Content based on claude.ai features as of June 2026 · Anthropic Claude Associate Blueprint v1.3

D1 Description D2 Discernment D3 Diligence D4 Delegation
1
Module 1

Product & Model Selection

The Four Decisions — set before the first prompt
Entry Points
Chat
One-off interactions. No persistent context. Best for exploratory tasks.
Projects
Recurs + stable context + consistent format (2 of 3). Persistent workspace.
Artifacts
Deliverable as a separate editable block — documents, reports, code.
Research
Deep multi-source synthesis. Paid plans. For current, multi-source investigations.
4-Layer Capability Model
Projects
Carry context — standing instructions + knowledge base + conversation history
Skills
Define procedures — account level, reusable, invoked automatically
Code Exec
Verify computations — sandboxed, returns a guaranteed correct result
Memory
Persist continuity — facts that carry forward, Project-scoped for isolation
Model Selection
TierWhen to use
HaikuHigh-volume, structured, clear rubric. Speed + cost efficiency compound.
SonnetDefault for professional work: drafting, synthesis, analysis.
OpusComplex judgment, ambiguous multi-layered inputs, high-stakes quality.
Context Degradation — 3 Responses
Restart
·
Summarise
·
Persist to Memory
Project Test: Build a Project when 2 of 3 apply: task recurs · stable context · consistent format. Model tier and time spent are NOT criteria.
2
Module 2

Prompting & Task Execution

The 5-Component Stack — Description competency
The 5-Component Prompt Stack
Role
Vocabulary, depth, assumptions — e.g. "as a financial analyst"
Context
Background Claude cannot infer: audience, situation, prior decisions, source material. Most often missing.
Task
The specific action with one primary verb
Constraints
Boundaries: length, tone, inclusions, exclusions
Format
Shape of result: table, list, memo, email
Diagnostic Iteration
SymptomRoot CauseFix
Generic / off-baseThin ContextAdd background
Wrong question answeredAmbiguous Task verbSharpen instruction
Wrong length / tone / shapeMissing Constraint or FormatAdd it
Close but one section offPartial gapIterate that section only
Strategy by Task Type
TypeTightenLoosen
AnalysisCriteria, standards, scopePhrasing
ResearchQuestion, sources, citationsSynthesis approach
DraftingAudience, tone, formatWord choice
BrainstormingGoal + guardrails onlyQuantity and direction
Change ONE component per iteration. Stop when further rounds produce marginal change — diminishing returns is the signal to stop.
3
Module 3

Evaluating & Validating Output

Discernment + Diligence — you own what you ship
5 Behavioral Properties of Claude
  • Responses vary — probability-based, not deterministic
  • Confident tone ≠ accuracy — fluency is uniform regardless of correctness
  • Context is a budget — degrades as sessions grow long
  • Knowledge has a training cutoff — post-cutoff needs a live source
  • Configured procedures still vary — Skills reduce, not eliminate variance
7 Hallucination Types
High risk
Fabricated specifics — precise-looking stats or citations that don't exist. The precision is the tell.
High risk
Capability hallucination — claims to have taken an external action it didn't.
Watch for
Completeness failure — confident summary masking silence on missing data.
Watch for
Confirmation bias — output frames evidence to support the premise.
Common
Plausible-but-unsupported claims · Confident tone masking uncertainty · Internal contradictions (long outputs)
4 Risk Thresholds (Diligence)
Stakes
Cost if wrong?
Reversibility
Can it be undone?
Audience
Who sees it?
Regulatory
Does a rule govern this?
4
Module 4

Workflow Integration & Solution Design

Delegation mapping — Delegation competency
Delegation Mapping — 3 Criteria
Reversibility
Can this step be undone if the output is wrong?
Stakes
What is the cost of an error at this step?
Accountability
Who is answerable? Accountability does not delegate.
3 Step Classifications
ClassificationProfileExample
AI-appropriateReversible, low stakes, mechanicalExtract clauses, classify tickets
CollaborativeAI drafts, human judges. Gate must be real.Draft redline → lawyer reviews
Human-retainedIrreversible, accountability-bearingApprove/reject, sign and send
3 Common Mapping Errors
  • Halo delegation — prior step went well → next step auto-delegated
  • Collapsing collaborative — 'AI drafts, human reviews' → review gate never staffed
  • Mapping the tool — building around features you like, not actual step risk
Escalation signal: When people rely on a Claude-built artifact as infrastructure → escalate to Developer or Architect. Prompt-and-iterate has run its course.
5
Module 5

