Handle professional tax tasks with AI evaluation

Tackle complex real-world tax workflows using AI agents powered by Surge AI's DAYJOB: Tax benchmark framework. The AI independently investigates, calculates, and delivers professional-standard tax documents or advice from incomplete and conflicting records.

Hacker Newslandonxi

Surge AI DAYJOB: TaxClaude Sonnet 5.5Claude Opus 5.5Claude Fable 5.1

Added 2026-10-31 · originally published 2026-10-28

Steps

1Prepare workspace files containing client requests and supporting records (supporting formats such as PDF, Excel, Word, email, CSV, and images).
2Input the client's initial request into the tax agent (such as tax planning for an individual selling an apartment or asset division issues).
3Have the AI agent review relevant options, calculate potential tax deductions or compliance requirements, and handle conflicting evidence (such as reconciling invoices, cross-state work logs, cross-border, and cryptocurrency records).
4Ask the AI to identify crucial issues the client did not explicitly raise (such as hidden deadlines or legal preconditions like marital status).
5Review the final deliverables output by the AI (such as tax forms, working papers, technical reviews, or client advisory letters) and evaluate them against a 95% accuracy grading rubric.

Ideas for Chinese platforms

This practice can be adapted for automated tax/consulting copywriting on Xiaohongshu or WeChat official accounts, or for complex data organization and information reconciliation workflows on Xianyu, leveraging AI to process multi-source conflicting data and uncover potential risks.

Copy-ready prompt

As a professional tax and financial agent, please handle the following client request: [Enter client's tax consulting request or business background]. Analyze all supporting records provided in the workspace (including [enter file types, such as PDFs, Excel workbooks, receipt photos, logs, etc.]), calculate relevant data, identify hidden potential risks, deadlines, or unstated key assumptions, and provide final professional advice or deliverables.

View original post Hacker News discussion

#AI Agent#Tax Evaluation#Professional Workflow#Prompt Engineering

Create code-rendered videos using Claude Skill

Use the video-director skill to guide Claude Opus 5.5 (in Claude Code) through planning, writing, rendering, and QA-checking short code-rendered videos (HTML/Canvas/SVG converted to MP4). It ensures video quality through a phased workflow, QA scripts, and an evaluation system.

Replicating Stripe's internal AI agent workflow

Handle repetitive tasks using the same AI agent setup used internally by Stripe, reducing task completion time from 20 days to 4 days compared to standard Claude Code. This system is built using over 100 saved prompts (one per step) with multiple agents collaborating to handle the build work.

Build formally verified web apps using Claude and Lean

The author used Claude Opus 5.5 under high-level guidance to develop Lasm, bringing the formally verifiable Lean language to browsers, Node, serverless, and edge environments. This enables developers to build end-to-end web applications with formally verified specifications (such as Express or Hono servers running on Cloudflare Workers).

Found this useful? Get daily updates on Telegram or X.

Join on Telegram Follow @CaiXiang23766

Summarized by AI from the original source - refer to the original post for details. Copyright belongs to the original author.

Steps

Ideas for Chinese platforms

Related use cases