Mustafa Qureshi.ai
← Alef AI

Architecture

A request enters through an interface, the Boss Agent plans and delegates, specialists do the work using tools and memory — and a governance layer sits around all of it. This describes the system as designed; parts of it are still being built and tested.

Governance layer — wraps every step
Owner
requests · approvals
Telegram
text · voice notes
Desktop
Windows interface
Boss Agent
plan · delegate · review · report
Planner
Research
Operator
Curator
Support
Finance
Admin
Tools & desktop control
controlled input
Memory
SQLite foundation
Playbooks
19 in development
Permission-based executionOwner-only temporary accessPrompt-injection defencesPer-agent policiesAgent-level budgetsApproval requirementsSensitive-action restrictionsAudit logsBackup mechanismsEmergency stop
Request lifecycle

Nine things the Boss Agent does with every request.

  1. 01Understand the request
  2. 02Break down the task
  3. 03Assign specialist agents
  4. 04Manage dependencies
  5. 05Coordinate execution
  6. 06Collect results
  7. 07Review outputs
  8. 08Report progress
  9. 09Request approval for consequential actions
Agent roster

Every agent has a job description.

Each one is defined by four things: its responsibilities, its permissions, the policies it must follow, and how its performance is tracked. Not every agent operates fully autonomously in production.

AgentResponsibilityDefined by
Boss AgentUnderstands requests, breaks them down, assigns work, reviews results and asks for approval.role · permissions · policy · tracking
PlannerBreaks complex requests into structured plans.role · permissions · policy · tracking
ResearcherGathers and analyses information.role · permissions · policy · tracking
OperatorHandles approved computer and workflow operations.role · permissions · policy · tracking
CuratorOrganises information and knowledge.role · permissions · policy · tracking
Customer SupportSupports customer-service workflows.role · permissions · policy · tracking
FinanceAssists with finance-related business workflows.role · permissions · policy · tracking
AdministrationAssists with administrative operations.role · permissions · policy · tracking

Persistent memory

A SQLite-based foundation for structured long-term memory: retrieving relevant context, keeping task history, organising knowledge, and giving continuity across workflows so agents don't start from zero every time.

Skills & playbooks

Reusable, text-based playbooks describe research procedures, operational procedures, quality checks and execution policies. The development environment holds 19 of them — working material for the agents, not 19 validated commercial capabilities.

Next: the roadmap