Configuration & Knowledge Management

The right home for each type of content
4 Configuration Mechanisms
MechanismWhat goes hereWhere it lives
Standing InstructionsBehaviour rules: tone, format defaults, verification habitsInside a Project
Knowledge BaseFacts, reference documents, policiesInside a Project
SkillsRepeatable multi-step proceduresAccount level — reusable across all Projects
Scoped MemoryEvolving project state: decisions, stakeholder namesProject-isolated
Instruction Precision Test
Vague (fails silently)
"Make the reports good and accurate."
Two people read it differently.
Precise (changes output)
"For every figure, state its source. Mark unverified figures. Lead with a one-sentence headline."
Routing Rule
Rule → Instruction
·
Reference → Knowledge Base
·
Procedure → Skill
Monthly maintenance cadence. Waiting until output quality drops means drift has already reached deliverables. 'It used to work' = stale config.
6
Module 6

Governance, Risk & Responsible Use

Daily practice — not just audit checkboxes
3 Use-Case Classifications
Fully appropriate
Internal FAQ from approved docs, public summaries, formatting tasks
With review
Candidate screening, customer responses, analysis feeding decisions. Requires a defined gate.
Inappropriate
Final medical/legal determinations, unreviewed eligibility decisions, autonomous external actions
Data Sensitivity — Green / Yellow / Red
Green
Published material, anonymised data, cleared internal docs. Safe to use.
Yellow
Internal docs not meant to leave the company, named individuals, unreleased material. Review first.
Red
Regulated data (health/financial/gov), credentials, third-party confidentiality. Stop and escalate.
Skill Trust — 3 Checks
  • Source: Who published it? Unknown = escalate to org review
  • Reach: What does it inherit? Skills get full session access — not just the task scope
  • Appropriateness: Right tool? Or more capability than the task needs?
Incognito ≠ compliance. Incognito controls persistence only. It does not override org data retention. It does not make red-tier data safe to upload.
7
Module 7

Troubleshooting & Optimization

Cheapest fix first — step 5 is last, never first
4 Root-Cause Failure Patterns
PatternSignalFix
Under-specificationWrong on first responseAdd missing component(s)
Context overloadDegrades over time in sessionRestart or summarise
Wrong feature/modelSpecific, repeatable error typeUse the right tool
Stale configuration"It used to work"Run M5 maintenance checklist
Diagnostic Sequence — Cheapest First
  1. Re-read prompt vs. 5 components: under-specified?
  2. Check conversation length: context overloaded?
  3. Check feature and model: needs Code Execution? Wrong tier?
  4. Check configuration: instructions, knowledge, Skills current?
  5. Question whether the task is a fit at all (last resort)
3 Friction Signals → Fixes
Repetition
Same paste every run → saved context or standing instruction
Correction
Same flaw every output → configuration change
Variance
Different results, same task → shared Skill or knowledge base
Capture the fix: phrasing that works → standing instruction. Multi-step fix → Skill. Leaving it in a one-off chat means rediscovering it every cycle.
8
Module 8

Course Summary & Next Steps

The arc — and where Associate scope ends
AI Fluency Framework — 4 Competencies
D1

Description — Telling Claude precisely what you want. Prompting discipline.

D2

Discernment — Critically evaluating output against requirements, sources, standards.

D3

Diligence — Owning and verifying output. Accountability does not delegate.

D4

Delegation — Deciding which steps Claude does, which stay human, which are collaborative.

The 7-Module Arc
Each skill assumes the one before it.
M1 Selection
M2 Prompting
M3 Evaluation
M4 Integration
M5 Configuration
M6 Governance
M7 Troubleshooting
Certification Boundary
Associate
Individual practitioner. Prompt-and-iterate. This course.
Developer
API, SDKs, agents, tool development. Escalate when prompt-and-iterate is insufficient.
Architect
Enterprise architecture, integration design, governance at scale.
Recognising the Associate/Developer boundary and escalating across it is itself an Associate-level skill.