How it works
From request to customer told, in five steps.
Whoever knows the problem asks, agents resolve it with review, everyone follows along and the customer hears at the right time. Production follows your engineers’ call.
1Set up
Engineering connects, Alfrig works out the rest.
A guided walkthrough that takes a few minutes. The Ready for agents panel shows what’s missing for the first fix, and Alfrig works out almost everything on its own.
- Connect the code: Alfrig reads each repository and writes its card (what it is, the stack, how it’s tested and what it depends on).
- Where fixes go: agents deliver to a test branch; your team takes it to production.
- Requests and notices: a label in ClickUp, Jira, Linear or Azure Boards opens the task, and notices go to Slack, Teams or email.
- Invite the people who ask: CS and Product open requests, answer and follow along, without seeing settings.
- Check in the test environment: after the merge, QA checks each delivery the way a person would.
- The first delivery: a small, real task Alfrig spotted in your code.
2Ask
In your own words, the easiest way.
In the chat with Alfrig, type or speak, attach a screenshot or a screen recording, or paste the ticket link. Alfrig understands the problem, asks only what’s missing and shapes the request.
- Text, voice, a screenshot, a screen recording or the ticket link.
- Alfrig asks what’s missing, with options to click: what happens, what should happen, how to reproduce it and where.
- A broad idea becomes a Product initiative, with an agent in charge from start to finish.
- Also through a label in your tracker, the API or an AI assistant over MCP.
3Resolve
One agent fixes, another checks.
Every request becomes a spec with acceptance criteria. One agent investigates, fixes and tests; another reviews criterion by criterion; with green CI, the merge lands on the agreed branch.
- Each criterion says how it’s checked: test, QA or manual.
- When confidence is low, Alfrig confirms what it understood with whoever asked.
- Review in rounds up to a limit (3 by default); if tests fail, it becomes a draft PR, never a merge.
- Several repositories in one task, merged in dependency order.
- Every task leaves lessons about the project and keeps AGENTS.md up to date through PRs.
4Follow
Everything in plain sight, without asking anyone.
Progress shows who is working, what needs you and what was delivered. Notices arrive with the answer right there, in the app, Slack or Teams.
- Questions with options, answered with one click in the notice.
- Ask Alfrig "how is it going?" or ask it to approve, resume or comment on the ticket: each action becomes a card that only runs once you confirm.
- Each agent is a mascot that shows whether it’s free, working, needs you or has the delivery ready.
- The My requests filter shows only what you asked for.
5Tell the customer
You reply to the customer the day it goes live.
The timeline runs from received to live. When it reaches production, you get a notice and a suggested reply to review before sending.
- Received, understood, fixed in test, released, live.
- Released means it goes to production with the next release; live means it’s already there.
- A suggested reply to the customer, ready to copy.
- A tracking link that opens without signing in.
Agents
A real team, with names and faces.
The team comes ready, and any agent does any step. Each one is a mascot with a name, shape and color, and shows at a glance whether it is free, working, needs you or has delivered.
Name, shape and color
Five shapes and nine colors to choose from. Indigo belongs to Alfrig, who looks after them all.
No roles to configure
Investigating, building, reviewing, analyzing or designing: the step defines the work, and whoever is free does it.
Talk to them like a colleague
Chat with the agent in charge of a task, at any stage. What you agree on feeds the work.
- Anaworking
- Taylordelivered
- Lianeeds you
- Justinworking
- Theofree
- Irisfree
Built for your ecosystem
Alfrig understands your projects, your design and your day.
Nobody needs to know which repository the bug is in.
Import repositories straight from your GitHub, GitLab, Bitbucket or Azure DevOps account. An agent reads each project, writes its card and works out who depends on whom. That map is how agents pick where to change code and in which order to merge.
- A card per project: what it does, stack and how to test it.
- Dependencies with evidence: contract, package, API or events, each with the snippet that proves it.
- Whole repository or a monorepo folder; environment detected automatically (Node, PHP, Python, Java/Kotlin, .NET, Go, Ruby, Flutter or mixed).
