For Engineering
Product and business context, in the agent writing the service.
Afara gives your coding agent the tickets, acceptance criteria and business rules behind the work, and your company's patterns for how to build it.
What your agent receives
Product context
Stories and acceptance criteria from the tickets the service is being built for.
Business context
The rules the business depends on, such as "a card is charged once per order", stated where the agent can act on them.
Service patterns
How this service is built inside: its layers, its boundaries and where business rules live.
Enterprise patterns
How it talks to other services: protocols, messaging and entry points.
Your implementation becomes context for frontend and QA.
Injected into the backend agent
by Afarapayments-api: how to build PAY-981
- Confirm in the domain layer, through the payment-provider port
- Enforce one charge per order in the domain, not the adapter
- Publish payment.confirmed; never call orders directly
- The receipt in PAY-981 is part of done
What engineering teams use most.
Next to git
Generate, link and push from the branch you already have.
Pre-push hook
Offline, fast, and only on branches that name a ticket.
Existing services too
Map a feature from the code as it is now with --existing.
Code stays local
Your AI tool reads a read-only copy. Only derived context is shared.
Afara for other teams
See Afara on one of your own features.
A 30-minute walkthrough with an engineer. Bring two repositories and a ticket, and see the context your agent would get.