The Determinism Ladder: Where Enterprise Agents Need Hard Control
Agent Script in Production: State, Gates, Chains, and Proof
Multiplayer Agents Are Going Open Source. Here's What That Means for Salesforce Teams
Why Agents Fail in Production
All posts
Agent Script Best Practices: Building Agentforce Agents That Behave Like Software
Agent Script Best Practices: Building Agentforce Agents That Behave Like Software
A practical architecture guide for building reliable Agentforce agents with deterministic orchestration, bounded reasoning, explicit state, least-privilege tools, and production-grade engineering workflows.
A practical architecture guide for building reliable Agentforce agents with deterministic orchestration, bounded reasoning, explicit state, least-privilege tools, and production-grade engineering workflows.
The Determinism Ladder: Where Enterprise Agents Need Hard Control
The Determinism Ladder: Where Enterprise Agents Need Hard Control
A risk-based architecture for placing reasoning, grounding, state, actions, and Agent Script controls exactly where failure becomes expensive.
A risk-based architecture for placing reasoning, grounding, state, actions, and Agent Script controls exactly where failure becomes expensive.
Agent Script in Production: State, Gates, Chains, and Proof
Agent Script in Production: State, Gates, Chains, and Proof
A hands-on engineering guide to deterministic Agentforce workflows with explicit state, action contracts, routing gates, and testable execution paths.
A hands-on engineering guide to deterministic Agentforce workflows with explicit state, action contracts, routing gates, and testable execution paths.
Multiplayer Agents Are Going Open Source. Here's What That Means for Salesforce Teams
Multiplayer Agents Are Going Open Source. Here's What That Means for Salesforce Teams
What Y Combinator's open source agent harness gets right, and where it stops short of a Salesforce org.
What Y Combinator's open source agent harness gets right, and where it stops short of a Salesforce org.
Why Agents Fail in Production
Why Agents Fail in Production
The failure modes that never show up in a demo, and what they have in common.
The failure modes that never show up in a demo, and what they have in common.
Evaluating Agents Without a Benchmark
Evaluating Agents Without a Benchmark
How to know an agent is getting better when there is no leaderboard for your org.
How to know an agent is getting better when there is no leaderboard for your org.
The Cost of a Wrong Write
The Cost of a Wrong Write
Why confirmation gates belong on some actions and nowhere near others.
Why confirmation gates belong on some actions and nowhere near others.
Beyond the Vector DB
Beyond the Vector DB
Why retrieval quality depends more on your schema than your embedding model.
Why retrieval quality depends more on your schema than your embedding model.
The path to AGI
The path to AGI
Notes on what actually compounds in agent capability, and what does not.
Notes on what actually compounds in agent capability, and what does not.
ReAct vs Plan-and-Execute
ReAct vs Plan-and-Execute
Choosing the right agent loop for Agentforce workloads.
Choosing the right agent loop for Agentforce workloads.
TypeScript vs Python
TypeScript vs Python
Picking a runtime for agent tooling when both teams have opinions.
Picking a runtime for agent tooling when both teams have opinions.
Context Windows Are Not Memory
Context Windows Are Not Memory
A large context window solves a different problem than the one teams reach for it to solve.
A large context window solves a different problem than the one teams reach for it to solve.
Tool Design Is the Real Prompt
Tool Design Is the Real Prompt
Most agent behaviour is determined before the model reads a single instruction.
Most agent behaviour is determined before the model reads a single instruction.
The End of Prompt Engineering
The End of Prompt Engineering
Prompts are becoming interfaces. What replaces the prompt as the unit of work.
Prompts are becoming interfaces. What replaces the prompt as the unit of work.
When Not to Use an Agent
When Not to Use an Agent
A short list of problems where a flow, a formula, or a report is the better answer.
A short list of problems where a flow, a formula, or a report is the better answer.
Human in the Loop Is a Design Decision
Human in the Loop Is a Design Decision
Where to put the person, and why the default answer is usually wrong.
Where to put the person, and why the default answer is usually wrong.
Observability for Agent Systems
Observability for Agent Systems
What to log so that the question after an incident has an answer.
What to log so that the question after an incident has an answer.
Multi Agent Systems Are Usually One Agent
Multi Agent Systems Are Usually One Agent
When splitting into several agents helps, and when it is one agent with extra latency.
When splitting into several agents helps, and when it is one agent with extra latency.
Data Hygiene Is an AI Problem Now
Data Hygiene Is an AI Problem Now
The CRM cleanup nobody funded is suddenly the thing blocking the agent rollout.
The CRM cleanup nobody funded is suddenly the thing blocking the agent rollout.