Idea → Ticket → Tests → Code → Review → Done.
The same loop every great team runs — except the agent does the middle three. You start with an idea. You end with a merged PR.
From paragraph to pull request.
Type a sentence. Watch specship write the spec, the tests, and the implementation — in that order, every time.
specship will draft a full ticket with acceptance criteria
A spec-driven loop, on autopilot.
Click any feature to see it in action.
Assign a ticket. Get a PR.
The agent reads your ticket, writes the spec, drafts failing tests, implements, and opens a PR. You stay in the loop on every step — and in control of every decision.
- Acceptance criteria gate
- Tests written before code
- Conventional commits & branch naming
Add CSV export to invoices table
- User can click 'Export' in the table toolbar
- CSV includes filtered rows
- Streams to handle 10k+ rows
No surprise AI bills.
Subscription billing. Daily caps. Full per-ticket telemetry. The opposite of opening your dashboard to find an "oops" line item.
Set a ceiling. Specship respects it.
Per-project daily token spend cap. Defaults to a conservative $10/day and you can move it from there.
Threshold hit → everything stops.
Instead of running over budget, Specship pauses in-flight work and pings you. Resume manually or wait for tomorrow.
Every cent has a ticket attached.
Token spend is broken down per project, per ticket, per loop phase. Audit anything, no analytics integration required.
Five steps. Zero handoffs.
Connect
Authorize your Git host and your PM tool. Takes 30 seconds.
Describe
Open a ticket. Write a paragraph. Drop in a screenshot if you have one.
Assign
Route it to Shipd with your configured assignment, label, mention, or ready status. The agent picks it up immediately.
Review
Read the PR. Comment to request changes. The agent watches the ticket.
Ship
Merge. The bot updates the ticket and closes it. You're done.
Match this dashboard table layout
Same data as today, but laid out like this wireframe. Use existing components.
Paste a screenshot. Skip the Figma handoff.
Drop any image into a ticket comment — wireframe, screenshot, sketch on a napkin. The agent reads it, maps to your existing components, and matches the UI as closely as it can.
- No plugin. No spec doc. No handoff meeting.
- Uses your component library, not generic Tailwind.
- Asks if it's unsure — never guesses on ambiguity.
Research tickets that actually finish.
Tag a ticket as R&D. The agent researches the topic, reads docs and code, writes a comparison, and posts the whole thing back to your workspace.
Stripe vs. Paddle for European VAT handling
Simple tiers. Waitlist while we tune.
Pricing TBD — join the list to lock in beta rates.
Solo
For founders shipping alone.
- 1 connected repo
- 1 PM tool integration
- Unlimited tickets / month
- Test-driven workflow
- R&D ticket mode
- Visual spec attachments
- Multi-seat collaboration
- Private repo support
- Self-hosted runners
- SSO + audit logs
- Priority support
Team
For small teams that want guardrails.
- Up to 5 connected repos
- Unlimited PM tools
- Unlimited tickets / month
- Test-driven workflow
- R&D ticket mode
- Visual spec attachments
- Multi-seat collaboration
- Private repo support
- Self-hosted runners
- SSO + audit logs
- Priority support
Enterprise
For teams with their own compliance bar.
- Unlimited repos
- Unlimited PM tools
- Unlimited tickets / month
- Test-driven workflow
- R&D ticket mode
- Visual spec attachments
- Multi-seat collaboration
- Private repo support
- Self-hosted runners (rolling out)
- SSO + audit logs (planned)
- Priority support