Skip to main content

Field notes

Notes from the field

What we learn designing and deploying AI automations: what carries work, what stalls, and why.

Intelligent Document Processing Without the Enterprise Suite
AI AutomationWorkflow AutomationProcess Automation
Intelligent Document Processing Without the Enterprise Suite
A document arrives and the automation reads it into a structured record with named fields. What that record carries, and where extraction goes wrong.
9/10/2026
7 min read
Human-in-the-Loop AI: Which Steps Wait for a Person
AI AutomationAI GovernanceWorkflow Automation
Human-in-the-Loop AI: Which Steps Wait for a Person
In a deployed automation every step either runs and reports or waits for a named person. Human-in-the-loop is the decision about where that gate sits.
9/10/2026
7 min read
EU AI Act Compliance Timeline: What to Stand Up Before December 2027
AI GovernanceEU AI ActAI Compliance
EU AI Act Compliance Timeline: What to Stand Up Before December 2027
The EU AI Act's high-risk obligations apply from December 2027. The record they require is retrospective, so the program has to run in 2026.
9/10/2026
10 min read
Autonomous AI Agents: Autonomy Is a Dial, Not a Switch
Agentic AIAI AgentsAI Strategy
Autonomous AI Agents: Autonomy Is a Dial, Not a Switch
An autonomous AI agent carries work from trigger to done without a person starting each step. What autonomy means, and where it has to stop.
9/10/2026
6 min read
What Is an Agentic Workflow? A Working Definition and a Field Test
Agentic WorkflowAgentic AIAI Agents
What Is an Agentic Workflow? A Working Definition and a Field Test
An agentic workflow lets a model choose the next step instead of following a fixed sequence. A working definition, the anatomy, and a five-question test.
7/20/2026
6 min read
What Is AI Automation? The Definition We Build Against
AI AutomationWorkflow AutomationDefinitions
What Is AI Automation? The Definition We Build Against
AI automation is software that carries work from trigger to done, with a model handling the judgment steps. The definition, its boundaries, and examples.
7/20/2026
5 min read
The Private LLM Option: What Running AI on Your Own Hardware Actually Takes
Private LLMSelf-Hosted LLMOpen-Source Models
The Private LLM Option: What Running AI on Your Own Hardware Actually Takes
Private LLMs are practical now. What a self-hosted model can and cannot do, what the hardware really costs, and when the API is still the right call.
7/20/2026
7 min read
AI Automation Tools Are Not AI Automation
AI Automation ToolsBuild vs BuyImplementation
AI Automation Tools Are Not AI Automation
The tool list is the easy part. Why a stack of AI automation tools doesn't automate anything by itself, and what turns tools into work that runs.
7/20/2026
5 min read
Why Your AI Needs Rules: Bridging the Gap Between Deterministic and Probabilistic Reasoning
AI StrategyAI GovernanceAI Architecture
Why Your AI Needs Rules: Bridging the Gap Between Deterministic and Probabilistic Reasoning
The future of software is hybrid: deterministic rules around probabilistic cores. A guide for architects moving from rigid code to fluid patterns.
2/23/2026
7 min read
Boutique AI Consulting vs. Large Firms: What Mid-Market Companies Should Know
AI StrategyBusiness StrategyBest Practices
Boutique AI Consulting vs. Large Firms: What Mid-Market Companies Should Know
Most AI projects fail. What drives AI success for mid-market companies choosing between a boutique AI shop and a large firm, and it is not brand or team size.
2/18/2026
9 min read
Can You Beat My Dog at Chess? What Games Reveal About AI Agent Performance
Agentic SystemsAI StrategyLLMs
Can You Beat My Dog at Chess? What Games Reveal About AI Agent Performance
Ten browser games built entirely by AI agents, logic, UI, and opponent rules included. A fun experiment that became the most honest AI evaluation we have run.
2/7/2026
12 min read
The 95% Problem: Why Your AI Pilot Succeeds But Never Scales
AI StrategyImplementationScaling
The 95% Problem: Why Your AI Pilot Succeeds But Never Scales
95% of AI pilots and proofs of concept never scale. The three gaps that stop them, and a practical framework for moving from experiment to production.
2/1/2026
8 min read
What 'Agentic' Really Means for Your Business
AIAgentic SystemsAutomation
What 'Agentic' Really Means for Your Business
Cut through the agentic AI hype. What autonomous AI agents and agentic workflows actually do, when they're ready for business, and how to evaluate them.
1/29/2026
7 min read
Shadow AI in Your Company: The Hidden Security Risk No One's Talking About
Shadow AISecurityCompliance
Shadow AI in Your Company: The Hidden Security Risk No One's Talking About
67% of employees use unauthorized AI tools. Detect shadow AI, assess risks, and build governance that enables innovation safely.
1/23/2026
12 min read
The Intake-to-Action Loop: Automate the Gap Between Intent and Execution
AI StrategyWorkflow AutomationBusiness Operations
The Intake-to-Action Loop: Automate the Gap Between Intent and Execution
Most companies leave hours or days between receiving a request and acting on it. Here's how to automate the distance between customer intent and fulfillment.
1/13/2026
8 min read