---
title: "Foundations · concept · Agentic Atlas"
description: "Foundations: the ideas every other pattern assumes, and the test for what belongs here."
canonical: "https://agentic-atlas.dev/nodes/foundations"
last-updated: "2026-09-23"
---

1. [Agentic Atlas](https://agentic-atlas.dev/)
2. [Patterns in the Agentic Atlas](https://agentic-atlas.dev/atlas)
3. Foundations

Parent of [Baseline Skill](https://agentic-atlas.dev/nodes/baseline-skill), [The Contract](https://agentic-atlas.dev/nodes/contract-documentation), [The Contract Keystone](https://agentic-atlas.dev/nodes/the-contract-keystone), [LLM Dispatch](https://agentic-atlas.dev/nodes/llm-dispatch), [Statelessness](https://agentic-atlas.dev/nodes/statelessness), [Effect Discipline](https://agentic-atlas.dev/nodes/effect-discipline), [Verification Asymmetry](https://agentic-atlas.dev/nodes/verification-asymmetry).

1. concept
   # Foundations
   **What do you need before designing an agent workflow?**
   Agent design rests on the baseline skill, two primitives, contracts and dispatch, and three premises: statelessness, effect discipline, and verification asymmetry.
   Hook
   the ideas every other pattern assumes, and the test for what belongs here
   Laws & fences
   - A topic belongs here only if applying the other pattern families properly requires understanding it.
   - Foundations never admits material just because it fits nowhere else.
   - A skill trades a name slot, standing attention, and upkeep for a reusable, discoverable, callable handle.
   - An unheld premise makes the pattern families built on it fail silently.
   When to reach
   - Reach for this when a design treats the model as remembering past calls or a documented contract as enforced.
   - Reach for this when stacked verifiers add failures, or discarded runs still leave changes behind.
   - For costs, design moves, or storage and staging mechanics, look in other nodes, not here.
   Provenance
   [foundations/model-and-claims](https://agentic-atlas.dev/nodes/foundations#model-and-claims) · v1.0.11
   Addresses
   atlas_cards foundations
2. [Baseline Skill](https://agentic-atlas.dev/nodes/baseline-skill)
3. [LLM Dispatch](https://agentic-atlas.dev/nodes/llm-dispatch)
4. [The Contract](https://agentic-atlas.dev/nodes/contract-documentation)
5. [The Context Economy](https://agentic-atlas.dev/nodes/context-economy)
6. [Statelessness](https://agentic-atlas.dev/nodes/statelessness)
7. [Effect Discipline](https://agentic-atlas.dev/nodes/effect-discipline)
8. [Verification Asymmetry](https://agentic-atlas.dev/nodes/verification-asymmetry)
9. [The Contract Keystone](https://agentic-atlas.dev/nodes/the-contract-keystone)
10. field notes
    - “the altitude above the single skill (N skills, compounding costs)”

Verification AsymmetryThe Contract Keystone unfold the map fold the map

The card, in place · its connections drawn edges from atlas_links foundations

On this plate

[why-it-matters](https://agentic-atlas.dev/nodes/foundations#why-it-matters) [definition](https://agentic-atlas.dev/nodes/foundations#definition) [model-and-claims](https://agentic-atlas.dev/nodes/foundations#model-and-claims) [scope-and-boundaries](https://agentic-atlas.dev/nodes/foundations#scope-and-boundaries) [implications-the-consequence-map](https://agentic-atlas.dev/nodes/foundations#implications-the-consequence-map) [evidence-the-test-s-track-record](https://agentic-atlas.dev/nodes/foundations#evidence-the-test-s-track-record) [relationships](https://agentic-atlas.dev/nodes/foundations#relationships) [lineage](https://agentic-atlas.dev/nodes/foundations#lineage) [relationships-ledger](https://agentic-atlas.dev/nodes/foundations#relationships-ledger)

Every section is addressable on its own. Read only the ground you need.

## Why it matters

[Permalink to Why it matters section](https://agentic-atlas.dev/nodes/foundations#why-it-matters)

Two problems, one family.

Every move you make in an agentic design presupposes facts it never argues: what a [skill](https://agentic-atlas.dev/glossary/skill) minimally *is*, that the model holds nothing between calls, that a documented [contract](https://agentic-atlas.dev/glossary/contract) is persuasion rather than enforcement, that checking a result is cheaper than producing it, that a discarded run must not have changed the world. Left unstated, the presuppositions fail silently — designs inherit the stateful-colleague error, verifiers stack failure instead of compounding reliability, "discard" quietly means "keep the mess."

