Agentic
The Conductor Prompt: Ten Specialist Roles, Five Workers in Flight
A catalog, a task packet, and a fail-closed ledger, not a project-manager persona
Brian Gagne
How to use AI at work
The exact prompt, why it works, and when it won't
Every guide shows the prompt and why it works, so you can adapt it to your job. New to AI? Pick the track for your role. Already prompting? Skip ahead to agents and security.
SYSTEM:
You classify customer support tickets. Return only JSON matching:
{"label": "billing" | "technical" | "account", "confidence": number 0-1, "reasoning": string}
Labels:
billing: charges, invoices, payments
technical: product not working as expected
account: access, password, profile, subscription state
Choose the label the ticket primarily concerns. When ambiguous, prefer the
category that describes what the user wants to happen, not what caused the
problem. Include a one-sentence reason.
USER:
{ticket_text}Newest
What do you want to get better at?
Five subjects, from writing a better prompt to keeping an agent from being tricked. If AI is new to you, begin with Start here.
Newest in each pillar
Chain-of-thought, few-shot, structured output, meta-prompting.
Multi-step chains, tool use, orchestration, feedback loops.
Injection defense, red/blue team, threat analysis.
Code gen, debugging, tests, CI: prompts that ship code.
Healthcare, finance, legal, marketing by role.
Hear about new guides, or ask a question
There's no newsletter yet. Until there is, here's how to hear about new guides and ask questions.
RSS feed
Every new guide lands in your feed reader, with nothing to sign up for.
Subscribe with RSSDiscord
Ask a question, or share a prompt that worked for you.
Join the DiscordEmail
Stuck on a prompt, or want a guide on something? Write in. A person reads every message.
[email protected]
No newsletter signup yet. When there is one, it will be right here.
Playbooks
One job, start to finish: what you need first, each prompt in order, and what you end up with.
- Techniques
Build a Classification Prompt That Beats Fine-Tuning
A production-ready classification prompt for your own labels, with self-consistency voting, structured output, and an eval harness, with 90%+ accuracy as the target and no fine-tuning.
- Applied
Build a RAG Eval Harness That Catches Regressions
A repeatable test suite measuring faithfulness, answer relevance, and context precision across 50-200 Q&A pairs. Ship gates on it; your RAG quality stops being vibes-based and becomes observable.
- Security
Prompt Injection Test Suite for Production Agents
A regression-runnable suite of 40+ injection probes that catches the classes of attacks your agent will actually face. Run nightly, track pass rate per prompt/model version, catch regressions before users do.
- Agentic
Supervisor-Worker Agent Pattern for Cost Optimization
Cut agent costs by routing cheap sub-tasks to Haiku-class models and reserving the frontier for planning. Includes a full Python reference implementation, cost accounting, and the fallback logic.
- Development
Token Budget & Cost Estimator for Production LLM Apps
A pre-flight cost calculator that tells you, before you call, how many tokens a given prompt + expected response will burn, across multiple models, so your app can choose the cheapest model that fits the window.
Look up a word or a topic
Plain definitions from the glossary, each with a prompt to try and when not to use it, plus the topics we write about most.
Rather have someone set it up for you?
That's a fair call. LTFI, the agentic business operating system from Kief Studio, can set up the work these guides describe and run it with you. No website yet? Kief Studio will build you one for free.
More recent guides
TechniquesGrounding Prompts With Retrieved Context: The RAG Prompt Patterns That Stop Invented Answers
Stop bolting retrieval onto bad prompts. Design prompts that actually use retrieved context correctly
Brian Gagne
AgenticYour Agent Skips Step 3 Every Time: Stop Describing Your Procedure and Verify Its Trace Instead
Turn your workflow's "always do X before Y" rules into machine-checkable invariants that catch out-of-order tool calls before they cause damage.
Brian Gagne
TechniquesGPT-5.6 Pays You to Delete Your System Prompt: State Every Rule Once and Stop Repeating Yourself
OpenAI's own tests show trimming duplicated instructions raises scores 10-15% while cutting tokens up to 66%. Your old scaffolding is now a tax.
Brian Gagne
AgenticMagentic Just Hit 1.0, and Your Whole Agent Team Lives or Dies by the Manager's Ledger Prompt
Microsoft Agent Framework's magentic pattern lets a manager invent the workflow at runtime. Here's the ledger prompt that makes it converge instead of loop forever.
Brian Gagne
TechniquesChain-of-Thought Is Sabotaging Your Model's Sense of Direction: Prompt Grids as Symbols, Not Sentences
Seventeen models, thirteen spatial benchmarks, one verdict: "think step by step" makes maps, mazes, and layouts worse. Here's what to send instead.
Brian Gagne
AgenticYour Agent's 'Done' Is a Lie: Gate Completion on Disk Evidence, Not Its Final Message
Steal the validation-gated completion pattern from July 2026's Paper-replication skill and make every agent attach a receipt before it stops.
Brian Gagne
AgenticYour Agent's Planner Is Fine. Its Aggregator Is What's Broken
ROMA hit state-of-the-art on SealQA by compressing every subtask tree before it bubbles up. Here are the four node prompts you can copy without adopting the framework.
Brian Gagne
TechniquesStop Trusting Free-Form Chain-of-Thought. Make Your Model Sign a Logical Certificate Instead
Meta's semi-formal reasoning template forces premises, traced paths, and a derived conclusion, so you can see exactly where the model is bluffing.
Brian Gagne