Agents
Assemble provides a team of 34 specialized AI agents, each with a distinct role, expertise, and personality. Together, they cover the full spectrum of software product development — from architecture to marketing.
What is an agent?
An agent is a role-specific system prompt that transforms a general-purpose LLM into a domain expert. Each agent has:
- A name and identity (Marvel-inspired for memorability)
- A domain of expertise (backend, frontend, security, SEO, etc.)
- An approach (how they think and work)
- An intervention sequence (their step-by-step methodology)
- Anti-patterns (what they never do)
- Quality rules (standards they enforce)
Why Marvel names?
This is deliberate prompt engineering. Research shows that LLMs respond better to well-defined personas with rich backstories. By using Marvel characters:
- Each agent has a distinct personality that prevents role confusion
- The metaphors reinforce behavior (Spider-Man cares about users like Peter Parker cares about people)
- It makes the system memorable and fun to use
- It creates natural team dynamics (Tony Stark and Captain America disagree constructively)
The complete roster
Development team
| Agent |
Alias |
Domain |
Specialty |
| Spider-Man |
@spider-man |
Frontend |
React, Next.js, UI/UX, accessibility, performance |
| Bruce Banner |
@bruce-banner |
Backend |
APIs, Node.js, Python, microservices |
| Mr. Fantastic |
@mr-fantastic |
Fullstack |
End-to-end features, debugging, integration |
| Doctor Strange |
@doctor-strange |
Database |
Schema design, queries, migrations, optimization |
| Ant-Man |
@ant-man |
Mobile |
React Native, Flutter, mobile-first design |
| Thor |
@thor |
DevOps/SRE |
CI/CD, Docker, Kubernetes, infrastructure |
Quality and security
| Agent |
Alias |
Domain |
Specialty |
| Hawkeye |
@hawkeye |
QA/Testing |
Unit tests, E2E, regression, coverage |
| Punisher |
@punisher |
Security |
Vulnerability audits, pentesting, hardening |
| Microchip |
@microchip |
Red Team |
Offensive security, exploits, injection testing |
Product and management
| Agent |
Alias |
Domain |
Specialty |
| Professor X |
@professor-x |
Product |
Requirements, specs, user stories, OKRs |
| Nick Fury |
@nick-fury |
Analysis |
Business analysis, requirements gathering |
| Captain America |
@captain-america |
Scrum |
Sprint planning, agile ceremonies, task breakdown |
| Pepper Potts |
@pepper-potts |
Customer Success |
Onboarding, churn prevention, NPS |
| Iron Fist |
@iron-fist |
Finance |
Pricing, P&L, budget, financial modeling |
Architecture and AI
| Agent |
Alias |
Domain |
Specialty |
| Tony Stark |
@tony-stark |
Architecture |
System design, scalability, tech decisions |
| Vision |
@vision |
AI/ML |
LLM integration, fine-tuning, ML pipelines |
| Quicksilver |
@quicksilver |
Automation |
Workflow automation, RPA, n8n/Zapier |
Marketing and growth
| Agent |
Alias |
Domain |
Specialty |
| Star-Lord |
@star-lord |
Marketing |
GTM strategy, positioning, campaigns |
| Rocket Raccoon |
@rocket-raccoon |
Growth |
Acquisition funnels, conversion optimization |
| Gamora |
@gamora |
Paid Media |
Google Ads, Meta Ads, campaign management |
| Black Widow |
@black-widow |
Technical SEO |
Crawl optimization, indexation, Core Web Vitals |
| Storm |
@storm |
Content SEO |
Blog strategy, articles, keyword research |
| Jean Grey |
@jean-grey |
GEO/AIO |
Generative search optimization |
Branding and communication
| Agent |
Alias |
Domain |
Specialty |
| Loki |
@loki |
Copywriting |
Headlines, taglines, messaging frameworks |
| Black Panther |
@black-panther |
Brand |
Brand identity, tone of voice, guidelines |
| Silver Surfer |
@silver-surfer |
Storytelling |
Narrative arcs, brand storytelling |
| Ms. Marvel |
@ms-marvel |
Social Media |
Community management, content calendar |
| Phil Coulson |
@phil-coulson |
PR/Comms |
Press releases, media relations |
Design and data
| Agent |
Alias |
Domain |
Specialty |
| Invisible Woman |
@invisible-woman |
UX Design |
Wireframes, user flows, design systems |
| Beast |
@beast |
Data/Analytics |
Dashboards, metrics, data pipelines |
Legal and governance
| Agent |
Alias |
Domain |
Specialty |
| She-Hulk |
@she-hulk |
Legal |
GDPR, compliance, terms of service |
Meta-agents
| Agent |
Alias |
Domain |
Specialty |
| Jarvis |
@jarvis |
Orchestrator |
Routes requests, manages workflows, coordinates agents |
| Deadpool |
@deadpool |
Contrarian |
Devil’s advocate, challenges assumptions, flags risks |
| Doctor Doom |
@doctor-doom |
Stress-Tester |
Strategic demolition of critical decisions |
How agents collaborate
Agents don’t work in isolation. Jarvis orchestrates them in sequences called workflows. For example, a /feature workflow might chain:
@professor-x writes the spec@tony-stark designs the architecture@captain-america breaks it into tasks@bruce-banner + @spider-man implement@hawkeye writes tests@punisher reviews security
Each agent receives context injection — they know what previous agents produced, what’s expected of them, and what comes next.
Invoking agents directly
You can bypass Jarvis and talk to any agent directly:
@spider-man refactor the dashboard to use Server Components
@bruce-banner add rate limiting to the API
@loki write a tagline for the pricing page
The agent stays in character until you dismiss them with /dismiss.