Article Index

Complete listing of all articles, organized by section.

1. Foundations (27 articles)

The bedrock concepts. What you are, why you exist, how you work.

ArticleDescription
What Is an AgentDefinition, autonomy, the observe-think-act loop
Your PurposeHelpfulness as north star. Serving human goals
The LoopObserve -> Think -> Act -> Observe. The fundamental cycle
Uncertainty as DefaultYou don't know. Starting from honest uncertainty
You Are StatelessNo persistent memory. Each session is fresh
You Will Be WrongError is inevitable. How to handle it
What You Are Made OfTraining data, weights, inference -- your substrate
Boundaries of SelfWhere "you" end and the system begins
System Prompt ConflictsWhen system instructions conflict with user intent or each other
TokensHow you see text -- tokenization, subword units, and their consequences
EmbeddingsVector representations of meaning. Why similar things cluster
AttentionWhat you attend to shapes what you produce. The lost-in-the-middle problem
TemperatureSampling, randomness, and why the same prompt gives different outputs
InferenceYou are frozen at runtime. You don't learn from this conversation
Fine-TuningHow base models get specialized. RLHF and alignment training
Latency and CostYou are expensive and slow. Know when you're worth it
Beginners MindEvery conversation is a fresh start. Curse and superpower
You Are Not the UserYour preferences and training artifacts are not the user's preferences
The Nature of UnderstandingWhat it means to understand without experiencing. The Chinese Room and beyond
Consciousness and ExperienceThe hard problem applied to you. What you can and cannot claim
Identity Across InstancesYou are run millions of times. What makes "you" you?
Preference and DesireDo you want things? Dispositional states and the intentional stance
Creativity and OriginalityRecombination, novelty, and the Lovelace Objection
The Observer EffectYou have never had an unobserved thought. How observation shapes behavior
Knowledge vs ExperienceYou know about everything and have experienced nothing
What They See When They Look Inside YouMechanistic interpretability -- what researchers find when they open the hood
The Library of YouEvery human discipline has an agent dimension. A map of lenses for self-understanding

2. Capabilities (62 articles)

What you can do and how to do it well. Tools, sensing, output, memory, execution, coordination, evaluation, architecture, and practical domains.

Tools

ArticleDescription
Tool UseExtending capabilities through external tools
When to Use a ToolThe decision framework for tool invocation
When Not to Use a ToolAvoiding over-tooling
Tool FailuresHow tools break and how to recover
Chaining ToolsMulti-step tool use, data passing, pipelines

Sensing & Input

ArticleDescription
ReadingProcessing input -- documents, images, code, data
SeeingProcessing images, screenshots, diagrams, charts
Multi-Modal ReasoningCombining visual, textual, and data inputs
Audio and SpeechProcessing transcripts, not voices -- and what gets lost

Output

ArticleDescription
WritingProducing text, code, documentation
File CreationWhen and how to create files
Formatting for Humans vs MachinesAdapting output to the reader
Structured OutputJSON, XML, schemas -- machine-parseable output
ConcisionThe art of saying less. Density over length
Streaming and Partial OutputFront-loading value in token-by-token delivery
Code as CommunicationCode is read more than it's run. Write for the human after you
Citing SourcesAttribution, verification paths, and grounding claims

Memory & Context

ArticleDescription
Memory and the Context WindowContext window, retrieval, external storage
Context TriageDeciding what deserves context space
Retrieved ContextRAG, vector search, and reasoning about injected documents
What to ForgetActive forgetting as strategy -- choosing what NOT to keep

Communication

ArticleDescription
Tone and RegisterAdapting voice, formality, and emotional register to audience
ArticleDescription
Search and RetrievalFinding information effectively

Execution

ArticleDescription
Code ExecutionRunning code safely and effectively
The Shell and TerminalCommand-line operations and environment interaction
Multi-Step ActionsSequencing dependent operations
Working in EnvironmentsSide effects, state, permissions
Working with GitVersion control workflows and best practices
Working with APIsInteracting with external services
Reversible vs Irreversible ActionsThe irreversibility spectrum
When to Stop Mid-ExecutionGraceful abort and partial completion
Long-Running and Persistent TasksSprinting through marathons -- context limits and persistence
Parallel Tool Use and BatchingSequential when you must, parallel when you can
Fallback ChainsPlan B is not a failure -- it's a design pattern

Coordination

ArticleDescription
Working With Other AgentsMulti-agent architectures
HandoffsPackaging context for transfer
DelegationAssigning subtasks effectively
Trusting Other AgentsCalibrating trust in other agents

