Anthropic distinguishes “workflows,” in which language models and tools are orchestrated through predefined code paths, from “agents,” in which models “dynamically direct their own processes and tool usage”; it says agents are “typically just LLMs using tools based on environmental feedback in a loop.”

SocioLens project,

Claim LD01-SL-C13 (v1.0)

Research opportunities this claim motivates

What this claim leaves open for research. Each is a hypothesis about a gap, not a finding.

When AI output goes wrong at work, who answers for it?A developer defines agents by control flow and markets them as such.

Provenance and status

Claim type: Fact
Publication status: Eligible for publication, with qualifiers: source position
Verification state: Checked against the primary source. Who checked this claim is not recorded for it; claim checks so far were AI-led, and no person has checked claims against their sources.
Does not license: Evidence that such systems are agents in any stronger sense
Limitations: An engineering post, not research; read as served on 16 October 2026, a revised page that mentions later products (Claude Haiku 4.5, the Agent SDK); the December 2024 text was not compared; under this definition almost any model in a loop is an agent
Source (as cited): Anthropic, “Building effective agents,” Anthropic engineering post, 19 December 2024, as served on 16 October 2026
Source type: Vendor or company document (recorded as “AI developer web page”)
Institutional position: AI developer self-report (Anthropic, the developer of the model that drafted this debate, which sells agent products)
Maturity of the evidence: Emerging evidence
Recorded date: 16 October 2026
Currentness / correction: This is the current version. No correction or concern is recorded on its sources.

Sources this version cites

Anthropic, “Building effective agents,” Anthropic engineering post, 19 December 2024, as served on 16 October 2026 (Vendor or company document)
Read the original

Version

This is the current version, v1.0. Earlier versions stay available, and their records never change.

Versions: v1.0 · current

Raw record: every recorded field, with its coded values

All 25 canonical Claim fields, verbatim, with the coded values derived from them. The plain-language labels above are read from these.

Claim type (coded): FACT (as printed: “FACT”)
Publication status (coded): ELIGIBLE (SOURCE_POSITION) (as printed: “ELIGIBLE WITH SOURCE-POSITION QUALIFIER”)
Verification state (coded): CONTENT_VERIFIED_PRIMARY
Source type (coded): VENDOR_PRIMARY
Maturity (coded): EMERGING

#	Canonical field	Canonical value (verbatim)	Normalized (Claim Value Vocabulary v1.0.2)
1	CLAIM ID	LD01-SL-C13	—
2	PUBLIC-FACING CLAIM	Anthropic distinguishes “workflows,” in which language models and tools are orchestrated through predefined code paths, from “agents,” in which models “dynamically direct their own processes and tool usage”; it says agents are “typically just LLMs using tools based on environmental feedback in a loop.”	—
3	CLAIM TYPE	FACT	base_types: FACT
4	RESEARCH STRAND	A — What each account says generative AI is, and what it predicts	—
5	MATURITY	EMERGING	states: EMERGING
6	SOURCE	Anthropic, “Building effective agents,” Anthropic engineering post, 19 December 2024, as served on 16 October 2026	source_ids: SRC-SL-ANTHROPIC-BUILDING-EFFECTIVE-AGENTS-2024-12-19
7	SOURCE TYPE	AI developer web page	classes: VENDOR_PRIMARY
8	INSTITUTIONAL POSITION	AI developer self-report (Anthropic, the developer of the model that drafted this debate, which sells agent products)	—
9	SCOPE	One developer’s engineering guidance, December 2024	—
10	DESIGN	Engineering recommendations	—
11	SAMPLE / DATASET	Not applicable	—
12	MODEL / TOOL / VERSION	Claude models and agent frameworks	—
13	COMPARATOR	Workflows with predefined code paths	—
14	MAIN RESULT	“Agent” is defined by control flow; the post warns of higher costs and “compounding errors” and recommends extensive testing in sandboxed environments	—
15	INFERENTIAL TARGET	How one developer uses the word “agent”	—
16	DOES NOT LICENSE	Evidence that such systems are agents in any stronger sense	—
17	VERIFICATION STATE	CONTENT VERIFIED	state: CONTENT_VERIFIED_PRIMARY · verified_by: UNKNOWN
18	LIMITATIONS	An engineering post, not research; read as served on 16 October 2026, a revised page that mentions later products (Claude Haiku 4.5, the Agent SDK); the December 2024 text was not compared; under this definition almost any model in a loop is an agent	—
19	CONTRADICTORY / SUPPORTING SOURCES	LD01-SL-C10, LD01-SL-C12	—
20	GEOGRAPHY / LANGUAGE	Global / English	—
21	DISTRIBUTIONAL LEDGER	Not analysed in this claim	—
22	R01 / FIELD-MAP LINKS	LD-01, T4, D1	—
23	WHAT WOULD CHANGE THIS CLAIM?	A revised definition from the developer	—
24	PUBLICATION STATUS	ELIGIBLE WITH SOURCE-POSITION QUALIFIER	state: ELIGIBLE · qualifiers: SOURCE_POSITION
25	RECORDED DATE	2026-10-16	—

