LLM Development Guide
LLM Development Guide
A practical, trust-first workflow for planning, prompting, executing, and reviewing LLM-assisted development.
Agents
27 posts tagged “agents”
Agent systems become production systems the moment they can call tools. This tag groups posts on building agents that keep working under load and under adversarial inputs.
Start here:
LLM Development Guide
Chapter 16: Worked Example: Converting an Ansible Playbook to a Go Temporal Workflow
An end-to-end example of migrating a procedural runbook to a durable Temporal workflow using reference implementations, phased prompts, and verification.
Cruvero - AI Agent Ecosystem Platform
A production-grade, Temporal-native AI agent orchestration platform in Go: durable multi-agent workflows, governance, MCP integration, and an operational UI.
LLM Development Guide
Chapter 15: Worked Example: Creating a Helm Chart From a Reference Chart
An end-to-end example of the workflow: plan, prompt docs, work notes, execution loop, and verification to create a new Helm chart from a known-good reference.
LLM Development Guide
Chapter 14: Building a Prompt Library: Governance + Quality Bar
How to build and maintain a team prompt library that stays useful: structure, templates, contribution rules, and governance.
LLM Development Guide
Chapter 13: Templates + Checklists: The Copy/Paste Kit
Minimal templates for plans, prompts, work notes, and checklists. Copy, adapt, and keep the workflow consistent.
LLM Development Guide
Chapter 12: Team Collaboration: Handoffs, Shared Prompts, and Review
How to make LLM-assisted development work on a team: handoff artifacts, shared prompt libraries, and review discipline.
LLM Development Guide
Chapter 11: Measuring Success: Solo + Team Metrics Without Fake Precision
How to measure whether LLM-assisted development is actually helping: practical metrics, baselines, and lightweight reporting.
LLM Development Guide
Chapter 10: Stop Rules + Pitfalls: When to Upgrade, Bail, or Go Manual
Concrete stop rules for LLM-assisted development, plus common pitfalls and a recovery checklist when things go sideways.
PinnedGo + AI in Production
MCP Servers in Production: Hardening, Backpressure, and Observability (Go)
A production-first guide to running Model Context Protocol servers safely: threat modeling, input validation, budgets, rate limits, and telemetry, implemented with Go patterns.
LLM Development Guide
Chapter 9: Security & Sensitive Data: Sanitize, Don't Paste Secrets
Practical data-handling rules for LLM-assisted development: what never to paste, how to sanitize, and how to verify you didn't leak secrets.
LLM Development Guide
Chapter 8: Choosing the Right Model: Capability Tiers, Not Hype
Model choice is an engineering decision: match capability to task complexity, upgrade when stuck, and avoid stale vendor claims.
LLM Development Guide
Chapter 7: Large Projects with Phase Documents + Implementation Prompts
An example-heavy pattern for multi-week LLM-assisted work: phase specifications, implementation prompt documents, and strict execution gates.
LLM Development Guide
Chapter 6: Scaling the Workflow: Phases, Parallelism, Hygiene
How to scale LLM-assisted development from a 1-day task to multi-week work: sub-phasing, parallelization, and repo hygiene.
LLM Development Guide
Chapter 5: The Execution Loop: Review Discipline + Commit Discipline
A repeatable execution loop for LLM-assisted work: implement small units, update notes, verify, and commit (without batching).
LLM Development Guide
Chapter 4: Work Notes: External Memory + Running Log
How to preserve state across LLM sessions with work notes: decisions, assumptions, open questions, session logs, and commit links.
LLM Development Guide
Chapter 3: Prompt Documents: Prompts That Survive Sessions
Turn your plan into reusable prompt docs: phase-aligned prompts with constraints, deliverables, session management, and verification.
LLM Development Guide
Chapter 2: Planning: Plan Artifacts, Constraints, Definition of Done
How to turn vague work into a phased plan that an LLM can execute safely: goals, constraints, references, verification, and stop rules.
PinnedLLM Development Guide
Chapter 1: A Practical Workflow for LLM-Assisted Development That Doesn't Collapse After Day 2
A trust-first, executable loop for LLM-assisted development: plan artifacts, prompt docs, work notes, verification, and commit discipline (with a worked example).
Production Systems
Agent Observability That Doesn't Lie
Tracing decisions, tool calls, cost, and side effects across an agent system - without turning logs into a data leak.
Production Systems
Cost Is a Reliability Problem
Budgets, quotas, and circuit breakers for LLM systems - because runaway cost is just an outage where the failure mode is billing.
Production Systems
Durable Agents with Temporal: Retries, Idempotency, and Long-Running State
Most agent demos assume perfect networks and short runs. Production agents need durable execution: retries, idempotency, replay, and human-in-the-loop - without losing state.
Production Systems
Evals for Tool-Using Agents: Regression Tests Beyond Prompts
If your eval can't fail when a tool breaks, it's not an eval. Here's how to test tool selection, arguments, side effects, and safety - without flaky 'vibe checks.'
Production Systems
From Stdio to Enterprise: The MCP Gateway Pattern
When MCP outgrows local stdio servers, you need a gateway: auth, tenancy, quotas, routing, audit, and safe tool contracts - without killing developer velocity.
Production Systems
Tool Discovery at Scale: Solving the Million Tool Problem
Once you have dozens (or hundreds) of tools, 'just include all schemas' stops working. Here's a production-first playbook for tool discovery, ranking, and safe invocation.
Production Systems
The Real Security Model for Agents
Prompt injection is real - but it's not just an LLM problem. Secure agents by securing tools, secrets, egress, and outputs with a zero-trust contract.
Go MCP Server Ecosystem
Production-grade MCP servers in Go that expose iCloud, Todoist, and Notion as safe, typed tools for LLM agents.
No posts match your search.