I Gave My Strategist Agent WebSearch. 5 Topics Took 20 Minutes. Splitting It Into 3 Roles Made It 3.

May 18, 2026 · 1:00 PM UTC ·7 min read · 0 reactions · 0 comments · 22 views

TL;DR · WeSearch summary

The article discusses the author's experience optimizing an AI agent for topic selection. By splitting the task into three distinct roles, the author significantly reduced the time taken for topic selection from 20 minutes to just 3 minutes. The author emphasizes that removing WebSearch from the judgment process improved efficiency and reduced context pollution.

Key facts

▪The original setup involved one agent performing all tasks, which took 20 minutes to select five topics.
▪By dividing the task into three roles, the author reduced the time to 3 minutes and cut token costs by about 60%.
▪The author argues that allowing the judgment agent to use WebSearch leads to inefficiencies and context pollution.

About this source

DEV.to (Top) files mainly under programming. We currently carry 4,924 of its stories.

All DEV.to (Top) coverage →

Original article

DEV.to (Top)

Read full at DEV.to (Top) →

Story provenance

Source · retrieval · rights · ranking — open for full record

inspect →

Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.

Record

Original publisher	DEV.to (Top)
Canonical URL	https://dev.to/kenimo49/i-gave-my-strategist-agent-websearch-5-topics-took-20-minutes-splitting-it-into-3-roles-made-it-3-27na
Publication time	Mon, 18 May 2026 13:00:00 +0000
Retrieval time	2026-05-18T13:04:56.494Z
Last seen	2026-05-18T13:04:56.494Z
Headline source	Publisher (no WeSearch rewrite)
Excerpt source	publisher body
Excerpt method	First ~120 words (~800 chars) of extracted publisher body, fair-use limited.
Summary	WeSearch · cerebras-chat (WeSearch summarizer)
Summary source text	contentText
Citation coverage	Summary is a WeSearch-generated derivative; primary citation is the original publisher URL.
Cluster	7Q7bVQ5RQF9k
Cluster logic	Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison.
Ranking reason	Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking.
Publisher visit	Yes — open original
Substitutes article?	No — link-out required for full text

Rights status (four layers)

Publisher-declared

No publisher-confirmed rights record for this source yet.

Machine-readable

No source-specific machine-readable restriction detected beyond the public feed.

WeSearch interpretation

WeSearch declared handling (basis: Derived from the published RSS/Atom feed). This is WeSearch policy, not a legal grant on the publisher's behalf.

Unknown

Retrieval and training permissions are not asserted unless the publisher confirms them.

WeSearch handling by dimension

Indexing	May the item be indexed (stored, ranked, made findable)?	Allowed
Snippet	May a short excerpt of the publisher's text be shown?	Allowed
AI summary	May WeSearch generate its own short summary of the article?	Limited
Retrieval / RAG	May the content be exposed for third-party retrieval-augmented generation?	Not asserted
Model training	May the content be used to train AI models?	Not asserted
Commercial reuse	May the content be reused commercially?	Not permitted

Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.

Open original publisher → Source rights JSON → Machine-readable provenance → Rights framework → WESEARCH-STORY-PROVENANCE-V1

Opening excerpt (first ~120 words) tap to expand

try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3800250) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Ken Imoto Posted on May 18 • Originally published at kenimoto.dev I Gave My Strategist Agent WebSearch. 5 Topics Took 20 Minutes. Splitting It Into 3 Roles Made It 3. #ai #agents #claudecode #harness I thought one agent doing everything was elegant. One claude -p call, "pick today's topics and write the articles," done. It took 20 minutes to pick 5 topics. Splitting it into three agents took the same job to 3 minutes and dropped token cost by about 60%.

…

Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).

Anonymous · no account needed

Discussion

0 comments