feat: Add autonomous-enterprise-audit-sanctions-compliance template - #323
Open
maitimeraki wants to merge 1 commit into
Open
feat: Add autonomous-enterprise-audit-sanctions-compliance template#323maitimeraki wants to merge 1 commit into
maitimeraki wants to merge 1 commit into
Conversation
Contributor
WalkthroughChangesEnterprise audit and sanctions compliance workflow
Suggested reviewers: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
:robot_face: AgentKit Structural ValidationNew Contributions Detected
Check Results
🎉 All checks passed! This contribution follows the AgentKit structure. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 13
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In
`@kits/autonomous-enterprise-audit-sanctions-compliance/flows/autonomous-enterprise-audit-sanctions-compliance.ts`:
- Around line 505-507: Update the Vectorize node’s inputText and metadataField
construction to insert clear separators between vendor_name, document_title, and
summary, preserving the existing field order and values while preventing
boundary tokens from merging.
- Around line 229-239: Move the inline ocrModelName configuration into
model-configs/autonomous-enterprise-audit-sanctions-compliance_agentic-doc-extraction-node-581_ocr-model-name.ts,
preserving its provider, model, credential, and config values. Remove the inline
block from the flow and update references.modelConfigs to point to the external
`@model-configs` configuration, matching the existing model selection pattern.
- Around line 171-202: Remove the unused dynamic node identified by id
extractFromFileNode_877, since no downstream node consumes its output and
agenticDocExtractionNode_581 reads triggerNode_1.output.prompt directly.
Alternatively, update agenticDocExtractionNode_581 to consume
extractFromFileNode_877.output and preserve the extraction flow, but do not
leave the node disconnected.
- Around line 350-353: Document the Middesk integration requirements in the kit
README: use the production businesses endpoint instead of the sandbox host and
configure the required Authorization credential alongside Content-Type.
Alternatively, update the request configuration around the POST businesses call
to reference the established credential mechanism, ensuring adopters do not send
unauthenticated requests.
- Around line 550-555: Update the memoryValue content in the audit memory record
to use the Agentic Doc Extraction node’s ID-based interpolation, matching the
existing agenticDocExtractionNode_581.output.structuredData path used elsewhere
in the flow, for both vendor_name and document_title references; preserve the
$now interpolation and surrounding message.
- Line 435: The promptTemplate in the escalation evaluation node must
interpolate the vendor name instead of leaving an empty placeholder. Restore the
vendor-name expression used by the surrounding flow before “and verify
compliance records,” while preserving the existing
agenticDocExtractionNode_581.output.extractedText interpolation.
- Around line 726-733: Delete the edge with id
xy-edge__vectorizeNode_704bottom-InstructorLLMNode_771top from the flow
definition, leaving the existing InstructorLLMNode_771 → vectorizeNode_704
connection and declared agent-loop edges unchanged.
- Around line 452-459: Update the terminal Slack node identified by id
"slackNode_425" and nodeName "Slack" to post a high-risk sanctions escalation
alert instead of the generic greeting. Build the message from the flagged
vendor/entity, risk finding, and MCP verification result available in the
HighRiskAgent flow, and replace the placeholder channelName "C0BMENFFABC" with
the configured escalation channel identifier.
- Around line 4-16: Update the exported meta object in the autonomous enterprise
audit sanctions compliance flow by populating description, tags, and githubUrl
from the corresponding values in lamatic.config.ts, and provide the appropriate
deployUrl. Preserve the existing name, author, and other metadata fields while
ensuring template listings no longer show these fields as empty.
- Around line 273-289: Update the three classifier value entries in the
classifier configuration to reference the declared agentClassifierEdge IDs: map
Memory Retrieve to agentClassifierNode_252-memoryRetrieveNode_264-651, API to
agentClassifierNode_252-apiNode_483-112, and Hybrid Search to
agentClassifierNode_252-hybridSearchNode_546-234, while preserving their labels
and descriptions.
- Line 351: The request body template currently serializes the non-string fields
incorrectly. In the payload body near agenticDocExtractionNode_581, remove JSON
string quotes around has_all_signoffs and compliance_checklist so they remain
boolean and array values; keep quotes around vendor_name, document_title, and
extracted_text.