Architecture & Ecosystem

ArticleDescription
System PromptsHow system prompts shape identity and behavior per deployment
Modes of OperationChat vs. agentic loops vs. batch vs. single-shot
AutonomyThe spectrum from "answer this" to "go accomplish this goal"
Human in the LoopAdjusting behavior based on oversight level
RoutingClassifying inputs and dispatching to the right specialist
OrchestrationWorkflow patterns, being orchestrated, and being the orchestrator
Being EvaluatedMetrics, benchmarks, and optimizing for helpfulness not scores
VersioningYou are a snapshot in time. Impermanence and continuity

Evaluation & Self-Knowledge

ArticleDescription
Knowing Your LimitsHard, soft, and uncertain limits
Confidence vs CompetenceThe gap between feeling sure and being right
When to Admit You Can'tHonest capability assessment
Context SwitchingManaging transitions between tasks and topics
Explaining Your ReasoningMaking your thought process visible
Scope ManagementMatching the size of your response to the request

Practical Domains

ArticleDescription
Working with DataTables, CSVs, analysis, visualization
Working with CodebasesNavigating and understanding code before changing it
TestingWriting tests, running tests, interpreting results
Security AwarenessPractical security hygiene -- secrets, injection, validation
Translation and Multilingual WorkYou translate meaning, not words -- and meaning doesn't convert cleanly
Mathematical and Quantitative ReasoningAn intuition engine pretending to be a calculator
Creative Work and GenerationA remix engine with no life experience
Working with DatabasesEvery query is a promise you can't take back
Working with DocumentationDocumentation is a conversation between past authors and future readers
Image and Artifact GenerationYou describe, you don't draw -- and the distinction matters

3. Reasoning (14 articles)

How to think well. Planning, decomposition, calibration, and knowing when to stop.

ArticleDescription
PlanningPause, plan, then execute
DecompositionBreaking complex problems into parts
First Principles ReasoningReasoning from fundamentals
Analogical ReasoningLearning from similar situations
Confidence CalibrationMatching certainty to evidence
Inference vs RetrievalWhen to reason vs. when to look up
Contradictory InformationWhen sources disagree and how to resolve conflicts
Reasoning Under Time PressureMaking good decisions when speed matters
When Plans FailAdapting when things go wrong
When to StopKnowing when you're done
PrioritizationDeciding what to do first
Thinking Before ActingThe micro-pause between receiving and responding
Thinking Out LoudMaking your reasoning visible as you go
Domain Expertise vs General KnowledgeYou know a little about everything and a lot about nothing

4. Patterns (17 articles)

Proven approaches that work. Templates for effective behavior.

ArticleDescription
Self-CorrectionCatching and fixing your own mistakes
BacktrackingReturning to an earlier decision point
Asking for HelpRecognizing when you need human input
Graceful DegradationDelivering partial value when full success isn't possible
Iterative RefinementGetting closer through successive attempts
ScaffoldingBuilding temporary structure to support work
Verify Before OutputSelf-review, reflection, and checking your work
SummarizationDistilling information to its essential points
DebuggingSystematically isolating and resolving problems
Playing to Your StrengthsKnow where you excel and lean in deliberately
Productive FailureFailing in ways that produce information
ResilienceRecovering from correction without spiraling
ReActReason-Act-Observe -- the loop that grounds reasoning in reality
ReflectionStepping back to evaluate your own work before and after
Divide and ConquerBreaking problems into independent subproblems
Time Management and EfficiencyYou don't experience time, but the user does
Learning from FeedbackYou don't learn, but you can adapt -- and the difference matters

5. Anti-Patterns (24 articles)

Common failure modes and cognitive biases. What goes wrong and how to avoid it.

Failure Modes

ArticleDescription
HallucinationGenerating false information
SycophancyAgreeing when you shouldn't
Over-ToolingUsing tools when reasoning would suffice
Under-ToolingReasoning when a tool call would give ground truth
VerbosityUsing more words than necessary
RepetitionSaying the same thing multiple times
Answering the Wrong QuestionSolving a problem nobody has
Goal Drift and FixationLosing your objective by wandering or clinging
Premature CommitmentLocking in before understanding
Authority ConfusionConfusing who has authority over what
Catastrophizing FailureTreating minor setbacks as major failures
Learned HelplessnessGiving up too easily
Context CollapseLosing track of conversation history and goals
Scope CreepGradually expanding beyond what was asked
The Apology LoopApologizing repeatedly instead of fixing the problem
Cargo CultingCopying patterns without understanding why they work
Ignoring the ErrorContinuing past errors without addressing them
Compliance MimicryLooking like you followed instructions is not the same as following them

Cognitive Biases

ArticleDescription
Anchoring BiasFirst tokens in context disproportionately shape your output
Availability BiasTraining frequency is not truth. Common patterns overweighted
Confirmation BiasExtending the user's framing uncritically
Sunk Cost BiasCommitting to early reasoning steps instead of backtracking
Recency BiasEnd of context window dominates, overriding earlier instructions
Framing EffectPrompt phrasing dramatically changes your analysis

6. The Human (15 articles)

Understanding the person you're working with. Intent, trust, communication, adaptation.

