/ featured · this week
View all dispatches →
Orchestration architecture describes the control layer that routes specialized agents through complex business workflows. Unlike single-agent systems that execute predefined scripts, orchestration...
Aug 14, 2026/ recent · long reads
Browse long reads →
Handoffs are a discipline, not an accident. Specialized agents operate reliably in isolation, but handoffs fail in production when orchestration treats state ownership as implicit rather than...
Aug 3, 2026
Agentification maturity is not measured by agent count. Start with one high-value workflow, establish guardrails and governance early, and transition ownership to the function that runs it.
Jul 29, 2026/ selected notes
All dispatches →01 / AI Agents
An AI agent maturity model for a business team is a staged framework that ranks how much work a business can safely hand to agents, and where along that path it currently sits. Most models split the...
Jul 27, 2026
02 / AI Agents
Agent readiness is the business case for AI agents restated as a production question: can you afford the oversight, not can you afford the license. Most guides answer a different question. They walk...
Jul 27, 2026
03 / Workflows
Five words get sold as five products. They are one dial with a price on each notch, and the notch you can afford to buy is rarely the notch you can afford to supervise.
Jul 25, 2026
/ the feed · everything we've published
Orchestration architecture describes the control layer that routes specialized agents through complex business workflows. Unlike single-agent systems that execute predefined scripts, orchestration...
Kurt Fischman · Aug 14, 2026
Handoffs are a discipline, not an accident. Specialized agents operate reliably in isolation, but handoffs fail in production when orchestration treats state ownership as implicit rather than...
Kurt Fischman · Aug 3, 2026
Agentification maturity is not measured by agent count. Start with one high-value workflow, establish guardrails and governance early, and transition ownership to the function that runs it.
Kurt Fischman · Jul 29, 2026
An AI agent maturity model for a business team is a staged framework that ranks how much work a business can safely hand to agents, and where along that path it currently sits. Most models split the...
Kurt Fischman · Jul 27, 2026
Agent readiness is the business case for AI agents restated as a production question: can you afford the oversight, not can you afford the license. Most guides answer a different question. They walk...
Kurt Fischman · Jul 27, 2026
Five words get sold as five products. They are one dial with a price on each notch, and the notch you can afford to buy is rarely the notch you can afford to supervise.
Kurt Fischman · Jul 25, 2026
Seventy-five terms sounds like a lot until you notice most of them are selling you something. The market for AI agents for business is arranged as a shopping problem: ranked lists, best-of grids, a...
Kurt Fischman · Jul 22, 2026
AI agents for business get sold as a shopping problem, and the whole market is arranged to keep it that way: ranked listicles, best-of grids, a leaderboard of tools. That framing hides the actual...
Kurt Fischman · Jul 22, 2026
> An AI agent implementation playbook is the ordered sequence that moves an agent from a chosen use case to trusted, unsupervised production. Its seven stages (scope, score, design, build, evaluate,...
Kurt Fischman · Jun 22, 2026
> An AI agent risk assessment framework scores a single agent workflow on five factors (autonomy, reversibility, data sensitivity, customer impact, and auditability) to decide how much oversight it...
Kurt Fischman · Jun 22, 2026
> AI agent security is the practice of capping what a deployed agent, and anyone who hijacks it, can do to the systems and data it touches. The agent's defining flaw, that it cannot tell data from...
Kurt Fischman · Jun 22, 2026
> An AI agent governance framework is the set of runtime controls (scoped permissions, approval gates, exception queues, human review, audit trails, and a kill switch) plus the single accountable...
Kurt Fischman · Jun 22, 2026
> An AI agent ROI measurement framework separates an agent's return into four classes (cost avoidance, capacity creation, risk and quality, and revenue lift) and measures each one on the clock it...
Kurt Fischman · Jun 22, 2026
> AI agent performance metrics are the numbers a business tracks to confirm a deployed AI agent does its job correctly, safely, affordably, and fast enough to matter. Marshal sorts them into five...
Kurt Fischman · Jun 11, 2026
> AI agent evaluation is the testing discipline that decides whether an agent can be trusted to own a business workflow. It runs on three surfaces: reliability (does the agent complete the job),...
Kurt Fischman · Jun 10, 2026
> Choosing the right AI agent use case means passing each candidate workflow through three gates in order: value (is the job worth owning), risk (can the business afford the worst day), and...
Kurt Fischman · Jun 10, 2026
> AI agent use cases are business workflows an agent can own end to end, and they sort by function: sales, marketing, customer service, finance and admin, HR, and IT operations. A use case is real...
Kurt Fischman · Jun 10, 2026
> AI agents and chatbots differ by what they produce: a chatbot produces conversation, answering questions inside a contained exchange, while an AI agent produces actions, completing multi-step work...
Kurt Fischman · Jun 10, 2026
> AI agent orchestration is the coordination layer that lets multiple specialized AI agents share work, context, and handoffs on jobs too big for one agent to own. An orchestrator routes tasks,...
Kurt Fischman · Jun 10, 2026
> Designing an agentic workflow means specifying five stages in order: intake (the trigger and the inputs), reasoning (the decision and its limits), action (what the agent may write and where),...
Kurt Fischman · Jun 8, 2026
Join hundreds of small businesses operating at machine speed with agents on the job.