Tag

ai-agents

Harness Engineering Series #7: Sandboxes, Permissions, and Failure Boundaries

A concrete operator guide to sandboxes, permissions, and failure boundaries: what changes, who owns it, how to verify it, and where it breaks.

Harness Engineering Series #10: The Harness Engineering Audit

A concrete operator guide to the harness engineering audit: what changes, who owns it, how to verify it, and where it breaks.

The AI Context Layer Series #2: Context as Infrastructure

Context becomes infrastructure when you maintain, permission, refresh, and reuse it across agent workflows.

The AI Context Layer Series #1: Agents Need a Business Model, Not Just Documents

Giving an AI agent access to documents and tools isn't enough if it still misunderstands how your business actually operates.

The AI Context Layer Series #4: Source Priority and Freshness

The context layer must determine which data source takes priority and how fresh the answer needs to be for a specific action.

The AI Context Layer Series #3: Grounding Agents in Business Objects

AI agents need structured business objects, relationships, and defined states before they need more unstructured text.

The AI Context Layer Series #7: Tool Access Needs Business Context

Without business context, AI tools will confidently execute actions against the wrong object, customer, metric, or state.

The AI Context Layer Series #6: Memory Without Stale Truth

Agent memory is only useful when it defers to current facts rather than quietly prioritizing outdated information.
You've successfully subscribed to Antoine Buteau
Great! Next, complete checkout to get full access to all premium content.
Welcome back! You've successfully signed in.
Unable to sign you in. Please try again.
Success! Your account is fully activated, you now have access to all content.
Error! Stripe checkout failed.
Success! Your billing info is updated.
Error! Billing info update failed.