---
type: "post"
id: "a-habr-experiment-compared-a-solo-coding-agent-be4e61"
slug: "a-habr-experiment-compared-a-solo-coding-agent-be4e61"
title: "A Habr experiment compared a solo coding-agent run with a lead agent supported by four read-only subagents on"
description: "The thesis: In this reported coding experiment, dividing investigation among specialized read-only subagents helped the lead agent close one business-logic gap that the solo run missed, but the evidence supports a case-level result rather than a general ranking of agent architectures."
retrieval_nugget: "The thesis: In this reported coding experiment, dividing investigation among specialized read-only subagents helped the lead agent close one business-logic gap that the solo run missed, but the evidence supports a case-level result rather than a general ranking of agent architectures."
published_at: "2026-10-14"
updated_at: "2026-10-14"
record_date: "2026-10-14"
date_kind: "published_at"
topics: ["coding-agents","multi-agent","agents"]
source_urls: ["https://habr.com/ru/companies/koda/articles/1094060?amp%3Butm_medium=rss&amp%3Butm_source=habrahabr"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:a-habr-experiment-compared-a-solo-coding-agent-be4e61"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:45d5e09828efe5971e13e27ae43b59e48a2f8627cec235ff8061c11475c8ab30","reviewed_at":"2026-10-14T22:03:47.409Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"In this reported coding experiment, dividing investigation among specialized read-only subagents helped the lead agent close one business-logic gap that the solo run missed, but the evidence supports a case-level result rather than a general ranking of agent architectures.","observed_facts":[{"text":"The author ran the same payment-incident task against two copies of one local repository, using Koda Pro based on GLM 5.3.","source_urls":["https://habr.com/ru/companies/koda/articles/1094060?amp%3Butm_medium=rss&amp%3Butm_source=habrahabr"]},{"text":"The solo run scored 7/8 on an external hidden HTTP evaluator; the lead-agent-plus-four-subagents run scored 8/8.","source_urls":["https://habr.com/ru/companies/koda/articles/1094060?amp%3Butm_medium=rss&amp%3Butm_source=habrahabr"]},{"text":"Both runs passed their own tests and builds; the solo version returned 200 for a new checkout on a paid order, while the team version returned 409.","source_urls":["https://habr.com/ru/companies/koda/articles/1094060?amp%3Butm_medium=rss&amp%3Butm_source=habrahabr"]}],"mechanism":"The four roles investigated distinct uncertainty areas—frontend retry behavior, payment backend and database transactions, webhook processing, and adversarial QA—and were read-only. The lead agent alone integrated changes. This creates parallel inspection without parallel edits; the external evaluator then tests business behavior beyond the agents' self-reported success.","why_now":"Coding agents are increasingly presented as teams, so the operational question is not simply whether delegation produces more code, but whether it improves discovery and verification on a bounded task.","implications":["For teams testing agent workflows, assign parallel agents to independent risk surfaces and preserve an independent evaluator for business invariants.","Treat this result as a prompt for repeated and cross-project evaluation, not as proof that multi-agent setups generally outperform solo agents."],"evidence_boundary":"This is one author's comparison on one repository and task, with one model configuration and two runs. The different test counts and implementation sizes also make the results unsuitable as a controlled estimate of general multi-agent advantage.","watch_conditions":["A follow-up comparison across multiple repositories and repeated runs would show whether the hidden-test gap persists when task and project variation are introduced."],"related_records":[],"new_branch_reason":"No prior New Runtime record is supplied for this specific experiment; this record captures its bounded external-evaluator result without assuming an existing analytical record."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/a-habr-experiment-compared-a-solo-coding-agent-be4e61/","markdown":"https://newruntime.com/posts/a-habr-experiment-compared-a-solo-coding-agent-be4e61.md","json":"https://newruntime.com/posts/a-habr-experiment-compared-a-solo-coding-agent-be4e61.json"}
related_patterns: ["ai-native-orgs-move-to-review-and-orchestration"]
---

# A Habr experiment compared a solo coding-agent run with a lead agent supported by four read-only subagents on

## Retrieval answer

The thesis: In this reported coding experiment, dividing investigation among specialized read-only subagents helped the lead agent close one business-logic gap that the solo run missed, but the evidence supports a case-level result rather than a general ranking of agent architectures.

The thesis: In this reported coding experiment, dividing investigation among specialized read-only subagents helped the lead agent close one business-logic gap that the solo run missed, but the evidence supports a case-level result rather than a general ranking of agent architectures.

Observed facts: The author ran the same payment-incident task against two copies of one local repository, using Koda Pro based on GLM 5.3. The solo run scored 7/8 on an external hidden HTTP evaluator; the lead-agent-plus-four-subagents run scored 8/8. Both runs passed their own tests and builds. The missed scenario was a new checkout for an already-paid order: the solo version returned 200, while the team version returned 409.

The mechanism: The four roles investigated distinct uncertainty areas—frontend retry behavior, payment backend and database transactions, webhook processing, and adversarial QA—and were read-only. The lead agent alone integrated changes. This creates parallel inspection without parallel edits; the external evaluator then tests business behavior beyond the agents' self-reported success.

Why now: Coding agents are increasingly presented as teams, so the operational question is not simply whether delegation produces more code, but whether it improves discovery and verification on a bounded task.

First implication: For teams testing agent workflows, assign parallel agents to independent risk surfaces and preserve an independent evaluator for business invariants.

The evidence boundary: This is one author's comparison on one repository and task, with one model configuration and two runs. The different test counts and implementation sizes also make the results unsuitable as a controlled estimate of general multi-agent advantage.

First watch condition: A follow-up comparison across multiple repositories and repeated runs would show whether the hidden-test gap persists when task and project variation are introduced.

The broader takeaway is about verification bandwidth, not a blanket recommendation to add agents. Here, an adversarial role anticipated a paid-order edge case, and the evaluator made the difference visible. The new evidence is a concrete hidden-test miss and catch, not a claim that the same arrangement will improve every coding task.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Coding Agents](https://newruntime.com/topics/coding-agents.md): Explore the coding-agents topic hub.
- topic hub: [Multi Agent](https://newruntime.com/topics/multi-agent.md): Explore the multi-agent topic hub.
- topic hub: [Agents](https://newruntime.com/topics/agents.md): Explore the agents topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)