ExcelGPT vs Kiln

ExcelGPT turns plain-language spreadsheet questions into formulas, charts, cleaned data, templates, and analysis workflows. Its formula generator supports more than 400 functions across Excel, Google Sheets, WPS, and LibreOffice Calc. Users can upload spreadsheets and chat across multiple files and sheets to clean, merge, or query data, while Work Agent runs multi-step workflows across files. ChatDB connects to MySQL, PostgreSQL, Supabase, and SQL Server, restricting database work to read-only SELECT queries through a query guard and read-only transaction. Imports include Excel, CSV, ODS, PDF, PNG, and JPG files, with XLSX as an export format. Google Sheets connection is optional and uses per-file OAuth permission; ExcelGPT says it cannot browse or read other Google Drive files. ChatGPT with GPT-4o/GPT-5 is available, alongside Claude, Gemini, and OpenAI workflows. The free plan offers up to 90 credits per month through daily check-in. Pro costs $19.90 a month, and Max costs $29.90 a month. ChatGPT-powered features need a live connection, though the last response is cached for offline reading.

Kiln is an AI workbench for teams building and improving AI systems, with evaluation, fine-tuning, and optimization tools. Users can describe an evaluation goal and generate prompts and synthetic datasets, then compare judge results with human ratings. Kiln supports composing agents and subagents, inspecting tool calls, and evaluating each level of an agent hierarchy. It supports MCP servers and providers including AWS Bedrock, Azure OpenAI, Vertex AI, OpenAI, Anthropic, Fireworks, Gemini, Ollama, and OpenAI-compatible endpoints. Datasets, traces, and evaluations sync to Git. Prompts, outputs, ratings, and fine-tuning jobs are stored as JSON files on the user's filesystem, while provider API calls go directly from the user's machine to the chosen provider. Kiln says it can run fully offline with Ollama, vLLM, Llama.cpp, or another compatible local server. The free Individual plan includes a Python library, source-available desktop app, Git-synced local datasets, rate-limited standard models, and community support.