Claude Architect · Ders

Alt Aracılar Geçmişi Devralmaz

Gereken tüm bağlamı her alt aracı istemine açıkça aktarın.

Alt Aracılar Geçmişi Devralmaz, CoddyKit'te ücretsiz bir Claude Architect dersidir. Bu, 4 dersinin 3. dersidir. Aşağıdan dersin tamamını ücretsiz okuyabilir, sonra tarayıcıda yerleşik kod editörü ve 7/24 yapay zeka koçu ile uygulamalı olarak pratik yapabilirsin. Bu, Claude Architect öğrenme yolunun bir parçasıdır ve ilerlemeniz web ve CoddyKit uygulaması arasında senkronize olur. Claude Architect kursu toplamda 4 dersten oluşur.

Bu dersin bazı bölümleri henüz çevrilmemiş olup İngilizce olarak gösterilmektedir.

The Memory Trap

You build a hub-and-spoke multi-agent system. The coordinator has had a long conversation with the user: requirements, constraints, prior decisions. Then it delegates a task to a subagent and assumes the subagent already "knows" all of that.

It does not. This is the single most common multi-agent bug, and it appears directly on the Claude Certified Architect exam.

The rule: subagents do NOT inherit the coordinator's conversation history. Every piece of context a subagent needs must be passed explicitly in its prompt.

Why History Doesn't Transfer

The Claude API is stateless. The model keeps NO server-side memory between requests. On every turn you resend the FULL messages history yourself.

A subagent runs as its own independent loop, with its own messages array. The coordinator's history lives in the coordinator's request, not in some shared global memory. Nothing copies it across.

So when a subagent starts, its context is exactly what you put in its system prompt and first messages entry — and nothing more.

# Each agent owns its own messages array.
# Nothing is shared automatically between them.
resp = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=2048,
    system=subagent_system_prompt,   # subagent's OWN instructions
    messages=subagent_messages,      # subagent's OWN history (starts empty)
)

Hub-and-Spoke, Restated

In the hub-and-spoke pattern the coordinator decomposes the work, delegates to subagents, then aggregates and routes the results. It owns orchestration and error handling.

But delegation is a one-way handoff of explicit instructions, not a shared brain. Think of each subagent as a brand-new contractor who has never seen your earlier emails. You must brief them fully in the work order itself.

Coordinator: decompose, delegate, aggregate, route, handle errors.
Subagent: receives a self-contained brief, does one focused job, returns a result.

The Failure Mode

Here is what the bug looks like in practice. The user told the coordinator the target is the checkout service and the deadline is strict. The coordinator then spawns a reviewer subagent with a vague brief.

The subagent has no idea which service, which constraints, or what "the file" refers to. It hallucinates a target, reviews the wrong thing, or asks a question the coordinator can't relay back cleanly.

# ANTI-PATTERN: assumes the subagent 'remembers' the chat
Task(
    description="Review the file",
    prompt="Review the file we discussed and flag any bugs.",
    subagent_type="code-reviewer",
)
# 'the file we discussed' means NOTHING to a fresh subagent.

The Fix: Self-Contained Briefs

Rewrite the brief so it stands entirely on its own. Pass the target, the constraints, the prior decisions, and the exact output you expect.

A good subagent prompt answers: What is the task? On what exact input? Under what constraints? In what output format? No reference to "earlier" or "as we said" survives the handoff.

Task(
    description="Review checkout/payment.py",
    prompt=(
        "Review the file checkout/payment.py for correctness bugs.\n"
        "Context: this handles card charges; idempotency is required.\n"
        "Prior decision: refunds over $500 must route to a human.\n"
        "Flag a comment ONLY when it contradicts the code.\n"
        "Return findings as a JSON list of {line, severity, issue}."
    ),
    subagent_type="code-reviewer",
)

Pass Facts Verbatim, Not Vibes

Don't summarize transactional facts into mush before handing them off. Progressive summarization makes numbers, percentages, and dates vague — and a subagent acting on "roughly last quarter" instead of "2026-Q1" will be wrong.

Keep the hard facts a subagent needs in a verbatim "context" block: IDs, thresholds, file paths, exact dates. Summarize prose for flavor; never summarize the load-bearing details.

context_block = (
    "CASE FACTS (verbatim):\n"
    "- customer_id: CUS-88231 (identity verified)\n"
    "- order_id: ORD-55012\n"
    "- refund_amount: $512.00  (exceeds $500 policy threshold)\n"
    "- requested_date: 2026-06-10\n"
)
subagent_prompt = context_block + "\nTask: draft the refund-approval request."

Least Privilege Travels With the Brief

An AgentDefinition carries: name, description, system_prompt, and allowed_tools. Because the subagent is isolated, its tools and its system prompt ARE its whole world — scope them to the role.

Give a subagent the 4-5 tools it actually needs (4-5 per agent is optimal; 18+ degrades tool selection). And remember: for the coordinator to spawn subagents at all, the coordinator's allowedTools must include "Task".

reviewer = AgentDefinition(
    name="code-reviewer",
    description="Reviews one file for correctness bugs; returns JSON findings.",
    system_prompt=(
        "You review a single file. All needed context is in the user "
        "message. Never assume prior conversation exists."
    ),
    allowed_tools=["Read", "Grep"],   # least privilege
)

Parallel Subagents Are Fully Independent

Issuing multiple Task calls in a single response runs them in parallel. That is powerful — but it doubles down on the isolation rule.

