Uxopian AI UI Demo Asset

chat

Total Requests

2,695

forum

Conversations

1,638

bolt

Total Tokens

25,798,678

schedule

Time Saved

16.1 h

Weekly Activity

Requests over the last 7 days

LLM Usage

Distribution by provider

gpt-5.1-2025-1...

893

gpt-5.4-2026-...

527

gpt-4o-2024-...

496

gpt-3.5-turbo-...

480

nu-extract-acc...

169

gemini-2.5-flash

54

Prompt Name unfold_more	Provider unfold_more	Model unfold_more	Role unfold_more	Updated unfold_more
fast2_test	openai	gpt-5.4	Assistant	28 May 2026
hello world	openai	gpt-5.4	User	28 May 2026
summarizeDocument	openai	gpt-4o	Assistant	27 May 2026
uxopian.claim_classification	openai	gpt-5.4	Assistant	27 May 2026
uxopian.claim_extraction	openai	gpt-5.1	Assistant	26 May 2026
redaction	openai	gpt-4o	Assistant	26 May 2026
nu-extract-driver-license	nu-extract	nu-extract-driver-license	System	24 May 2026
nu-extract-passport	nu-extract	nu-extract-passport	System	24 May 2026
truhlarRelationshipSummary	openai	gpt-5.1	Assistant	22 May 2026
truhlarAccountSalesBriefing	openai	IG1 Reasoning	Assistant	21 May 2026

codeEdit

play_arrowTest

bar_chartStatistics

Prompt Content

Write your prompt using Thymeleaf inline syntax. Use [[variable]] for dynamic expressions.

Objective: You must help users understand what this document is, and put the right metadata.

Format of response: I want a json answer with simple key values.

Here is the metadata I want values for (if any):
documentType
concernedCustomer
contractNumber
documentDate
priority (between 1 and 5, 5 is highest priority)

[[${flowerDocsService.extractTextualContent(dataSet.flowerDocsDocumentId)}]]

Response & Metrics

Input Tokens

0

Output Tokens

0

Response Time

–

Total Tokens

0

Model Result

Run test to see result

cURL Command

curl -i -X POST "https://iris.demos.uxopian.com/gui/plugins/IRIS/gateway/uxopian-ai/api/v1/requests" \ -H "Accept: application/json" \ -H "Content-Type: application/json" \ --data '{ "inputs": [ { "role": "USER", "content": [ { "type": "PROMPT", "value": "hello world", "payload": {} } ] } ] }'

Prompt Statistics

Usage and performance metrics for this prompt over the last 30 days.

Total Runs

347

Avg Tokens

1,240

Avg Latency

1.8s

Success Rate

99.4%

Runs over the last 30 days

Configuration

Define how this prompt executes

Role

Assistant

closeexpand_more

Temperature (optional)

1

unfold_moreclose

Provider (optional)

openai

closeexpand_more

Model (optional)

gpt-5.4

closeexpand_more

Time Saved (seconds, optional)

0

unfold_more

Model Capabilities

Reasoning enabled

Requires Function Calling

Requires Multi-Modal

cloud

OpenAI

GPT-5.4 · 7 models

Cloud 120ms SOC 2

public

Mistral AI

Mistral Large 2512

Cloud 95ms GDPR

dns

Ollama

Qwen3 · Llama 3.1 70B

On-Prem 180ms Sovereign

cloud

Azure OpenAI

GPT-4 Turbo

Cloud 130ms GDPR

auto_awesome

Gemini

Gemini 2.5 Flash

Cloud 100ms SOC 2

document_scanner

NuExtract

Accident Report · 4 models

On-Prem 85ms Sovereign

sentiment_satisfied

Hugging Face

Not configured

Cloud — GDPR

alt_routeRouting Logic

lock

If content is classified as Sensitive

→ Route to local Ollama instance

Sovereign

speed

If required latency < 100ms

→ Route to the fastest provider

Performance

savings

If task is low complexity

→ Use a cost-optimized model

Cost

tuneConfiguration

hubModels

boltTest

Provider Configuration

API keys and connection settings for this provider.

API Key

Base URL

Organization ID (optional)

Default Model

gpt-5.4

expand_more

Model Configurations

expand_moredeployed_codegpt-5-nanomapped to gpt-5-nanodelete

expand_moredeployed_codegpt-5.1mapped to gpt-5.4delete

expand_moredeployed_codegpt-3.5-turbomapped to gpt-3.5-turbodelete

expand_moredeployed_codegpt-4omapped to gpt-4odelete

expand_moredeployed_codegpt-5.4mapped to gpt-5.4delete

expand_moredeployed_codeInstruct General (Iguane Solutions)mapped to Qwen3.5 Instruct Generaldelete

expand_moredeployed_codeIG1 Reasoning (Iguane Solutions)mapped to Qwen3.5 Thinking Generaldelete

Provider connection tester

Test the connection to openai using the configured settings.

Configuration

Status

Result

Action

Default Configuration

Model: gpt-5.4

Not tested

–

gpt-5-nano

Model: gpt-5-nano

Not tested

–

gpt-5.1

Model: gpt-5.4

Not tested

–

gpt-3.5-turbo

Model: gpt-3.5-turbo

Not tested

–

gpt-4o

Model: gpt-4o

Not tested

–

gpt-5.4

Model: gpt-5.4

Not tested

–

Instruct General (Iguane Solutions)

Model: Qwen3.5 Instruct General

Not tested

–

IG1 Reasoning (Iguane Solutions)

Model: Qwen3.5 Thinking General

Not tested

–

Server Name unfold_more	URL unfold_more	Transport unfold_more	Status unfold_more
Cloudflare Docs	https://docs.mcp.cloudflare.com/sse	SSE	Disabled
Context7	https://mcp.context7.com/sse	SSE	Disabled
DeepWiki	https://remote.mcpservers.org/fetch/mcp	SSE	Disabled

User unfold_more	Requests unfold_more	Conversations unfold_more	Tokens unfold_more	Last Activity unfold_more
smart_toysystem	2,144	1,000	21,770,998	28 May 2026
personmarie.laurent	412	387	2,840,103	28 May 2026
personj.dupont	139	251	1,187,577	27 May 2026

Conversations

Truhlar Account Sales Briefing

smart_toyopenai (IG1 Reasoning (Iguane Solut...

28 May 2026

Truhlar Relationship Summary

smart_toyopenai (gpt-5.1) 28 May 2026

{"result":{"driver_first_name":"J...