidating at first, but most useful queries are built from a handful of fields, operators, and functions.

This guide covers the JQL building blocks, a set of queries PMs reuse constantly, and how to save filters, share them, subscribe to them, and use them to power boards and dashboards. Field names can vary slightly between Jira sites, especially for custom fields, so use autocomplete in the advanced search box to confirm names on your instance.

Spec to tickets

Working in Jira? Turn your spec into dependency-ordered tickets.

Paste the feature or spec. Vantage pulls out the requirements and breaks them into tickets, ordered by what blocks what, ready to groom with your team.

How this works

We save what you typed. No AI runs on this page.
You create a free account.
Vantage builds a PRD and dependency-ordered tickets from it inside your own workspace.

Why ask for an account? We’re a small team, and a full generation runs a multi-step AI pipeline that costs us real money. So we tie it to a free account instead of running it anonymously. You also get to keep the result and edit it.

Your text is only used to create your project, and it stays private to your account. If you don’t sign up, we delete it after 7 days. Privacy policy

Step-by-step guide

Open advanced search

Go to Filters and choose to search work items or issues, then switch from basic to JQL (advanced) mode. The JQL editor autocompletes field names, operators, and values as you type, which is the fastest way to learn the syntax on your own Jira site. If a field you expect is missing, it may be a custom field with a different name or not available in the projects you are searching.

Open the Filters menu and start a new search
Switch to JQL mode
Type a field name and use autocomplete to explore operators and values

Learn the core building blocks

A JQL clause is a field, an operator, and a value: project = MOB. Combine clauses with AND and OR, group them with parentheses, and sort with ORDER BY. The operators you will use most are =, !=, IN, NOT IN, ~ (contains text), IS EMPTY, and comparison operators for dates. Relative dates such as -7d or -2w make queries reusable without editing.

Use IN for lists: status IN ("In Progress", "In Review")
Use IS EMPTY to find missing data: assignee IS EMPTY
Use relative dates: created >= -14d
Sort results: ORDER BY priority DESC, created ASC

Use functions for dynamic queries

Functions make filters adapt automatically. openSprints() returns active sprints, so sprint IN openSprints() always shows the current sprint without editing. currentUser() makes one filter work for everyone. startOfWeek() and endOfWeek() help with weekly reporting. membersOf("group-name") filters by a Jira group.

Build the PM queries you will reuse

A few queries cover most PM needs. Current sprint work for a project: project = MOB AND sprint IN openSprints() ORDER BY rank. High-priority open bugs: type = Bug AND priority IN (Highest, High) AND statusCategory != Done. Stale work: statusCategory = "In Progress" AND updated <= -10d. Unassigned items ready for the sprint: status = "Ready" AND assignee IS EMPTY. Using statusCategory instead of specific status names makes queries resilient to workflow differences between projects.

Current sprint scope for your projects
Open bugs by priority across projects
In-progress items not updated in 10 days
Items missing an estimate or assignee before planning

Query history with CHANGED and WAS

JQL can look at history, which is valuable for weekly updates. status CHANGED TO Done DURING (startOfWeek(), now()) lists what was completed this week. priority CHANGED AFTER -7d shows recent reprioritization. status WAS "Blocked" DURING (-14d, now()) finds items that were blocked at any point in the last two weeks, even if they have since moved on.

Save, share, and subscribe

Once a query returns the right results, save it as a filter with a descriptive name. Set sharing permissions so the right project or group can see it. Add a subscription to receive the results by email on a schedule; a Monday-morning subscription to 'high-priority bugs opened last week' is a simple way to stay on top of quality without opening Jira.

Save the query as a filter with a name that describes the question
Share it with the relevant project, group, or users
Create a subscription for a weekly email digest
Star the filter so it appears in your favorites

Use saved filters on boards and dashboards

Boards and dashboard gadgets are driven by saved filters. A dashboard with a filter results gadget, a pie chart grouped by status, and a created vs resolved chart can all point at the same saved filter. Changing the filter updates every gadget, which keeps reports consistent.

Common mistakes

Hardcoding sprint names

Writing sprint = "Sprint 42" means editing the filter every two weeks. Use sprint IN openSprints() or futureSprints() instead.

Matching specific status names across projects

Different projects often use different workflows. statusCategory = Done works across all of them; status = Done only matches projects that use that exact status.

Sharing filters too narrowly

If a dashboard gadget points to a filter that viewers cannot see, the gadget shows nothing for them. Check filter sharing permissions before building shared dashboards.

Tips

Use the text operator ~ sparingly; it searches text fields and can return noisy matches.

Keep a personal doc of your best JQL queries so you can copy them into new filters quickly.

Combine statusCategory with resolution date fields for accurate weekly completion counts.

Name filters after the question they answer, for example 'Open P1 bugs - Mobile'.

How Vantage helps

JQL is how you see the work; Vantage helps you shape it before it lands in the tracker. PMs turn context and a PRD into dependency-aware tickets in Vantage, with requirement links that make filtering by feature reliable once tickets are pushed to Jira or Linear.