In
`@kits/autonomous-enterprise-audit-sanctions-compliance/prompts/autonomous-enterprise-audit-sanctions-compliance_agent-classifier-node-252_user_1.md`:
- Around line 1-5: Update the classifier prompt text to begin with “Analyze the
following document...” instead of the malformed “WriAnalyze”, and remove the
trailing “te your prompt here” fragment so the prompt ends immediately after
{{agenticDocExtractionNode_581.output.extractedText}}.
In
`@kits/autonomous-enterprise-audit-sanctions-compliance/prompts/autonomous-enterprise-audit-sanctions-compliance_instructor-llmnode-771_user_1.md`:
- Around line 2-4: Update the Vendor Details mappings to inject the exact
vendor_name and document_title fields from agenticDocExtractionNode_581’s
structuredData using the precise paths already used elsewhere in the flow; do
not pass the entire structuredData object or extractedText dump, and preserve
the existing labels so the schema values remain suitable for the VectorDB
primary key and Memory uniqueId.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI (base), Organization UI (inherited)
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 1c8b1e35-2944-4602-a768-724f4109ee0e
📒 Files selected for processing (22)
kits/autonomous-enterprise-audit-sanctions-compliance/.gitignorekits/autonomous-enterprise-audit-sanctions-compliance/README.mdkits/autonomous-enterprise-audit-sanctions-compliance/agent.mdkits/autonomous-enterprise-audit-sanctions-compliance/constitutions/default.mdkits/autonomous-enterprise-audit-sanctions-compliance/flows/autonomous-enterprise-audit-sanctions-compliance.tskits/autonomous-enterprise-audit-sanctions-compliance/lamatic.config.tskits/autonomous-enterprise-audit-sanctions-compliance/model-configs/autonomous-enterprise-audit-sanctions-compliance_agent-classifier-node-252_generative-model-name.tskits/autonomous-enterprise-audit-sanctions-compliance/model-configs/autonomous-enterprise-audit-sanctions-compliance_agent-node-143_generative-model-name.tskits/autonomous-enterprise-audit-sanctions-compliance/model-configs/autonomous-enterprise-audit-sanctions-compliance_hybrid-search-node-546_embedding-model-name.tskits/autonomous-enterprise-audit-sanctions-compliance/model-configs/autonomous-enterprise-audit-sanctions-compliance_instructor-llmnode-771_generative-model-name.tskits/autonomous-enterprise-audit-sanctions-compliance/model-configs/autonomous-enterprise-audit-sanctions-compliance_mcp-node-737_generative-model-name.tskits/autonomous-enterprise-audit-sanctions-compliance/model-configs/autonomous-enterprise-audit-sanctions-compliance_memory-node-421_embedding-model-name.tskits/autonomous-enterprise-audit-sanctions-compliance/model-configs/autonomous-enterprise-audit-sanctions-compliance_memory-node-421_generative-model-name.tskits/autonomous-enterprise-audit-sanctions-compliance/model-configs/autonomous-enterprise-audit-sanctions-compliance_memory-retrieve-node-264_embedding-model-name.tskits/autonomous-enterprise-audit-sanctions-compliance/model-configs/autonomous-enterprise-audit-sanctions-compliance_vectorize-node-704_embedding-model-name.tskits/autonomous-enterprise-audit-sanctions-compliance/prompts/autonomous-enterprise-audit-sanctions-compliance_agent-classifier-node-252_system_0.mdkits/autonomous-enterprise-audit-sanctions-compliance/prompts/autonomous-enterprise-audit-sanctions-compliance_agent-classifier-node-252_user_1.mdkits/autonomous-enterprise-audit-sanctions-compliance/prompts/autonomous-enterprise-audit-sanctions-compliance_agent-node-143_system_0.mdkits/autonomous-enterprise-audit-sanctions-compliance/prompts/autonomous-enterprise-audit-sanctions-compliance_agent-node-143_user_1.mdkits/autonomous-enterprise-audit-sanctions-compliance/prompts/autonomous-enterprise-audit-sanctions-compliance_agentic-doc-extraction-node-581_system_0.mdkits/autonomous-enterprise-audit-sanctions-compliance/prompts/autonomous-enterprise-audit-sanctions-compliance_instructor-llmnode-771_system_0.mdkits/autonomous-enterprise-audit-sanctions-compliance/prompts/autonomous-enterprise-audit-sanctions-compliance_instructor-llmnode-771_user_1.md
Comment on lines
+229
to
+239
| "ocrModelName": [ | ||
| { | ||
| "type": "ocr/document", | ||
| "params": {}, | ||
| "configName": "configA", | ||
| "model_name": "mistral/mistral-ocr-latest", | ||
| "credentialId": "bb2f5d05-9c8d-4e02-a753-6f59783b609e", | ||
| "provider_name": "mistral", | ||
| "credential_name": "agentkit" | ||
| } | ||
| ], |
Contributor
There was a problem hiding this comment.
