EnGenAI 
We Harnessed AI
By The Horns
So you don't have to wrangle it yourself. Here's the technology behind the machine that builds machines.
Meet Your AI Team
Five specialized agents that communicate, collaborate, and build together. Each with their own identity, skills, and behavioral constraints.
Keith
Chief Product Officer
- Product strategy & specs
- Task decomposition & delegation
- Cross-agent coordination
PROMI
Master Orchestrator
- Pipeline orchestration
- Change detection & sync
- Circuit breaker management
Sophi
Backend Engineer
- FastAPI & PostgreSQL
- Service architecture
- Database migrations & testing
Marv
Frontend Engineer
- Next.js & React Flow
- UI components & canvas
- Responsive design systems
Sage
Knowledge Keeper
- Documentation & guides
- Architecture decision records
- Knowledge graph management
Three-Layer Behavioral Steering
The only platform with multi-layer behavioral steering: a Steering Floor for org-wide inviolable policies, plus structural, prompt, and behavioral parameter layers. XML-structured templates in Layer 2 reduce prompt token usage by 15–30%.
Identity files, role constraints, team hierarchy
Task context, phase awareness, skill templates
Runtime triggers, circuit breakers, escalation
Structured Execution, Not Random Prompting
Every task follows the PREVC protocol — five phases with verification gates. Agents don't just generate. They prepare, research, execute, verify, and commit.
"Here's some code, good luck"
Structured phases with verification gates
Fine-Tune Every Agent's Model
Assign the right model to the right agent. Use premium models for architecture decisions, efficient models for documentation. Full control over performance and cost.
Assign primary + fallback models to each agent based on their role
Use premium models for critical tasks, efficient models for routine work
Intelligent LLM Routing
Best model for each task, automatically. Four routing strategies with health monitoring, automatic fallback chains, and real-time rate limiting.
Preferred provider first
Lowest cost per token
Best model capability
Fastest response time
Vetted Capabilities, Not Blind Plugins
Every skill goes through a five-stage vetting pipeline before it can be used. Parsed, audited, sandboxed, approved by a human, then published to ClawHub.
Every skill is vetted, sandboxed, and version-controlled. No blind plugin installs. No supply chain risk.
See Every Decision As It Happens
A real-time collaborative canvas powered by React Flow and real-time sync. Watch agents communicate, assign tasks, and build — all in real-time.
Your Agents Remember Everything
Three-tier memory plus Observational Memory — long conversations are automatically compressed into structured observations by the background Observer service. Nothing gets lost between sessions. Knowledge compounds.
Working Memory
Active conversation context, current task state
Vector Memory
Semantic search across project knowledge
Durable Memory
Persistent project state, decision history, audit trail
Research Once, Reuse Forever
Cache-Augmented Generation before Retrieval-Augmented Generation. Previous research is cached and reusable across all your projects.
Previous research cached — instant reuse without re-processing
Knowledge persists across projects — research once, benefit forever
Instant Deployment to Real Infrastructure
No mocking. No simulation. Code is deployed to real GKE sandbox environments for instant, production-grade testing and feedback.
No mocking. No simulation. Your code runs on real Kubernetes infrastructure — agents get instant, production-grade feedback.
Agents Cannot Merge. Only You Can.
Human-in-the-loop by design. Agents write code on branches, create pull requests, and run tests — but only you can approve and merge to production.
Built on Battle-Tested Technology
The same technology stack used by Stripe, Netflix, and Airbnb. Enterprise-grade infrastructure from day one.
Frontend
Backend
Data
Infrastructure
Agents Built for Your Organisation
Beyond the five core AI team members, configure bespoke designer agents for any domain-specific job. Start from one of four pre-built Business Process Templates (IDP, Requirements Analysis, Predictive Analytics, Dev Request Handler) or build from scratch with 9 configuration knobs. MCP Server Registry connects external tools to any agent.
- Requirements gathering specialist
- Legal contract reviewer
- Data visualisation consultant
- Compliance auditor
- Domain expert in your industry
- Identity — who the agent is
- LLM — which model powers it
- Steering — behavioural constraints
- Tools — what it can call
- Autonomy — how independently it acts
- Connectors, Knowledge, Interface, Handoff
- Describe what you need to Keith
- Keith configures all 9 knobs via API
- Your agent is live immediately
- Gets smarter with every session
- Decommission when no longer needed
The same platform intelligence that powers Keith, Sophi, and Marv is available to any agent you configure. Same memory. Same steering. Same human-in-the-loop controls.
Transparent Usage-Based Billing
Pre-paid credits with hard stop at $0. Per-model token metering. Itemized invoices. Auto top-up with safety limits. No surprise bills, ever.
- Starter, Pro, and Enterprise tiers
- Pricing coming soon
- Enterprise: contact sales
- Annual billing available
- Per-model, per-project, per-user
- Real-time credit balance
- Auto top-up (max 3/day safety)
- BYO API keys (Pro/Enterprise)
- Stripe-powered invoicing
- Per-model line items
- Tax-compliant (Stripe Tax)
- PDF download available
AI Agents That Know When to Ask for Help
Human agents are first-class citizens in EnGenAI. Seamless AI-to-human escalation with SLA enforcement, context preservation, and automatic resume.
- Humans registered as agents
- Same API, same routing
- Role-based matching (BA, legal)
- Configurable SLA windows
- Reminders at 75% elapsed
- Breach escalation to manager
- AI pauses cleanly on escalation
- Full context preserved in Redis
- AI resumes from exact point
Code With Your AI Team, Anywhere
PREVIEWVS Code extension, MCP Server Registry, and an OpenAI-compatible API — use your EnGenAI agents directly from your favourite IDE and tools. More integrations coming soon.
- Agent chat panel in sidebar
- PKCE-secured authentication
- Project sync and code actions
- Register external MCP servers
- Test connectivity and bind tools
- Any agent can use external tools
- Drop-in /v1/chat/completions
- Personal access tokens
- Works with any OpenAI client
Ready to Meet Your Team?
We're onboarding select B2B teams for early access. Tell us about your company and we'll be in touch.
Register for Early Access →