Policy makers/reseachers companion
13 runs
GPT 5.6 Terra
Claude Opus Latest
Gemini Flash Latest
Muse Latest
GPT Sol Latest
GPT Astra Latest
Gemini Pro Latest
GLM 5.3 Flash
GLM-5.3
Inkling
Apertus 70B Instruct • in🇨🇭
Sunflower Chat
Sarvam 105B
Qwen3 Omni
Qwen3.8 Max
Qwen3.8 Flash
Qwen3.8 27B
Qwen3.8-2.4T
Qwen3.7 Plus • in 🇩🇪
Qwen3.7 Plus
GPT-6 Astra
GPT-Realtime-Mini
GPT-Realtime 2.1 Mini
GPT-Realtime 2.1
GPT-Realtime 1.5
GPT OSS 20B • in 🇬🇧
GPT-OSS-120b
GPT-6 Sol
GPT-6 Luna
GPT-6.1 Sol
GPT 5.6 Sol
GPT 5.6 Luna
GPT-5.5 (Thinking)
GPT-5.4 Nano
GPT-5.4 Mini
GPT-4o Mini
GPT-4o
Nemotron Lightning 3.5
Nemotron 3 Ultra
Kimi K3
Mistral Small 4
Mistral Medium 3.5
Mistral Large 4 (Preview)
Mistral Large 3
Ministral 3 14B
MiniMax M3
Muse Wonder
Muse Spark 1.3
Muse Spark 1.2
Muse Glimmer
Dhenu 3 Beta Preview
Gemini 3.8 Flash
Gemma 4 31B
Gemma 4 26B
Gemini 4 Argon
Gemini 3.7 Flash
Gemini 3.6 Flash
Gemini 3.5 Flash
Gemini 3.1 Pro Preview
Gemini 3.1 Flash Live (Voice Only)
Gemini 3.1 Flash-Lite
DeepSeek V4.1 Flash
Claude Sonnet 5
Claude Opus 5.5
Claude Opus 5
Claude Fable 5.1
Claude Fable 5
Claude 4.8 Opus
Claude 4.7 Opus
Claude 4.6 Sonnet
Claude 4.6 Opus
Claude 4.5 Sonnet
SEA-LION v4
Llama3 8B CPT SEA-LIONv2.1 Instruct
AgriLLM Qwen-3 30B
Variables (1)
Show as Links
Add
Add Integrations
✨ Prompt
⏪ Before
⏩ After
FETCH API: Where is ISS?
Log and return variables (Response Only)
Weather Fetcher (Open-Meteo)
African Soil Composition API by ISDA
Get Weather Function
Anthropic JS SDK example
Python Functions
Web Search via Serper.dev API
wa_send_message
slack_send_message
Zapier Webhook + Google Docs
Firebase RTDB POST (with Cryptohash)
Log variables
Save Copilot Data to an External Server Endpoint
Timezone conversion
Current Weather
CryptoJS Sha256 Hashing example
Example POST Request
Functions Minimal Web Request
Plain Text / WhatsApp Symbols + Footnotes
———
Numbers ( [1] [2] [3] ..)
Source Title ( [Source 1] [Source 2] [Source 3] ..)
Source URL ( [https://source1.com] [https://source2.com] [https://source3.com] ..)
Symbols ( [*] [†] [‡] ..)
Markdown ( Source 1 Source 2 Source 3 ..)
HTML ( Source 1 Source 2 Source 3 ..)
Slack mrkdwn ( <https://source1.com|Source 1> <https://source2.com|Source 2> <https://source3.com|Source 3> ..)
Plain Text / WhatsApp ( [Source 1 https://source1.com] [Source 2 https://source2.com] [Source 3 https://source3.com] ..)
Markdown Numbers + Footnotes
HTML Numbers + Footnotes
Slack mrkdown Numbers + Footnotes
Plain Text / WhatsApp Numbers + Footnotes
Markdown Symbols + Footnotes
HTML Symbols + Footnotes
Slack mrkdown Symbols + Footnotes
🔗 Shorten citation links
By default we embed your knowledge files & links and cache their contents for fast responses.
Always Check for Updates
♻️ Refresh Cache
To improve answer quality, pick a synthetic data maker workflow to scan & OCR any images in your documents or transcribe & translate any videos. It also can synthesize a helpful FAQ. Adds ~2 minutes of one-time processing per file.
Default
Direct Upload
Wikipedia to text
Google Drive
Create a synthetic FAQ from a PDF
HVAC Manual & Video Synthetic Data Maker
Youtube Playlist
Hindi Translation
In general, you should not need to adjust these.
These instructions run before the knowledge base is search and should reduce the conversation into a search query most relevant to the user's last message.
Instructions to create a query for keyword/hybrid BM25 search. Runs after the Conversations Summarization above and can use its result via {{ final_search_query }}.
Text Embedding 3 Large (OpenAI)
Text Embedding 3 Small (OpenAI)
Text Embedding Ada 2 (OpenAI)
Mistral Embed (Mistral AI)
E5 large v2 (Liang Wang)
E5 base v2 (Liang Wang)
Multilingual E5 Base (Liang Wang)
Multilingual E5 Large (Liang Wang)
General Text Embeddings Large (Dingkun Long)
General Text Embeddings Base (Dingkun Long)
Weightage for dense vs sparse embeddings. 0 for sparse, 1 for dense, 0.5 for equal weight.Generally speaking, dense embeddings excel at understanding the context of the query, whereas sparse vectors excel at keyword matches.
0
1
0.5
The maximum number of document search citations.
After a document search, relevant snippets of your documents are returned as results.This setting adjusts the maximum number of words in each snippet (tokens = words * 2).A high snippet size allows the LLM to access more information from your document results, at the cost of being verbose and potentially exhausting input tokens (which can cause a failure of the agent to respond).
Your knowledge base documents are split into overlapping snippets.This settings adjusts how much those snippets overlap (overlap tokens = snippet tokens / overlap ratio).In general you shouldn't need to adjust this.
JSON Object
Low
Medium
High