Group 01
Define
What are we building, and for whom?
- 01Frame the idea
DefineResearchDecideBuild
Jary researches your market, finds the gap worth filling, pressure-tests the call, and turns it into a backlog that marks itself shipped when the PR merges. Every claim carries a link you can open.
Unified inbox for social-commerce sellers
Running · Read their trajectoryStep 5 · Research
Where the incumbents are heading, and which gaps they are already closing — read from shipped changelogs, not positioning pages.
Evidence gathered this stage
Bikko shipped WhatsApp Catalog sync in v4.2
gap closingCloses the catalog gap directly. Still no multi-channel inbox — orders from Instagram stay manual.
Tawk.to added Instagram DMs, dropped TikTok Shop
gap openingDeprecation notice cites low volume outside SEA. Leaves TikTok sellers in West Africa unserved.
Sellerfy raised Series A, hiring for "payments infra"
gap openingSix roles posted in ten weeks. Reads as a move into checkout, away from messaging.
Zendesk pricing moved to per-resolution
gap openingPrices out sellers under 200 orders/month — the exact band this idea targets.
Strategy lives in Notion. Tickets live in Linear. Code lives in GitHub. The translation between them is done by whoever has the smallest queue.
AI assistants suggest sentences. Ask one whether your competitor already shipped the thing you're scoping and it will guess, confidently, from a year-old snapshot of the web.
Jary goes and looks. Traffic, feature sets, shipped changelogs, complaint threads — pulled at run time, attached to the stage that used them, and cited in every claim it makes.
Each stage runs, leaves evidence, and unlocks the next. You can rerun any one of them, or interrupt and argue with the result.
Group 01
What are we building, and for whom?
Group 02
Who else is solving this, and where are they weak?
Group 03
Which gap do we commit to, and does it survive challenge?
Group 04
Turn the decision into backlog you can ship.
Research runs on its own. Decide always stops for you. Nothing rewrites a feature's scope without your approval.
This is the part other tools skip. Jary spends most of its run gathering things that are true, so the decision it argues for has something under it.
Stage 02
Names pulled from the language people actually use for the problem — search queries, community threads, and app directories — so the list isn't just the two or three brands you already had in mind.
Stage 03
Traffic and rank evidence separates real incumbents from names on a list. Nine competitors becomes three that matter and six you can stop worrying about.
Stage 04
Feature sets pulled from live product surfaces and compressed into the table stakes an MVP has to match before anyone will switch to it.
Stage 05
Changelogs and release notes say where incumbents are actually heading — which gaps they're closing this quarter, and which they've quietly walked away from.
Stage 06
Customer complaints grouped into recurring themes, ranked by how often they surface. The ones an MVP must solve to be adoptable, not the loudest one.
Gap analysis names the strongest unserved opening and the evidence behind it. Pick the focus commits to one. Then pressure-test turns around and makes the best case that the decision is wrong — using the contrary evidence from your own run.
If the focus survives that, it earns a backlog. If it doesn't, you found out before the sprint.
Stage 08 · Focus recommendation
Three of nine competitors are moving toward checkout and away from messaging. The complaint themes cluster on channel-switching, not catalog. Zendesk's per-resolution pricing prices out this exact band — 41 complaints reference cost at low volume.
Strongest case against
Bikko shipped WhatsApp Catalog sync six weeks ago and is the only competitor still investing in messaging. If they ship an inbox next, the wedge closes. What would have to be true: their hiring stays on messaging, not payments.
Link a repo and each shaped feature maps to a GitHub issue — or import the issues you already have. Your backlog and your code stop drifting apart.
Jary · shaped feature
GitHub · issue #142
PR #98 mergedissue #142 closedfeature advanced to Shipped
No ticket touched by handFor one person, getting organized.
The Idea Coach on its own — research, competitor intel, staged features.
Track features, bugs, and ideas through to shipped.
Everything in Standard, plus the Idea Coach and AI generation.
For organizations that need control and scale.
Coach and AI plans include AI usage; top up anytime — 1M tokens $15 · 5M tokens $60 · 20M tokens $200.
Eleven stages, one session, no credit card. Watch it find your competitors before you finish your coffee.