And *foundations* is a word that attracts everything that feels basic. Without an admission rule the set decays into a junk drawer — the residual home for material that merely lacked a better one — and a junk drawer tells you nothing about what a design actually has to hold.

## Definition

[Permalink to Definition section](https://agentic-atlas.dev/nodes/foundations#definition)

### The prerequisite residence test *(settled 2026-07-05)*

A node lives in Foundations **iff understanding it is required to properly apply the other families.** Two corollaries:

- **The residual clause is rejected.** "Baseline info that doesn't fit elsewhere" is the junk-drawer test, not this one. Load-bearing content that fails the prerequisite test belongs *inside the node that owns it*, never here. *(First eviction: the shared-workspace stub — its channel amendment dissolved into [LLM Dispatch](https://agentic-atlas.dev/nodes/llm-dispatch), its governing law into [The Contract](https://agentic-atlas.dev/nodes/contract-documentation).)*
- **Being introductory is a consequence, not the definition.** Prerequisites are what you would teach first — but a node earns residence by being presupposed, not by being introductory.

## Model and claims

[Permalink to Model and claims section](https://agentic-atlas.dev/nodes/foundations#model-and-claims)

### What a skill buys — the floor every family stands on

A skill is a **trade**. Bought: **addressability** (a named handle you invoke on purpose), **replayability** (capture intent once, invoke repeatedly across sessions), **discoverability** (it shows up in the skill list), a **[trigger contract](https://agentic-atlas.dev/glossary/trigger-contract)** (the description says when it fires), and a **composable [seam](https://agentic-atlas.dev/glossary/seam)** (other things can build on the name + contract). Paid: a **namespace slot**, a **line of attention** (the description stays resident so the model can route — the cost [The Context Economy](https://agentic-atlas.dev/nodes/context-economy) prices as propagation scope), and a **maintenance surface** (something now exists to keep correct).

This enumeration is root material because every family presupposes it: each pattern in the tree is a way of making the trade pay better — [Baseline Skill](https://agentic-atlas.dev/nodes/baseline-skill) is the trade at its smallest, and the *the altitude above the single skill (N skills, compounding costs)* is the trade at scale, where N slots compound. A skill that doesn't earn its slot is a bad trade however well it is built.

### The residents — five pillars, the keystone, the baseline

The family settled at **five pillars + the keystone + the baseline** *(2026-07-05; both then-contested residents passed the test)*. Each earns residence its own way:

- **The baseline artifact** — [Baseline Skill](https://agentic-atlas.dev/nodes/baseline-skill): the reference shape (name + description + body) every later pattern is a structural diff against. Prerequisite because a diff needs its base.
- **Two [primitives](https://agentic-atlas.dev/glossary/primitive)** — motivation-agnostic substrates the strategies *wield* rather than apply: [The Contract](https://agentic-atlas.dev/nodes/contract-documentation) (the seam) and [LLM Dispatch](https://agentic-atlas.dev/nodes/llm-dispatch) (the parent-child execution edge). Prerequisite because every family's move creates seams, crosses actor boundaries, or both — and pays off only when they are contracted.
- **Three premises** — facts to internalize, not moves to make:
  - [Statelessness](https://agentic-atlas.dev/nodes/statelessness) — the window is the entire state, re-shipped every call; the fact the context-engineering arithmetic and the verification family's recovery moves both derive from.
  - [Effect Discipline](https://agentic-atlas.dev/nodes/effect-discipline) — which recovery moves a dispatch's effects leave legal; presupposed by verification's discard, persistence's artifacts, and control flow's [gate](https://agentic-atlas.dev/glossary/gate).
  - [Verification Asymmetry](https://agentic-atlas.dev/nodes/verification-asymmetry) — checking ≪ doing, for the covered portion of intent, on external rungs only; presupposed directly everywhere, because every family checks seams.
- **The keystone** — [The Contract Keystone](https://agentic-atlas.dev/nodes/the-contract-keystone): the argument assembled from the pillars. The contract is the possibility condition of checking, the asymmetry its affordability condition, effect discipline the legality of the recovery move. Not another pattern — the argument that makes every other move worth making.

