slavi010/slanai
Blog post of my implementation of AI in Anaplan. Plug Claude, OpenAI etc, have a proposition inside your Anaplan builder page, review, local engine that predict the value before updateing the model. Human validation. Not at all CoModeler, but better.
SUMMARY AI summary by gpt-5-mini
sl-an-ai is an AI-driven tooling stack that lets Anaplan model builders propose, preview, and safely apply structural and formula changes with human review. It targets Anaplan model owners, planners, FP&A teams, and admins who need to evolve large, production models without breaking rollups or downstream logic. Key features: - Browser extension that renders “ghost” rows/columns and a Normal↔Proposed toggle to preview diffs in the live grid. - Human-in-the-loop workflow: agent drafts multi-step changes, shows predicted cell values, and waits for Push or Reject. - Local dry-run calculation engine (slengine) that evaluates formulas and shows blast radius before committing. - MCP agent server exposing tools; interchangeable LLM backends (cloud or local) so data can remain on-prem. - Reverse-engineered APIs layer (JSON-RPC for structural ops, STOMP websocket streaming plus Integration V2) enabling create/edit module/line-item operations and efficient grid access.
DETECTED Detected AI stack
AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.
Why this is classified AI-related
The AI relevance score checks four places for AI keywords and adds the weight of each one that matches. Full methodology
Total AI relevance score: 65 / 100
Owner
Anaplan Solution Architect. Computer Science engineer. pro@slavi.dev
Dates
| Created on GitHub | 2026-05-28 |
| Last push | 2026-05-28 |
| First seen here | 2026-05-28 |
| Last fetched | 2026-08-19 16:21 |