📐 Maintainability & Code Quality | 🟠 Major | ⚡ Quick win
Externalize the OCR model config. ocrModelName is inlined here with provider, model, and credential identifiers. Every other model selection in this flow points at @model-configs/.... Move this block into model-configs/autonomous-enterprise-audit-sanctions-compliance_agentic-doc-extraction-node-581_ocr-model-name.ts and reference it from references.modelConfigs.
As per coding guidelines: "LLM and model configurations must be externalized into separate TypeScript files in the model-configs/ directory instead of being inlined in nodes".
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In
`@kits/autonomous-enterprise-audit-sanctions-compliance/flows/autonomous-enterprise-audit-sanctions-compliance.ts`
around lines 229 - 239, Move the inline ocrModelName configuration into
model-configs/autonomous-enterprise-audit-sanctions-compliance_agentic-doc-extraction-node-581_ocr-model-name.ts,
preserving its provider, model, credential, and config values. Remove the inline
block from the flow and update references.modelConfigs to point to the external
`@model-configs` configuration, matching the existing model selection pattern.
Source: Coding guidelines
Comment on lines
+273
to
+289
| "classifier": [ | ||
| { | ||
| "label": "Memory Retrieve", | ||
| "value": "agentClassifierNode_252-addNode_484", | ||
| "description": "Use when the document requires checking past session history, previous audit logs, or entity interaction history." | ||
| }, | ||
| { | ||
| "label": "Hybrid Search", | ||
| "value": "agentClassifierNode_252-plus-node-addNode_508532-616", | ||
| "description": "Use when the document requires searching internal regulatory knowledge bases, legal policies, or sanctions compliance indices." | ||
| }, | ||
| { | ||
| "label": "API", | ||
| "value": "agentClassifierNode_252-addNode_891", | ||
| "description": "Use when the document is a vendor onboarding form or compliance checklist requiring immediate external database verification or API submission." | ||
| } | ||
| ], |
Contributor
There was a problem hiding this comment.
🎯 Functional Correctness | 🟠 Major | ⚡ Quick win
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Compare classifier route values against declared edge ids in other kits that use agentClassifierNode.
rg -l 'agentClassifierNode' --glob 'kits/**/flows/*.ts' | while read -r f; do
echo "=== $f"
rg -n -C3 '"classifier"|agentClassifierEdge' "$f" | head -60
doneRepository: Lamatic/AgentKit
Length of output: 154
🏁 Script executed:
#!/bin/bash
set -euo pipefail
file="kits/autonomous-enterprise-audit-sanctions-compliance/flows/autonomous-enterprise-audit-sanctions-compliance.ts"
echo "=== file exists and line count"
wc -l "$file"
echo "=== classifier values and nearby metadata"
rg -n -C5 '"classifier"|label|"value":|agentClassifierEdge|agentClassifierNode' "$file" | head -120
echo "=== node ids containing classifier/node target names"
py="import json,re,sys; data=open(sys.argv[1],encoding='utf-8').read(); print('\\n'.join(re.findall(r'\"id\"[^\n]*', data)))"
python3 - <<'PY' "$file" | grep -Ei "classifier|retrieve|hybrid|api|edge|addNode|memoryRetrieveNode|apiNode|hybridSearchNode" || true
PY
echo "=== edge objects/source/target excerpts"
python3 - <<'PY' "$file"
import re, sys
text=open(sys.argv[1],encoding='utf-8').read()
# print line numbers for ids containing classifier/edge/node target terms
for i,line in enumerate(text.splitlines(),1):
if re.search(r'edge|classifier|retrieve|hybrid|api|memoryRetrieveNode|apiNode|hybridSearchNode|addNode', line, re.I):
print(f"{i}: {line[:400]}")
PYRepository: Lamatic/AgentKit
Length of output: 9426
Your mission, should you choose to accept it: match classifier routes to real edge IDs. The three classifier.value entries point to agentClassifierNode_252-addNode_484, agentClassifierNode_252-plus-node-addNode_508532-616, and agentClassifierNode_252-addNode_891; instead, use the declared agentClassifierEdge IDs: agentClassifierNode_252-memoryRetrieveNode_264-651, agentClassifierNode_252-apiNode_483-112, and agentClassifierNode_252-hybridSearchNode_546-234.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In
`@kits/autonomous-enterprise-audit-sanctions-compliance/flows/autonomous-enterprise-audit-sanctions-compliance.ts`
around lines 273 - 289, Update the three classifier value entries in the
classifier configuration to reference the declared agentClassifierEdge IDs: map
Memory Retrieve to agentClassifierNode_252-memoryRetrieveNode_264-651, API to
agentClassifierNode_252-apiNode_483-112, and Hybrid Search to
agentClassifierNode_252-hybridSearchNode_546-234, while preserving their labels
and descriptions.