## Scope and boundaries

[Permalink to Scope and boundaries section](https://agentic-atlas.dev/nodes/foundations#scope-and-boundaries)

The test's price is strictness. Each admission is a standing claim that *every* other family depends on the node — so the burden of proof sits with admission, and the family stays small on purpose. What Foundations refuses on principle: prices (taught at [The Context Economy](https://agentic-atlas.dev/nodes/context-economy)), moves (taught in the families that make them), and mechanics (storage, staging layouts — instances, not substrate). The refusals cost cross-references; they buy a root that stays true as the tree grows.

## Implications — the consequence map

[Permalink to Implications — the consequence map section](https://agentic-atlas.dev/nodes/foundations#implications-the-consequence-map)

The test read backwards: which family breaks, and *how it breaks*, when a pillar goes unheld. *(The arrow list settled 2026-07-05; the failure readings — sharpened 2026-08-02 — name each arrow's silent failure.)*

- **Verification ← the asymmetry + the contract + statelessness's feature face.** Unheld: there is nothing declared to check against, and checking isn't known to be affordable — verifiers stack failure instead of compounding reliability.
- **Persistence ← effect discipline + the contract + statelessness.** Unheld: artifacts outlive the run unowned — "discard" quietly means "keep the mess."
- **Context engineering ← statelessness's cost face.** Unheld: the stateful-colleague error — budgeting as if the window persisted, so the re-shipping bill is never priced.
- **Control flow ← effect discipline.** Unheld: gates placed downstream of effects they can no longer revoke.
- **Composition, externalization, distillation ← the contract's seam.** Unheld: their moves multiply seams, and an uncontracted seam moves work around without making any of it checkable.

## Evidence — the test's track record

[Permalink to Evidence — the test's track record section](https://agentic-atlas.dev/nodes/foundations#evidence-the-test-s-track-record)

An admission rule is evidenced by what it discriminates, and this one has run three times with non-default outcomes *(all 2026-07-05)*:

- **One eviction.** The shared-workspace stub failed the test and dissolved — its channel amendment into [LLM Dispatch](https://agentic-atlas.dev/nodes/llm-dispatch), its governing law into [The Contract](https://agentic-atlas.dev/nodes/contract-documentation). This is the externally checkable item: the material demonstrably lives at its two destinations, not here.
- **Two contested admissions.** Both then-contested residents passed under challenge, not by default; their residence arguments stand in *Model and claims*.
- **One demotion.** The introductory role was argued as the family's definition and survived only as a consequence — the test cut a plausible framing, not merely weak content.

## Relationships

[Permalink to Relationships section](https://agentic-atlas.dev/nodes/foundations#relationships)

- **Children:** [Baseline Skill](https://agentic-atlas.dev/nodes/baseline-skill) (with the `tell-me-a-joke` exemplar), [The Contract](https://agentic-atlas.dev/nodes/contract-documentation), [The Contract Keystone](https://agentic-atlas.dev/nodes/the-contract-keystone), [LLM Dispatch](https://agentic-atlas.dev/nodes/llm-dispatch), [Statelessness](https://agentic-atlas.dev/nodes/statelessness), [Effect Discipline](https://agentic-atlas.dev/nodes/effect-discipline), [Verification Asymmetry](https://agentic-atlas.dev/nodes/verification-asymmetry).
- **Where the prices are taught — not here.** The price arithmetic lives at [The Context Economy](https://agentic-atlas.dev/nodes/context-economy) (Context engineering › statics). Foundations holds the substrate *fact* — statelessness — and economy derives the arithmetic from it.

## Lineage

[Permalink to Lineage section](https://agentic-atlas.dev/nodes/foundations#lineage)

The uses relation (Parnas, "Designing Software for Ease of Extension and Contraction", 1979): A uses B when A's function depends on a correct B, so a useful subset holds B without A and none holds A without B. The residence test is that relation over ideas rather than programs; its rejected residual clause is coincidental cohesion (Stevens, Myers & Constantine, 1974) refused by name. Nothing links against a premise, so an unheld one fails silently.

The relationships ledger

Evidence-bearing references

## Relationships

Every connection keeps the section where it was found. The map above orients; this ledger carries the evidence.

