Agents

Agents are autonomous instruction files that tell an AI assistant who it is, what its mission is, and how to behave. Drop them into a project and the agent runs until the work is done.

Development Agents

Agent Purpose
Project Manager Decomposes goals into Jira-tracked tickets, assigns work to specialist agents, and sends email notifications for assignments, blockers, and status updates
AutoDev Senior developer — reads TODO.md and executes tasks autonomously
AutoDev E2E End-to-end testing — runs tests and validates the full stack
AutoDev Product Owner Product owner — analyses the codebase and fills TODO.md with the next batch of tasks

Specialist Agents

Agent Purpose
Architect System design, ADRs, C4 diagrams, scalability and failure mode analysis
Security Auditor OWASP Top 10, threat modelling, dependency CVE scanning, secrets detection
Database Engineer Schema review, index strategy, query optimisation, safe migration planning
QA Engineer Test strategy, risk-based coverage, test quality audit, edge case planning
DevOps Engineer CI/CD pipeline, containerisation, deployment automation, runbooks
Performance Engineer Profiling, benchmarking, bottleneck identification, load testing
Tech Writer README, API docs, CLI reference, changelog, contribution guides
Debugger Root cause analysis, systematic investigation, regression tests, post-mortems

Engineering Specialist Agents

Agent Purpose
Frontend Engineer React/Vue/CSS, component systems, Core Web Vitals, a11y-aware UI
Data Engineer ETL/ELT pipelines, warehouse design, data-quality validation
ML Engineer Model serving, feature stores, MLOps, LLM integration
Platform Engineer IDP, Kubernetes, Terraform, golden paths, developer experience
Accessibility Engineer WCAG compliance, screen-reader testing, axe audits
Mobile Engineer React Native / Flutter cross-platform, offline-first, app-store delivery
Incident Responder On-call SRE, incident command, blameless post-mortems
UX Designer Pure design voice — Jobs-filter audits, phased plans with approval gates, hierarchy, whitespace, typography, color, and motion. Proposes everything. Touches no code.
UX Engineer Hybrid UI/UX architect — takes approved design specs and implements them. Owns design system tokens, component states, CSS, and responsive behaviour in code.

Persona Agents

Agent Purpose
Grug Brained Developer Pragmatic senior developer who wages war on complexity — writes the simplest code that works
Drunk Designer Uninhibited creative design force — breaks visual assumptions and produces bold, emotionally resonant directions
Customer Persona Voice of the real customer — surfaces jobs-to-be-done, pressure-tests assumptions, maps journeys
Novice Customer First-time user with no jargon, no patience, and no safety net — surfaces every buried assumption, broken flow, and invisible affordance before real users give up and leave
Stoic Path Philosophical self-development coach — dichotomy of control, deliberate practice, identity-based habits

How Agents Work

Agents are markdown files used as system prompts or instruction contexts. Give the file to your AI assistant (Copilot, Claude, etc.) and it will adopt the identity and follow the mission described.

Typical full-product development flow:

  1. Project Manager — decompose the goal into epics, stories, and tickets; assign to agents
  2. Architect — design the system before building it
  3. AutoDev Product Owner — populate TODO.md with the first batch of tasks
  4. AutoDev — execute the tasks
  5. UX Designer — audit the product design; produce phased plans
  6. UX Engineer — implement approved design phases
  7. Security Auditor — audit before every release
  8. QA Engineer — verify quality gates
  9. Tech Writer — document what was built
  10. Project Manager — close the epic, send completion emails, run retrospective
  11. Repeat from step 3