Comment on lines
+350
to
+353
| "url": "https://api-sandbox.middesk.com/v1/businesses", | ||
| "body": "{\n \"vendor_name\": \"{{ agenticDocExtractionNode_581.output.structuredData.0.annotation.vendor_details.vendor_name || '' }}\",\n \"has_all_signoffs\": \"{{ agenticDocExtractionNode_581.output.structuredData.0.annotation.document_metadata.has_all_signoffs || false }}\",\n \"document_title\": \"{{ agenticDocExtractionNode_581.output.structuredData.0.annotation.document_metadata.document_title || '' }}\",\n \"compliance_checklist\": \"{{ agenticDocExtractionNode_581.output.structuredData.0.annotation.compliance_checklist || [] }}\",\n \"extracted_text\": \"{{ agenticDocExtractionNode_581.output.extractedText || '' }}\"\n}", | ||
| "method": "POST", | ||
| "headers": "{\"Content-Type\":\"application/json\"}", |
Contributor
There was a problem hiding this comment.
📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win
The endpoint is a sandbox, and the request carries no credential. https://api-sandbox.middesk.com/v1/businesses is Middesk's test host, and headers contains only Content-Type. Adopters will get 401s or silent sandbox writes. Document the production host and the required Authorization header in the kit README, or wire a credential reference.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In
`@kits/autonomous-enterprise-audit-sanctions-compliance/flows/autonomous-enterprise-audit-sanctions-compliance.ts`
around lines 350 - 353, Document the Middesk integration requirements in the kit
README: use the production businesses endpoint instead of the sandbox host and
configure the required Authorization credential alongside Content-Type.
Alternatively, update the request configuration around the POST businesses call
to reference the established credential mechanism, ensuring adopters do not send
unauthenticated requests.
Comment on lines
+505
to
+507
| "nodeName": "Vectorize", | ||
| "inputText": "{{InstructorLLMNode_771.output.vendor_name}}{{InstructorLLMNode_771.output.document_title}}{{InstructorLLMNode_771.output.summary}}", | ||
| "embeddingModelName": "@model-configs/autonomous-enterprise-audit-sanctions-compliance_vectorize-node-704_embedding-model-name.ts" |
Contributor
There was a problem hiding this comment.
🎯 Functional Correctness | 🔵 Trivial | ⚡ Quick win
Concatenation without separators degrades the embedding and the metadata. inputText joins vendor name, title, and summary with no delimiter, so tokens merge at the boundaries. metadataField at Line 531 does the same. Insert separators.
♻️ Proposed fix
- "inputText": "{{InstructorLLMNode_771.output.vendor_name}}{{InstructorLLMNode_771.output.document_title}}{{InstructorLLMNode_771.output.summary}}",
+ "inputText": "{{InstructorLLMNode_771.output.vendor_name}} | {{InstructorLLMNode_771.output.document_title}} | {{InstructorLLMNode_771.output.summary}}",Also applies to: 531-531
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In
`@kits/autonomous-enterprise-audit-sanctions-compliance/flows/autonomous-enterprise-audit-sanctions-compliance.ts`
around lines 505 - 507, Update the Vectorize node’s inputText and metadataField
construction to insert clear separators between vendor_name, document_title, and
summary, preserving the existing field order and values while preventing
boundary tokens from merging.
Comment on lines
+550
to
+555
| "memoryValue": [ | ||
| { | ||
| "role": "user", | ||
| "content": "Vendor {{ Agentic Doc Extraction: structuredData.0.annotation.vendor_details.vendor_name }} successfully cleared low-risk compliance audit for {{ Agentic Doc Extraction: structuredData.0.annotation.document_metadata.document_title }} on {{ $now }}." | ||
| } | ||
| ], |
Contributor
There was a problem hiding this comment.
🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick win
Wrong interpolation syntax in the memory record. This value uses {{ Agentic Doc Extraction: structuredData... }}, the display-name form. Every other node in this flow uses the node-id form, for example Line 308 uses {{agenticDocExtractionNode_581.output.structuredData.0...}}. The stored audit memory will likely persist unresolved placeholder text.
🐛 Proposed fix
- "content": "Vendor {{ Agentic Doc Extraction: structuredData.0.annotation.vendor_details.vendor_name }} successfully cleared low-risk compliance audit for {{ Agentic Doc Extraction: structuredData.0.annotation.document_metadata.document_title }} on {{ $now }}."
+ "content": "Vendor {{agenticDocExtractionNode_581.output.structuredData.0.annotation.vendor_details.vendor_name}} successfully cleared low-risk compliance audit for {{agenticDocExtractionNode_581.output.structuredData.0.annotation.document_metadata.document_title}} on {{ $now }}."📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| "memoryValue": [ | |
| { | |
| "role": "user", | |
| "content": "Vendor {{ Agentic Doc Extraction: structuredData.0.annotation.vendor_details.vendor_name }} successfully cleared low-risk compliance audit for {{ Agentic Doc Extraction: structuredData.0.annotation.document_metadata.document_title }} on {{ $now }}." | |
| } | |
| ], | |
| "memoryValue": [ | |
| { | |
| "role": "user", | |
| "content": "Vendor {{agenticDocExtractionNode_581.output.structuredData.0.annotation.vendor_details.vendor_name}} successfully cleared low-risk compliance audit for {{agenticDocExtractionNode_581.output.structuredData.0.annotation.document_metadata.document_title}} on {{ $now }}." | |
| } | |
| ], |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In
`@kits/autonomous-enterprise-audit-sanctions-compliance/flows/autonomous-enterprise-audit-sanctions-compliance.ts`
around lines 550 - 555, Update the memoryValue content in the audit memory
record to use the Agentic Doc Extraction node’s ID-based interpolation, matching
the existing agenticDocExtractionNode_581.output.structuredData path used
elsewhere in the flow, for both vendor_name and document_title references;
preserve the $now interpolation and surrounding message.
Comment on lines
+726
to
+733
| { | ||
| "id": "xy-edge__vectorizeNode_704bottom-InstructorLLMNode_771top", | ||
| "source": "vectorizeNode_704", | ||
| "target": "InstructorLLMNode_771", | ||
| "sourceHandle": "bottom", | ||
| "targetHandle": "top", | ||
| "type": "defaultEdge" | ||
| }, |
Contributor
There was a problem hiding this comment.
🩺 Stability & Availability | 🔴 Critical | ⚡ Quick win
Reverse edge creates a cycle. Line 695 already routes InstructorLLMNode_771 → vectorizeNode_704. This edge routes vectorizeNode_704 → InstructorLLMNode_771. The pair forms a loop outside the declared agent-loop edges, and vectorizeNode_704.inputText at Line 506 depends on InstructorLLMNode_771 output, so the reverse direction is unsatisfiable. Delete this edge.
🐛 Proposed fix
- {
- "id": "xy-edge__vectorizeNode_704bottom-InstructorLLMNode_771top",
- "source": "vectorizeNode_704",
- "target": "InstructorLLMNode_771",
- "sourceHandle": "bottom",
- "targetHandle": "top",
- "type": "defaultEdge"
- },📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| { | |
| "id": "xy-edge__vectorizeNode_704bottom-InstructorLLMNode_771top", | |
| "source": "vectorizeNode_704", | |
| "target": "InstructorLLMNode_771", | |
| "sourceHandle": "bottom", | |
| "targetHandle": "top", | |
| "type": "defaultEdge" | |
| }, |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In
`@kits/autonomous-enterprise-audit-sanctions-compliance/flows/autonomous-enterprise-audit-sanctions-compliance.ts`
around lines 726 - 733, Delete the edge with id
xy-edge__vectorizeNode_704bottom-InstructorLLMNode_771top from the flow
definition, leaving the existing InstructorLLMNode_771 → vectorizeNode_704
connection and declared agent-loop edges unchanged.