### Outbound references 23

1. in-slice · occurrence 1
   [LLM Dispatch](https://agentic-atlas.dev/nodes/llm-dispatch)
   one LLM execution starting another, whether the parent waits, joins later, or never joins
   Evidence: [Definition](https://agentic-atlas.dev/nodes/foundations#definition) · occurrence 1
2. in-slice · occurrence 2
   [The Contract](https://agentic-atlas.dev/nodes/contract-documentation)
   the agreement on an artifact's shape and use whenever one component hands it to another
   Evidence: [Definition](https://agentic-atlas.dev/nodes/foundations#definition) · occurrence 2
3. in-slice · occurrence 1
   [The Context Economy](https://agentic-atlas.dev/nodes/context-economy)
   what each piece of context costs, in quality, dollars, and latency, and who pays
   Evidence: [Model and claims](https://agentic-atlas.dev/nodes/foundations#model-and-claims) · occurrence 1
4. in-slice · occurrence 2
   [Baseline Skill](https://agentic-atlas.dev/nodes/baseline-skill)
   the simplest complete skill, and the starting shape later skill patterns build on
   Evidence: [Model and claims](https://agentic-atlas.dev/nodes/foundations#model-and-claims) · occurrence 2
5. undisclosed · occurrence 3
   Undisclosed relationship
   the altitude above the single skill (N skills, compounding costs)
   Evidence: [Model and claims](https://agentic-atlas.dev/nodes/foundations#model-and-claims) · occurrence 3
6. in-slice · occurrence 4
   [Baseline Skill](https://agentic-atlas.dev/nodes/baseline-skill)
   the simplest complete skill, and the starting shape later skill patterns build on
   Evidence: [Model and claims](https://agentic-atlas.dev/nodes/foundations#model-and-claims) · occurrence 4
7. in-slice · occurrence 5
   [The Contract](https://agentic-atlas.dev/nodes/contract-documentation)
   the agreement on an artifact's shape and use whenever one component hands it to another
   Evidence: [Model and claims](https://agentic-atlas.dev/nodes/foundations#model-and-claims) · occurrence 5
8. in-slice · occurrence 6
   [LLM Dispatch](https://agentic-atlas.dev/nodes/llm-dispatch)
   one LLM execution starting another, whether the parent waits, joins later, or never joins
   Evidence: [Model and claims](https://agentic-atlas.dev/nodes/foundations#model-and-claims) · occurrence 6
9. in-slice · occurrence 7
   [Statelessness](https://agentic-atlas.dev/nodes/statelessness)
   the model keeps nothing between calls, so every turn re-sends and re-reads everything
   Evidence: [Model and claims](https://agentic-atlas.dev/nodes/foundations#model-and-claims) · occurrence 7
10. in-slice · occurrence 8
    [Effect Discipline](https://agentic-atlas.dev/nodes/effect-discipline)
    which recovery moves an agent run's side effects still allow: discard, retry, or compensate
    Evidence: [Model and claims](https://agentic-atlas.dev/nodes/foundations#model-and-claims) · occurrence 8
11. in-slice · occurrence 9
    [Verification Asymmetry](https://agentic-atlas.dev/nodes/verification-asymmetry)
    why checking an answer can be easier than producing it, and when that fails
    Evidence: [Model and claims](https://agentic-atlas.dev/nodes/foundations#model-and-claims) · occurrence 9
12. in-slice · occurrence 10
    [The Contract Keystone](https://agentic-atlas.dev/nodes/the-contract-keystone)
    how contracts, cheap checks, and safe discards together make agent handoffs safe
    Evidence: [Model and claims](https://agentic-atlas.dev/nodes/foundations#model-and-claims) · occurrence 10
13. in-slice · occurrence 1
    [The Context Economy](https://agentic-atlas.dev/nodes/context-economy)
    what each piece of context costs, in quality, dollars, and latency, and who pays
    Evidence: [Scope and boundaries](https://agentic-atlas.dev/nodes/foundations#scope-and-boundaries) · occurrence 1
14. in-slice · occurrence 1
    [LLM Dispatch](https://agentic-atlas.dev/nodes/llm-dispatch)
    one LLM execution starting another, whether the parent waits, joins later, or never joins
    Evidence: [Evidence](https://agentic-atlas.dev/nodes/foundations#evidence-the-test-s-track-record) · occurrence 1
15. in-slice · occurrence 2
    [The Contract](https://agentic-atlas.dev/nodes/contract-documentation)
    the agreement on an artifact's shape and use whenever one component hands it to another
    Evidence: [Evidence](https://agentic-atlas.dev/nodes/foundations#evidence-the-test-s-track-record) · occurrence 2
16. in-slice · occurrence 1
    [Baseline Skill](https://agentic-atlas.dev/nodes/baseline-skill)
    the simplest complete skill, and the starting shape later skill patterns build on
    Evidence: [Relationships](https://agentic-atlas.dev/nodes/foundations#relationships) · occurrence 1
17. in-slice · occurrence 2
    [The Contract](https://agentic-atlas.dev/nodes/contract-documentation)
    the agreement on an artifact's shape and use whenever one component hands it to another
    Evidence: [Relationships](https://agentic-atlas.dev/nodes/foundations#relationships) · occurrence 2
18. in-slice · occurrence 3
    [The Contract Keystone](https://agentic-atlas.dev/nodes/the-contract-keystone)
    how contracts, cheap checks, and safe discards together make agent handoffs safe
    Evidence: [Relationships](https://agentic-atlas.dev/nodes/foundations#relationships) · occurrence 3
19. in-slice · occurrence 4
    [LLM Dispatch](https://agentic-atlas.dev/nodes/llm-dispatch)
    one LLM execution starting another, whether the parent waits, joins later, or never joins
    Evidence: [Relationships](https://agentic-atlas.dev/nodes/foundations#relationships) · occurrence 4
20. in-slice · occurrence 5
    [Statelessness](https://agentic-atlas.dev/nodes/statelessness)
    the model keeps nothing between calls, so every turn re-sends and re-reads everything
    Evidence: [Relationships](https://agentic-atlas.dev/nodes/foundations#relationships) · occurrence 5
21. in-slice · occurrence 6
    [Effect Discipline](https://agentic-atlas.dev/nodes/effect-discipline)
    which recovery moves an agent run's side effects still allow: discard, retry, or compensate
    Evidence: [Relationships](https://agentic-atlas.dev/nodes/foundations#relationships) · occurrence 6
22. in-slice · occurrence 7
    [Verification Asymmetry](https://agentic-atlas.dev/nodes/verification-asymmetry)
    why checking an answer can be easier than producing it, and when that fails
    Evidence: [Relationships](https://agentic-atlas.dev/nodes/foundations#relationships) · occurrence 7
23. in-slice · occurrence 8
    [The Context Economy](https://agentic-atlas.dev/nodes/context-economy)
    what each piece of context costs, in quality, dollars, and latency, and who pays
    Evidence: [Relationships](https://agentic-atlas.dev/nodes/foundations#relationships) · occurrence 8