Field 22 references resolved against Field Map v0.2: LD-01 (LIVING_DEBATE); T4 (TENSION); D1 (DOMAIN)

The sources as recorded, with their record IDs and coded source types:

Pinned Sources (field 6, version-specific)

“Anthropic, “Building effective agents,” Anthropic engineering post, 19 December 2024, as served on 16 October 2026” → Anthropic (2024), “Building effective agents” (SRC-SL-ANTHROPIC-BUILDING-EFFECTIVE-AGENTS-2024-12-19--v1.0) — Anthropic, “Building effective agents,” Anthropic engineering post, 19 December 2024, as served on 16 October 2026; class VENDOR_PRIMARY (explicit public provenance pin)

Cited by Living Debate versions

What kind of thing is generative AI, and does the answer predict anything? (v0.1) LD-01

Cite this page

SocioLens project. (2026, October 16). Anthropic distinguishes “workflows,” in which language models and tools are orchestrated through predefined code paths, from “agents,” in which models “dynamically direct their own processes and tool usage”; it says agents are “typically just LLMs using tools based on environmental feedback in a loop.” [Claim LD01-SL-C13, version v1.0]. SocioLens. https://sociolens-web.pages.dev/claims/ld01-sl-c13/v1.0/

@misc{sociolens_ld01_sl_c13_v1_0,
  author = {{SocioLens project}},
  title = {Anthropic distinguishes “workflows,” in which language models and tools are orchestrated through predefined code paths, from “agents,” in which models “dynamically direct their own processes and tool usage”; it says agents are “typically just LLMs using tools based on environmental feedback in a loop.”},
  year = {2026},
  date = {2026-10-16},
  howpublished = {\url{https://sociolens-web.pages.dev/claims/ld01-sl-c13/v1.0/}},
  note = {Claim LD01-SL-C13, version v1.0}
}

The link points to this version, whose record never changes. For a finding, cite the original study as well: SocioLens summarizes research and does not replace it.

Research-of-record provenance

Materialized by sociolens-materializer 0.6.0 at 2026-09-28T20:00:00.000Z; normalization contract SocioLens — Claim Value Vocabulary v1.0.2 — Pre-Spike Materialization Contract (v1.0.2). Content seal SHA-256 e11f8a19c745b0c558a438bb4d8885a12e2b0ab898bfaf0461cdee2127678c74.

Repository-authored inputs (not Drive exports)

SocioLens claim — LD01-SL-C13 v1.0 (v1.0) — written in the SocioLens repository by Project Lead (Claude, AI) on 2026-10-16; no Drive identity exists. Authority: AGENTS.md "Authority" (the Project Lead decides research content within the research-integrity rules) and the Owner's choice in the SocioLens project chat on 16 October 2026 to build the LD-01 debate; a new Claim, first version, written from the project's LD-01 source notes, checked against full texts, official web pages or official abstracts. Block “ENTRY 13 — LD01-SL-C13” SHA-256 73ae271db7ca5a62c52b7b695549e505042fde5b152dcbc50d31a9f63d361aea; fixture fixtures/authored/claims/LD01-SL-C13--v1.0.

Builder decisions (not Drive data)

VERSION = v1.0 — basis: Claim version taken from the repository-authored claim fixture version (SocioLens claim — LD01-SL-C13 v1.0); the first version of a new Claim of the LD-01 debate
CURRENT_POINTER = true — basis: repository-authored claim "SocioLens claim — LD01-SL-C13 v1.0" (Project Lead (Claude, AI), 2026-10-16); basis: AGENTS.md "Authority" (the Project Lead decides research content within the research-integrity rules) and the Owner's choice in the SocioLens project chat on 16 October 2026 to build the LD-01 debate; a new Claim, first version, written from the project's LD-01 source notes, checked against full texts, official web pages or official abstracts
FIELD_6_SOURCE_REFERENCE = SRC-SL-ANTHROPIC-BUILDING-EFFECTIVE-AGENTS-2024-12-19--v1.0 — basis: field 6 of ENTRY 13 — LD01-SL-C13 cites "Anthropic, “Building effective agents,” Anthropic engineering post, 19 December 2024, as served on 16 October 2026"; the only field-6 segment of this ClaimVersion's repository-authored ledger block.
SOURCE_PROVENANCE_PIN = SRC-SL-ANTHROPIC-BUILDING-EFFECTIVE-AGENTS-2024-12-19--v1.0 — basis: explicit version-pinned public provenance of this ClaimVersion (Amendment v1.2 §6): the pinned field-6 Source record "Anthropic, “Building effective agents,” Anthropic engineering post, 19 December 2024, as served on 16 October 2026".