CUSTOM AI AGENTS · Product & engineering
Developer agentas part of your team.
Read relevant code. Implement the change. Prepare checks and an explanation.
Explore this agent for my team ↗01 · THE WORK, STEP BY STEP
How the task moves forward.
Agents work with project context, conventions and acceptance criteria. They prepare code, tests or documentation for the team's existing workflow.
- 01
Read relevant code
Locates modules and conventions relevant to the team's requested change.
- 02
Implement the change
Prepares an implementation scoped to the agreed acceptance criteria.
- 03
Prepare checks and an explanation
Explains affected files, checks and points requiring developer review.
02 · ILLUSTRATIVE EXAMPLE
A situation that may feel familiar.
A distributor adds order exports to an internal tool.
Illustrative scenario, not a customer case study or measured results.
SlackExampleIdentify the scope: paid orders and account isolation.
LinearExampleIt creates the task with the necessary scope and checks.
Export paid orders to CSV
Hugo · Development
- ○Export date, customer and total.
- ○Include only paid orders from the active account.
- ○Reject access without permission.
GitHubExampleModify the code and prepare tests on a separate branch.
Limit exports to the active account
export-orders-csv → main
const orders = await listOrders();const accountId = session.accountId;await requireAccess(user, accountId);const orders = await listOrders({ accountId, status: "paid"});return toCSV(orders);- ○Account permissions
- ○CSV columns
GitHubExampleCheck account isolation and exported content.
Checks for PR #128
| Case | Expected result | Result |
|---|---|---|
| Account A | Only that account’s paid orders | Passed |
| Access to account B | Access denied | Passed |
| CSV file | Date, client and total | Passed |
| Pending orders | Not included | Passed |
LinearExampleRecord the checks and link the proposal with the task.
Export paid orders to CSV
Hugo · Development
- ✓Export date, customer and total.
- ✓Include only paid orders from the active account.
- ✓Reject access without permission.
GitHubExampleThe delivery remains at the repository with its true context and status.
Export paid orders to CSV
Change prepared with permission and column checks. Review is required before merging and deployment.
acme/orders · PR #128 · export-orders-csv → mainSlackExampleexplain where the change is and what's missing to put into production.
03 · YOUR WAY OF WORKING
Fits the business you already have.
Context and tools
We start with your current documents, systems and channels. We assess feasible connections and define the permissions required for this specific task.
Improves with your feedback
Approved corrections are incorporated into instructions, examples or knowledge sources. We review changes before expanding the agent’s scope.
A clear way to evaluate
We agree on a representative sample and measure review time, errors, exceptions and output quality against the current workflow. Feasibility is decided using that evidence.
04 · COMMON QUESTIONS
Before getting started.
What information does this agent need?
Brief, authorized repository and acceptance criteria. We review quality, currency and access before connecting the workflow. You do not need to replace all your tools to begin.
What will my team receive?
Reviewable change before integration or deployment. We agree on the format and delivery channel during setup, together with cases that need review.
Which decisions remain with people?
The team retains approval over changes, merges and deployments.
Can it coordinate with other agents?
Yes. We define what this agent hands to the next one and who handles exceptions. It can interact through Slack, WhatsApp, email or Microsoft Teams, depending on the integration and permissions we configure.
INDUSTRY APPLICATIONS
Where it could fit.
RELATED AGENTS
A team that works together.
START WITH ONE TASK
How would this fit your business?
Tell us how you do it today. We will define the scope, tools and controls with you.