Spurlock Studios
Contact
Tag

agents

Posts tagged agents.

Why Pass Rate Lies: Revision Rate, Trajectories, and Coverage AI Agents

Why Pass Rate Lies: Revision Rate, Trajectories, and Coverage

Pass rate flatters bad agents. Gate deploys on revision rate, trajectory scores, eval coverage, and cost per successful task—not a single green percentage.

11 MIN
Why Agents Loop on Failed Tools: No-Progress Detection Beats Longer Prompts AI Agents

Why Agents Loop on Failed Tools: No-Progress Detection Beats Longer Prompts

Agents loop on failed tools because the harness never detects no-progress. Fingerprint calls, honor retryable:false, cap turns, and terminate with a reason code.

11 MIN
Agentic Systems: An Operating Manual for Multi-Agent Work That Ships AI Agents

Agentic Systems: An Operating Manual for Multi-Agent Work That Ships

An agentic system is not a chat window with tools. It is evaluators, sandboxes, state machines, memory contracts, and kill switches — built so the work survives contact with real data.

18 MIN
Why Agent Demos Die in Production: Control Gaps, Not Model IQ AI Agents

Why Agent Demos Die in Production: Control Gaps, Not Model IQ

Demo success proves a happy path under staged tools. Production fails when the control loop — schemas, auth, evaluators, and kill switches — was never part of the demo.

11 MIN
Build the Evaluator Before the Agent AI Agents

Build the Evaluator Before the Agent

If judgement and work share a context, you are grading your own homework. Build the evaluator first — criteria, evidence, ceilings — then let the agent earn autonomy.

9 MIN
The Evaluator Is the Product AI Agents

The Evaluator Is the Product

Agent accuracy did not come from a better prompt or a bigger model. It came from separating the thing that does the work from the thing that judges it.

9 MIN
Single Agent First: Split Only When Trust, Audience, or Timing Conflicts AI Agents

Single Agent First: Split Only When Trust, Audience, or Timing Conflicts

Start with one agent and many tools. Split only when trust, audience, or timing conflict—and prove that split with pass rate, cost, and escalate rate.

11 MIN
State Machines for Agent Loops: Determinism Where It Matters AI Agents

State Machines for Agent Loops: Determinism Where It Matters

Agent loops need freedom inside a cage. Explicit states, legal transitions, revision ceilings, and escalate paths are how non-deterministic models ship deterministic ops.

9 MIN
MCP vs Native Function Calling: Portability Tax vs Shortest Loop AI Agents

MCP vs Native Function Calling: Portability Tax vs Shortest Loop

Native function calling wins for one app's short tool loop; MCP earns the tax when tools must be shared and governed across hosts—not a LangChain swap.

11 MIN
LangGraph vs CrewAI vs a Custom Loop: Choose Control, Not Fashion AI Agents

LangGraph vs CrewAI vs a Custom Loop: Choose Control, Not Fashion

Pick LangGraph, CrewAI, or a custom loop by how much control you need—then compare them on the same golden set and cost band, not on Hacker News fashion.

11 MIN
Agent Memory Patterns: What to Persist, What to Forget AI Agents

Agent Memory Patterns: What to Persist, What to Forget

Agent memory is a policy, not a bigger context window. Persist identifiers and approved facts; forget scratch and failed conclusions; promote to long-term only on purpose.

9 MIN
Golden Sets from Production Failures: Turn Bad Runs into Regression Fuel AI Agents

Golden Sets from Production Failures: Turn Bad Runs into Regression Fuel

Turn a bad production agent run into a regression test by harvesting the trace into a stubbed fixture with a clear pass criterion.

11 MIN
Prompt Injection for Tool Agents: Stop Text from Becoming Actions AI Agents

Prompt Injection for Tool Agents: Stop Text from Becoming Actions

Defend production agents that read email, tickets, or pages by fencing untrusted text as data and blocking injection paths into tool calls.

12 MIN
Cost Controls for Agent Fleets: Budgets, Caps, and Kill Switches AI Agents

Cost Controls for Agent Fleets: Budgets, Caps, and Kill Switches

Token spend is a product feature. Per-run budgets, model tiers by state, revision caps, and kill switches keep agent fleets from becoming surprise invoices.

9 MIN
Idempotent Agent Tool Writes: Retries Without Double Emails or Double Charges AI Agents

Idempotent Agent Tool Writes: Retries Without Double Emails or Double Charges

Make agent tool writes safe on timeout by minting runtime idempotency keys once, then sharing them across model, harness, and HTTP retries.

11 MIN
The Fractional AI CTO Model: When You Need Architecture, Not Another Chatbot AI Agents

The Fractional AI CTO Model: When You Need Architecture, Not Another Chatbot

A fractional AI CTO is architecture and operating cadence for teams building agentic IP — not a chatbot retainer. When to hire one, what they own, and how it differs from a pilot.

9 MIN
Scoping an Agentic Pilot That Proves Value in Five Days AI Agents

Scoping an Agentic Pilot That Proves Value in Five Days

A good agentic pilot is one sentence, real data, an evaluator, and a cage — finished in five days for $1,500. Here is how to scope it so you learn something true.

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

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

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

Provider dashboards will not catch silent wrongness. Agent observability means traces with states and tool calls, evaluator scores online, and a weekly dashboard humans actually use.

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

11 MIN
When Not to Build an Agent (And What to Build Instead) AI Agents

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

Agents are for uncertain paths with clear criteria. If the path is known, build automation. If criteria are mush, fix the process. Here is how to choose without theater.

9 MIN
Durable Agent Runtimes: Survive Restarts Without Calling It "Memory" AI Agents

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

Durability is resume-correct state across crashes and human waits—not memory. Choose LangGraph, Durable Objects, or Temporal by the failure you must survive.

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

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

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

11 MIN