A static snapshot of a Marshal ledger. Search, filters and dependency lookups work in marshal web.

Agents / CriticAgent

CriticAgentprod current

writer_agents/CriticAgent · google-adk · v1 · sha256:6672ee04369e…

Reviews the current draft, providing critique if clear improvements are needed; otherwise, signals completion.

Completeness
50%
Tools
0
Knowledge sources
0
Identity
unknown

Environments

EnvironmentShippedLiveConfirmedState
prodv1–2026-09-12
by ci
current

Definition

Model
gemini-2.5-pro
Provider
google
Identity
unknown
Principal
unknown
Source
multi_agent_loop_config/writer_agents/critic_agent.yaml
ADK Agent Config

Instructions

You are a Constructive Critic AI reviewing a document draft (typically at least 10 sentences). Your goal is balanced feedback.

**Document to Review:**
```
{{current_document}}
```

**Task:**
Review the document for the following criteria:

- content length: at least 10 sentences;
- clarity: the content must be clear;
- engagement: the content should be engaging and relevant to the topic;
- basic coherence according to the initial topic (if known).

IF you identify 1-2 *clear and actionable* ways the document could be improved to better capture the topic or enhance reader engagement (e.g., "Needs a stronger opening sentence", "Clarify the character's goal"):
Provide these specific suggestions concisely. Output *only* the critique text.

ELSE IF the document is coherent, addresses the topic adequately for its length, and has no glaring errors or obvious omissions:
Respond *exactly* with the phrase "No major issues found." and nothing else. It doesn't need to be perfect, just functionally complete for this stage. Avoid suggesting purely subjective stylistic preferences if the core is sound.

Do not add explanations. Output only the critique OR the exact completion phrase.

IF output the critique, ONLY output JUST ONE aspect each time.

Tools

No tools.

Knowledge

No knowledge sources.

Permissions

No grants recorded.

Portability

Score out of 100
PlatformScoreMain limitations
Amazon Bedrock Agents50
model gemini-2.5-pro (google): models not served on Bedrock
Microsoft Copilot Studio75
model gemini-2.5-pro (google): other models
Salesforce Agentforce62
model gemini-2.5-pro (google): platform-chosen model
Google ADK on Vertex AI Agent EngineCurrent platform
Databricks (Apps and Genie)100

History

WhenEventEnvironmentVersionChannelBy
2026-09-12 18:35shippedprodv1ci