- Mapping a 4-project catalog took 3.6 min and cost US$ 0.16 in model usage.
cadastro-api
Customer registration module that validates and normalizes payloads according to CONTRATO.md.
Node · node --test
formatos-br
Brazilian formats library (currency, CPF, CNPJ, ZIP, phone, dates), no dependencies. Formatting reference for the customer contract.
Node · node --test
Screens that look like your product, not a generic template.
An agent surveys the tokens, libraries, patterns and components of your frontend from the code, and opens each sample in a browser to check it renders. Every screen on the design board uses that system and your brand rules.
- Samples checked in a real browser, in light and dark.
- Talk about a component: the new version the agent proposes becomes the saved sample.
- Your organization’s brand and tone (what never to do, references) apply to every screen.
- Surveying a frontend’s design system took 3.3 min and cost US$ 0.31 in model usage.
Alfrig open all day, outside the browser.
The Mac, Windows and Linux app opens Alfrig in its own window, with its own session, and updates itself. Product changes arrive right away, no reinstall.
- Universal Mac build (Apple Silicon and Intel), Windows and Linux (AppImage).
- Automatic background updates.
- Sign in through your browser: Google and magic link keep working.
- The icon gets your attention when something is waiting for you.
Artifacts
Specs and prototypes you decide who to share with.
Every document an agent delivers in a chat becomes an artifact: specs, PRDs, checklists, UI copy and HTML prototypes. Each one has versions, lives in a searchable gallery and is shared the way you choose.
Born in the chat
Ask an agent for a spec, a checklist or a screen prototype: it comes out as an artifact.
Versions, not copies
Asked for a tweak? The agent delivers the whole artifact again with the same title, and it gets a new version.
Searchable gallery
Find by title or content, and filter between yours, the organization’s and the public ones.
Prototypes in light and dark
Screen prototypes open in the browser and switch theme in one click, ready to show a client.
Screen prototype
Getting-started checklist
v3 · Lia
Share · Visibility
Strategy
OKRs that guide the agents, not a spreadsheet in a drawer.
Alfrig runs a consultant-style conversation and builds objectives, key results and KPIs. Each initiative’s priority comes from that plan, and each one points to the result it moves.
A yearly plan through a chat
No spreadsheet or pricey consultancy: the conversation becomes objectives, KRs and KPIs.
A plan per quarter
Key results are spread across the four quarters, with a focus and milestones.
Quarterly check-ins
Alfrig asks whoever runs the organization to update the numbers, in the app and by email.
Business units
Groups with several products get a strategy per unit, each with its own owner.
Hi, I’m Alfrig. Let’s build the 2027 plan. First: what is your company and who does it sell to?
A finance app for small businesses. We sell to owners who don’t have an in-house accountant.
And what must be different a year from now? Give me a number you track today.
Draftin progress
Company
Finance app for small businesses with no in-house accountant.
Objectives and key results
O1 · Make onboarding self-service
- KR1 First-week activation35% → 60%
- KR2 Onboarding support tickets120/mo → 70/mo
Questions
Questions about how it works
How long does it take to get started?+
Someone from engineering connects the code and confirms where fixes go in a few minutes. Alfrig maps the repositories and suggests the first delivery right away.
How does Alfrig know which repository to change?+
When you connect, an agent reads each project, writes its card (what it does, stack and how to test it) and finds the dependencies between them. Agents use that map to choose where to change and in which order to merge.
Does Alfrig do more than fix things?+
Yes. A broad request becomes a Product initiative: an agent in charge understands the problem, proposes the deliveries, designs the screens and follows the build. And there’s Strategy: OKRs built in a chat that set the priority of initiatives.
How do the agents learn?+
When a task ends, the agent saves short lessons about the project that go into the context of the next ones; you review, write and delete whatever you want. The project’s AGENTS.md is written when missing and updated through PRs.
Who decides what goes to production?+
Your engineers. By default, fixes land on the agreed branch after review and CI; taking them to production is your team’s call.
What do you need to fix today?
What do you need?Write to Alfrig. It asks what’s missing and sees it through.5 deliveries on us, no card needed.