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
| Environment | Shipped | Live | Confirmed | State |
|---|---|---|---|---|
| prod | v1 | – | 2026-09-12 by ci | current |
Definition
- Model
- gemini-2.5-pro
- Provider
- Identity
- unknown
- Principal
- unknown
- Source
- multi_agent_loop_config/writer_agents/critic_agent.yamlADK 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| Platform | Score | Main limitations |
|---|---|---|
| Amazon Bedrock Agents | 50 | model gemini-2.5-pro (google): models not served on Bedrock |
| Microsoft Copilot Studio | 75 | model gemini-2.5-pro (google): other models |
| Salesforce Agentforce | 62 | model gemini-2.5-pro (google): platform-chosen model |
| Google ADK on Vertex AI Agent Engine | Current platform | |
| Databricks (Apps and Genie) | 100 |
History
| When | Event | Environment | Version | Channel | By |
|---|---|---|---|---|---|
| 2026-09-12 18:35 | shipped | prod | v1 | ci |