### Inbound references 4

1. in-slice · occurrence 1
   [Baseline Skill](https://agentic-atlas.dev/nodes/baseline-skill#why-it-matters)
   the ideas every other pattern assumes, and the test for what belongs here
   Evidence: [Why it matters](https://agentic-atlas.dev/nodes/baseline-skill#why-it-matters) · occurrence 1
2. in-slice · occurrence 4
   [Baseline Skill](https://agentic-atlas.dev/nodes/baseline-skill#model-and-claims)
   the ideas every other pattern assumes, and the test for what belongs here
   Evidence: [Model and claims](https://agentic-atlas.dev/nodes/baseline-skill#model-and-claims) · occurrence 4
3. in-slice · occurrence 1
   [Baseline Skill](https://agentic-atlas.dev/nodes/baseline-skill#scope-and-boundaries)
   the ideas every other pattern assumes, and the test for what belongs here
   Evidence: [Scope and boundaries](https://agentic-atlas.dev/nodes/baseline-skill#scope-and-boundaries) · occurrence 1
4. in-slice · occurrence 1
   [Baseline Skill](https://agentic-atlas.dev/nodes/baseline-skill#relationships)
   the ideas every other pattern assumes, and the test for what belongs here
   Evidence: [Relationships](https://agentic-atlas.dev/nodes/baseline-skill#relationships) · occurrence 1

[↑ back to the top](https://agentic-atlas.dev/nodes/foundations#content) [← the survey](https://agentic-atlas.dev/atlas)

Node foundations · corpus 78c0e17 · Catalog revision e0cb75881244b1a82193ca738b82a0d508dd62e822524ae82873ec79d51dbb61