Parallel subagents cannot see each other's history OR the coordinator's. Each must be briefed independently and completely. There is no implicit ordering and no shared scratchpad between them; if subagent B needs subagent A's output, the coordinator must collect A's result and feed it into B's prompt explicitly.

# Two Task calls in ONE response -> run in parallel, fully isolated.
# Each gets its OWN complete brief; neither sees the other's.
Task(prompt=brief_for_auth_module, subagent_type="code-reviewer")
Task(prompt=brief_for_billing_module, subagent_type="code-reviewer")

Returning Results: Structured, Not Chatty

Isolation also shapes the return trip. The coordinator only gets back what the subagent emits — so make that emission machine-usable.

For aggregation, force structured output: a subagent with tool_choice="any" MUST call a tool, which guarantees the coordinator receives parseable JSON instead of free prose it has to scrape. And when a subagent fails, it should return structured context (failure type, attempted query, partial results) — not a generic "operation failed" that blocks recovery.

resp = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    system=subagent_system_prompt,
    messages=subagent_messages,
    tools=[report_findings_tool],
    tool_choice={"type": "any"},   # guarantees a structured result back to the hub
)

Sessions Are Not a Loophole

You might hope a resumed session smuggles history into a subagent. Be careful. --resume <name> continues a named session and fork_session branches from a shared point — but these resume a session's own state, they do not retroactively inject the coordinator's chat into a fresh subagent.

And resumed tool results can be stale if the codebase changed underneath them. Sometimes a fresh session seeded with a structured summary beats resuming — which is exactly the explicit-context discipline again.

A Practical Briefing Checklist

Before you spawn any subagent, confirm its prompt is self-contained. Walk this checklist:

Target: the exact file / record / id it operates on.
Constraints: policies, thresholds, prior decisions — verbatim.
Task: one focused job, stated with explicit criteria.
Output: the exact shape to return (JSON schema / fields).
Tools: only the 4-5 it needs, least privilege.

If you removed the coordinator entirely and handed this prompt to a stranger, could they do the job? If yes, you've briefed it correctly.

Quick Check: The Forgetful Subagent

A coordinator has spent 20 turns clarifying that the user wants a security review of auth/session.py, with the rule "only flag findings that are exploitable in production." It now delegates to a reviewer subagent. What is the correct way to delegate?

Recap: Brief Every Subagent Fully

Key takeaways:

The API is stateless and subagents are isolated — they inherit none of the coordinator's history.
Every subagent prompt must be self-contained: target, constraints, task, output format, tools.
Pass transactional facts (ids, thresholds, dates, paths) verbatim; don't let summarization blur them.
Parallel Task calls are independent — brief each one separately; the coordinator feeds one subagent's output into another explicitly.
Scope allowed_tools to the role (4-5 optimal); the coordinator needs "Task" to delegate.
Use tool_choice="any" for structured returns and structured errors for recoverable aggregation.

Brief the stranger, not the friend. That mindset passes both the exam and production.

Sıkça Sorulan Sorular

“Alt Aracılar Geçmişi Devralmaz” dersi ücretsiz mi?

Evet — “Alt Aracılar Geçmişi Devralmaz” dersin tüm metni burada web'de ücretsiz olarak okunabilir. Etkileşimli olarak pratik yapmak (yerleşik kod editörü ve 7/24 yapay zeka koçu) ve Claude Architect kursunun geri kalanını açmak için CoddyKit PRO'ya yükselt. Claude Architect kursu toplamda 4 dersten oluşur.

“Alt Aracılar Geçmişi Devralmaz” dersinde ne öğreneceğim?

Gereken tüm bağlamı her alt aracı istemine açıkça aktarın. Claude Architect ile uygulamalı kodu tarayıcıda doğrudan çalıştırarak pratik yaparsın ve 7/24 yapay zeka koçu dersi çalışırken sorularını yanıtlar.

Claude Architect öğrenmeye başlamak için deneyim gerekli mi?

Önceden deneyim gerekmez. CoddyKit'te Claude Architect, başlangıçtan ileri seviyeye kadar yapılandırıldığı için buradan başlayabilir veya başından başlayıp kendi hızında ilerleme yapabilirsin. Bu, 4 dersinin 3. dersidir.

“Alt Aracılar Geçmişi Devralmaz” dersi ne kadar sürer?

Çoğu CoddyKit dersi yaklaşık 5–10 dakika sürer. Her biri kısa ve etkileşimli olduğu için sabit ilerleme yaparsın ve web ile uygulama arasında tam olarak bıraktığın yerden devam edebilirsin.

Bu Claude Architect dersinde kod yazıp çalıştırabilir miyim?

Evet. Her Claude Architect dersi yerleşik bir kod editörü içerir, bu sayede tarayıcıda gerçek kod yazıp çalıştırabilir ve anlık yapay zeka geri bildirimi alırsın — yerel kurulum gerekli değildir.

Bu kursun tüm dersleri

← Claude Architect Sayfasına Dön