Spurlock Studios
Contact
AI Agents

Agentic posts from Will's Journal.

These are the Agentic posts from Will's Journal — writing from this practice, not the Agentic service page.

The Agentic practice: The night shift that does not invent a price — page 4 of this archive.

Which Agentic posts are in this archive?

A violet ring. Thesis: SCOPING AGENTIC PILOT PROVES VALUE. AI Agents

Scoping an Agentic Pilot That Proves Value in Five Days

Scope a 2–6 week agent pilot as one job, real data, an evaluator, and a cage. Five days proves the spike; extra weeks buy access, labels, and a second measure.

20 MIN
A violet ring. Thesis: PIN MODEL GATE UPGRADE CATCH. AI Agents

Pin the Model, Gate the Upgrade: Catch Agent Drift Before Customers Do

Yes—pin production agents to explicit model IDs. Floating aliases change behavior with no deploy. Upgrade only through a golden-set gate you actually run.

20 MIN
Two clipped paper packets. Thesis: OBSERVABILITY AGENTS TRACES SCORES DASHBOARD. AI Agents

Observability for Agents: Traces, Scores, and the Dashboard Ops Actually Reads

Provider dashboards miss silent wrongness. Agent observability is traces with redacted tool I/O, evaluator scores, and cost — the screen ops actually reads.

18 MIN
Nested brass frames. Thesis: TOOL SCHEMAS AGENTS FOLLOW DESCRIPTIONS. AI Agents

Tool Schemas Agents Follow: Descriptions, Enums, and Killing the Omnibus Tool

Agents invent arguments when schemas are vague. Write JSON Schema like agent UX—enums, required fields, property descriptions—and kill the do_anything tool.

16 MIN
Nested brass frames. Thesis: BUILD AGENT BUILD INSTEAD. AI Agents

When Not to Build an Agent (And What to Build Instead)

Skip the agent when the path is known or criteria are mush. A workflow plus one schema-checked LLM step is the default. Build the loop only after that fails.

28 MIN
A scuffed work smartphone with a blank glowing circular button. Thesis: DURABLE AGENT RUNTIMES SURVIVE RESTARTS. AI Agents

Durable Agent Runtimes: Survive Restarts Without Calling It "Memory"

A durable agent runtime stores resume-correct execution progress outside the process so a crash or human wait continues the same named run—not a new one.

20 MIN
A cracked amber fuse. Thesis: PRE EXECUTION POLICY GATES KILL. AI Agents

Pre-Execution Policy Gates: The Kill Switch That Lives Outside the Prompt

Your agent’s kill switch is a pre-execution policy gate outside the prompt: allow, deny, or pending-approval before side effects — fail closed on outages.

16 MIN
A violet scale. Thesis: LLM AS JUDGE RELIABILITY CALIBRATE. AI Agents

LLM-as-Judge Reliability: Calibrate the Scorer Before You Trust the Score

An LLM judge is a noisy instrument, not ground truth. Calibrate against human labels, kill position and verbosity bias, re-check after model or rubric changes.

19 MIN
Amber node beads on a dark rail. Thesis: AGENT LOOP LLM WORKFLOW PICK. AI Agents

Agent Loop vs LLM-in-Workflow: Pick the Shape That Matches the Uncertainty

Most jobs need a workflow with one LLM step, not an agent loop. Use a three-tier test — certainty, branching, blast radius — then prove hybrid is enough.

18 MIN
FAQ

What should I know about this Agentic archive?

What is this Agentic archive?
These are the Agentic posts from Will's Journal — writing from this practice, not the Agentic service page.
Is this the Agentic service page?
No. This is a journal lane archive. The Agentic practice is at /agentic. The night shift that does not invent a price.