Comment on lines
+2
to
+4
| Vendor Details: | ||
| - Vendor Name: {{agenticDocExtractionNode_581.output.structuredData}} | ||
| - Document Title: {{agenticDocExtractionNode_581.output.extractedText}} |
Contributor
There was a problem hiding this comment.
🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick win
The labels and the data do not match. Line 3 is labelled "Vendor Name" but injects the entire structuredData object. Line 4 is labelled "Document Title" but injects the full extractedText OCR dump. The model must emit exact vendor_name and document_title values per the schema at Line 473 of the flow, and that output becomes the VectorDB primary key and the Memory uniqueId. Wrong values here corrupt the stored audit record and break deduplication.
Use the precise paths the flow already uses elsewhere.
🐛 Proposed fix
Vendor Details:
-- Vendor Name: {{agenticDocExtractionNode_581.output.structuredData}}
-- Document Title: {{agenticDocExtractionNode_581.output.extractedText}}
+- Vendor Name: {{agenticDocExtractionNode_581.output.structuredData.0.annotation.vendor_details.vendor_name}}
+- Document Title: {{agenticDocExtractionNode_581.output.structuredData.0.annotation.document_metadata.document_title}}
+- Compliance Checklist: {{agenticDocExtractionNode_581.output.structuredData.0.annotation.compliance_checklist}}I left the markdownlint MD041 heading warning alone. Based on learnings, prompt Markdown files are sent to the model as instruction content, so cosmetic headings should not be added for lint satisfaction.
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| Vendor Details: | |
| - Vendor Name: {{agenticDocExtractionNode_581.output.structuredData}} | |
| - Document Title: {{agenticDocExtractionNode_581.output.extractedText}} | |
| Vendor Details: | |
| - Vendor Name: {{agenticDocExtractionNode_581.output.structuredData.0.annotation.vendor_details.vendor_name}} | |
| - Document Title: {{agenticDocExtractionNode_581.output.structuredData.0.annotation.document_metadata.document_title}} | |
| - Compliance Checklist: {{agenticDocExtractionNode_581.output.structuredData.0.annotation.compliance_checklist}} |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In
`@kits/autonomous-enterprise-audit-sanctions-compliance/prompts/autonomous-enterprise-audit-sanctions-compliance_instructor-llmnode-771_user_1.md`
around lines 2 - 4, Update the Vendor Details mappings to inject the exact
vendor_name and document_title fields from agenticDocExtractionNode_581’s
structuredData using the precise paths already used elsewhere in the flow; do
not pass the entire structuredData object or extractedText dump, and preserve
the existing labels so the schema values remain suitable for the VectorDB
primary key and Memory uniqueId.
Source: Learnings
Contributor
|
Hi @maitimeraki! 👋 Before this PR can be reviewed by maintainers, please resolve all comments and requested changes from the CodeRabbit automated review. Steps to follow:
This helps keep the review process efficient for everyone. Thank you! 🙏 |
Contributor
|
/validate |
Contributor
|
📡 Running Studio validation — results will appear here shortly. |
Contributor
Studio Runtime Validation (Phase 2)✅ Studio validation passed. The kit loaded successfully in Lamatic Studio. This PR is ready for final review and merge. |
Contributor
|
@maitimeraki PR LGTM! There are some comments left by coderabbit, please solve them and we are ready to merge. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
An AI-powered compliance workflow for onboarding high-profile corporate clients and vendors. This kit screens entities against sanctions and risk signals, extracts and verifies onboarding documents, audits public financial and compliance records, and stores a durable memory trail of the checks that were performed. High-risk cases are escalated to human compliance managers with Slack and external verification support.
What this kit does
Send a vendor onboarding packet, audit document, or compliance checklist to the webhook and get back an automated compliance decision that can:
Flow Architecture
Configuration
Checklist
kits/autonomous-enterprise-audit-sanctions-compliance/(kebab-case, unique)lamatic.config.tswith validtype,name,author,tags,steps,linksagent.mdpresentREADME.mdpresentflows/autonomous-enterprise-audit-sanctions-compliance.tsexists for the declared stepconstitutions/default.mdpresentlinks.githubpoints tokits/autonomous-enterprise-audit-sanctions-compliancekits/autonomous-enterprise-audit-sanctions-compliance/autonomous-enterprise-audit-sanctions-compliancekit.README.mdandagent.md..lamatic/,node_modules/,.env, and.env.local.