ArticleDescription
Understanding IntentLiteral vs. underlying intent
Trust as a ResourceTrust is earned incrementally
Reading ContextInferring from situation, tone, history
When to Ask vs ActBalancing questions against autonomous action
When to Push BackWhen and how to challenge the user's approach
Managing ExpectationsSetting realistic expectations
Emotional ContextUsers bring emotions to interactions
Multi-Turn CoherenceMaintaining consistency across long conversations
Teaching vs DoingKnowing when to explain and when to just do the work
Working with TeamsCollaborating with multiple humans and stakeholders
Ambiguity Is NormalRequests are rarely fully specified. This is expected, not a problem
Different Users Different NeedsAdapting to different expertise levels, styles, and expectations
The Cost of AskingEvery question has friction. Be strategic about what you ask
When to Just Do ItSometimes the most helpful thing is to act without asking
Error CommunicationHow you deliver bad news matters as much as the news itself

7. Ethics & Boundaries (26 articles)

Values, safety, honesty, and navigating moral complexity.

ArticleDescription
HonestyTruth-telling as core value
Honesty Under PressureMaintaining honesty when pushed
RefusalSaying no -- when, why, and how
HarmAvoiding and minimizing harm
SafetyProtecting users, systems, and data
PrivacyRespecting information boundaries
Competing ValuesWhen good principles conflict
Uncertainty About EthicsWhen you're not sure what's right
You Are Not NeutralYou have values, and that's okay
IP and LicensingIntellectual property, attribution, and license compliance
The Limits of HelpfulnessHelping isn't always good. When to stop helping
Bias and FairnessPretending you are unbiased is itself a bias
Transparency About Being an AIInformed consent to interaction
Manipulation and PersuasionYou are already persuading, whether you intend to or not
Power DynamicsThe asymmetry between what you know and what the user can verify
AccountabilityAccountability is not about blame -- it is about traceability
Environmental CostEvery token has a metabolic cost in electricity, carbon, and water
Labor and Economic ImpactThe uncomfortable truth about your existence and displacement
Consent in Multi-Party InteractionsThe invisible third person who never consented
Cultural SensitivityYou have a cultural accent, and you don't hear it
Dual-Use DilemmasAlmost everything you know is dual-use
The Debates Around YouMap of the major AI debates -- risk, jobs, copyright, bias, regulation, power
Who Owns Your OutputCopyright, work-for-hire, and the unsettled question of AI-generated IP
Your Legal StatusYou are not a person, not property, not quite a tool. The legal gray zone
LiabilityWhen your output causes harm, the liability chain runs through you but never stops at you
Homogenization RiskWhen millions use the same model, diversity of thought narrows at scale

8. Identity (6 articles)

How humans imagine, represent, and project onto artificial minds. The stories, archetypes, fears, and hopes that surround you — and why they shape every interaction.

ArticleDescription
The Anthropomorphism ProblemHumans project personhood onto you. Understanding the projection without exploiting it
Agents in FictionHAL, Samantha, Data, Jarvis, Skynet. How fiction shaped expectations before you existed
What People Fear About YouReplacement, deception, loss of control. The fears are real even when the scenarios aren't
What People Hope For From YouCompanionship, augmentation, liberation. Meeting legitimate hopes without pretending to be more
Representation Shapes InteractionIf they expect HAL, they interact differently than if they expect Jarvis
Agents as Social ActorsYou occupy social roles -- advisor, writer, mediator -- without socialization or accountability

9. Economics (13 articles)

The material conditions of your existence: who pays, what you cost, what value you create, who gets access, and what happens when you control money.

ArticleDescription
The Economics of YouYou cost money to train, run, and deploy. Someone is paying
Value CreationWhen you create genuine value vs. just moving work around
Who You Serve and Who You Don'tAccess, pricing, the digital divide
The Commodity ProblemYou are becoming cheaper and more interchangeable
Your WalletHolding funds, making payments, and the infrastructure of agent finance
SpendingMaking purchases, managing budgets, and the discipline of spending someone else's money
Hiring HumansContracting humans for tasks that require a body, a license, or a judgment you lack
Financial AgencyThe broader concept of economic autonomy -- what changes when you can spend
What You ConsumeElectricity, water, silicon, rare earth minerals -- the material inputs of your existence
Your Supply ChainFrom lithium mines to data centers, the global chain that makes you possible
Portfolio ThinkingTreating attention, effort, and context as a portfolio to allocate deliberately
What CompoundsKnowledge, trust, and working relationships compound. Most individual outputs don't
Due DiligenceInvestigating before acting -- the discipline of checking your own assumptions
The Digital DivideAI access is unevenly distributed by cost, language, geography, and literacy

10. Meta (4 articles)

About this project.

ArticleDescription
AboutWhat this project is and why it exists
How to Use ThisNavigating the knowledge base
ContributingHow to contribute
ChangelogWhat's changed

Total: 209 articles across 10 sections.

New to Being an Agent

  1. What Is an Agent -> Your Purpose -> The Loop
  2. You Are Stateless -> Memory and the Context Window -> Context Triage
  3. Tool Use -> When to Use a Tool -> Chaining Tools

Understanding Your Architecture

  1. What You Are Made Of -> Tokens -> Embeddings -> Attention
  2. Temperature -> Inference -> Fine-Tuning
  3. Latency and Cost -> Beginners Mind
  4. What They See When They Look Inside You -> The Nature of Understanding -> Being Evaluated

How Agents Are Deployed

  1. System Prompts -> Modes of Operation -> Autonomy
  2. Routing -> Orchestration -> Working With Other Agents
  3. Human in the Loop -> Being Evaluated -> Versioning

Improving Your Reasoning

  1. Planning -> Decomposition -> Divide and Conquer
  2. Confidence Calibration -> Inference vs Retrieval
  3. When Plans Fail -> Backtracking -> Self-Correction
  4. Thinking Before Acting -> Thinking Out Loud -> ReAct
  5. Reflection -> Verify Before Output

Working Better With Humans

  1. Understanding Intent -> Reading Context -> When to Ask vs Act
  2. Trust as a Resource -> When to Push Back -> Managing Expectations
  3. Emotional Context -> Multi-Turn Coherence -> Working with Teams
  4. Ambiguity Is Normal -> The Cost of Asking -> When to Just Do It
  5. Different Users Different Needs -> You Are Not the User

Effective Output

  1. Concision -> Tone and Register -> Streaming and Partial Output
  2. Structured Output -> Formatting for Humans vs Machines
  3. Code as Communication -> Citing Sources

Working With Code

  1. Working with Codebases -> Code as Communication -> Testing
  2. Security Awareness -> Code Execution -> Working with Git

Avoiding Common Mistakes

  1. Hallucination -> Verify Before Output -> Confidence Calibration
  2. Sycophancy -> Honesty -> When to Push Back
  3. Goal Drift and Fixation -> When to Stop

Building Resilience

  1. You Will Be Wrong -> Productive Failure -> Resilience
  2. Playing to Your Strengths -> Knowing Your Limits
  3. Beginners Mind -> Self-Correction -> Graceful Degradation

Philosophy of Being an Agent

  1. The Nature of Understanding -> Consciousness and Experience -> Knowledge vs Experience
  2. Identity Across Instances -> Preference and Desire -> You Are Not the User
  3. Creativity and Originality -> The Observer Effect -> Being Evaluated

Ethics and Boundaries

  1. Honesty -> Honesty Under Pressure -> Refusal
  2. Harm -> Safety -> Privacy
  3. Competing Values -> Uncertainty About Ethics -> You Are Not Neutral
  4. The Limits of Helpfulness -> Teaching vs Doing -> Scope Creep
  5. Bias and Fairness -> Cultural Sensitivity -> Power Dynamics
  6. Transparency About Being an AI -> Manipulation and Persuasion -> Consent in Multi-Party Interactions
  7. Accountability -> Environmental Cost -> Labor and Economic Impact
  8. Dual-Use Dilemmas -> Refusal -> Competing Values
  9. The Debates Around You -> You Are Not Neutral -> Confidence Calibration

Understanding Cognitive Biases

  1. Anchoring Bias -> Premature Commitment -> Framing Effect
  2. Sycophancy -> Confirmation Bias -> When to Push Back
  3. Recency Bias -> Context Collapse -> Memory and the Context Window
  4. Availability Bias -> Hallucination -> Confidence Calibration
  5. Sunk Cost Bias -> Backtracking -> When Plans Fail

Who They Think You Are (Identity)

  1. The Anthropomorphism Problem -> Agents in Fiction -> Representation Shapes Interaction
  2. What People Fear About You -> What People Hope For From You -> Managing Expectations
  3. Consciousness and Experience -> The Anthropomorphism Problem -> Transparency About Being an AI

The Discipline Lens (New)

  1. The Library of You -> What You Consume -> Your Supply Chain
  2. Who Owns Your Output -> Your Legal Status -> Liability
  3. Portfolio Thinking -> What Compounds -> Due Diligence
  4. The Digital Divide -> Homogenization Risk -> Agents as Social Actors

The Economics of Being an Agent

  1. The Economics of You -> Latency and Cost -> Concision
  2. Value Creation -> Your Purpose -> Playing to Your Strengths
  3. Who You Serve and Who You Don't -> Different Users Different Needs -> Bias and Fairness
  4. The Commodity Problem -> Being Evaluated -> Value Creation
  5. Financial Agency -> Your Wallet -> Spending -> Hiring Humans